Google's Gemma 4 E2B: The Ultimate Game Changer in On-Device AI

Have you ever worried about the next billing amount when running a generative AI for long hours? This is especially true since high-performance frontier models can easily run continuously for half a day or more. While we understand the incredible performance they offer, I'm sure many of you are wondering, "Isn't there a way to operate generative AI at a lower cost?" So, today, I would like to introduce "Gemma 4 E2B", an open-weight generative AI that you can download and use right on your local PC.

1. The Highly Anticipated Open-Weight Generative AI from Google: "Gemma 4 E2B"

Various AI companies have released open-weight generative AI models. My personal focus is on the Gemma series from Google, which is now in its 4th generation. It has steadily powered up with each generation, and among them, the performance of the smallest latest version, "Gemma 4 E2B QAT" (1), is particularly outstanding. This time, I built an application that predicts customer churn by combining machine learning with "Gemma 4 E2B QAT."

Here is its GUI. For this version, it features bilingual specifications supporting both English and Malay. This is the screen for training the machine learning model.

　　　　　　　　　　　　　　Model Training Screen (English)]

You can switch it to Malay as shown below. It makes it easy to use even in Kuala Lumpur, the capital of Malaysia!

　　　　　　　　　　　　　　　　Model Training Screen (Malay)

2. Exploring the Probability of Individual Customer Churn

Now, let's get down to business. By inputting individual customer data into the machine learning model, you can calculate the probability of that customer churning. Here, the system is set so that if the probability is 50% or higher, the customer is predicted to churn. The churn probability for the customer shown on this screen is 15.01%, so they were judged as "will not churn."

　　　　　　　　　　　　　　　　　　　Customer Data

What's really important here is the reasoning behind why it decided they wouldn't churn. For this, a metric called SHAP (2) is employed. The graph below shows numerically and visually how much each feature contributed to the decision.

　　　　　　　　　　　　　　　　Churn Probability and SHAP

However, the problem here is that SHAP is mostly well-known only to data scientists, and there's a high chance that ordinary business professionals aren't familiar with it at all. Therefore, simply saying "Please look at this graph" isn't very user-friendly.

This is where today's star, "Gemma 4 E2B QAT," steps in. As shown below, it explains the "basis for the decision" and the "model's accuracy" in plain, easy-to-understand English. With this, even a SHAP beginner can use it with absolute confidence.

　　　　　　　　Explanation of Decision Basis and Model Accuracy (English)

Of course, you can switch this to Malay. Generating this much explanatory text in two languages takes only about 35 seconds on a MacBook Air (M4 24GB). Even on a standard Windows PC, it can often be generated in under 5 minutes. Since "Gemma 4 E2B QAT" is compact, its processing speed is incredibly fast. It is well within practical levels for real-world use.

　　　　　　　　Explanation of Decision Basis and Model Accuracy (Malay)

3. The Quality of the Explanatory Text is Also Excellent

The most important point today is: "How accurate is the text generated by Gemma 4 E2B QAT?"

Small-scale generative AIs often lack the accumulated internal information compared to massive frontier models, so in my past experience, I frequently felt they were difficult to use practically in business. However, with "Gemma 4 E2B QAT," such worries were completely unnecessary. This app can output the prediction results as a PDF, so let's use that to take a closer look.

Here is the SHAP graph that served as the basis for the decision. We naturally want to explain this graph in easy-to-understand English, right?

Here is the explanatory text. What do you think? It's written in clear English, with absolutely no grammatical errors or spelling mistakes. I believe it provides a highly logical explanation based on the SHAP data above. When I first read it myself, I was actually a bit moved, thinking, "Can this little generative AI really do this much?"

So, what do you think? There are zero fees for using generative AI in this app. No invoices will be generated. You can use it freely for as many hours as you like. Isn't that fantastic!

Of course, "Gemma 4 E2B QAT" is not omnipotent, so it is necessary to use it strategically in combination with frontier models like Fable5 depending on the situation. However, I am beyond delighted that this ultra-compact generative AI has become a viable option. I feel we should actively use it while fully leveraging its major advantages: being entirely free and allowing highly confidential information to remain securely locked within your PC.

At Toshi Stats, we will continue to tackle tasks in the marketing field using the power of "Machine Learning + Generative AI." Stay tuned!

1)  Gemma 4 QAT models: Optimizing model compression for mobile and laptop efficiency, 5 June 2026, Olivier Lacombe, Omar Sanseviero, Google DeepMind

2) Welcome to the SHAP documentation

Copyright © 2026 ToshiStats Co., Ltd. All right reserved.

Notice: This is for educational purpose only. ToshiStats Co., Ltd. and I do not accept any responsibility or liability for loss or damage occasioned to any person or property through using materials, instructions, methods, algorithms or ideas contained herein, or acting or refraining from acting as a result of such use. ToshiStats Co., Ltd. and I expressly disclaim all implied warranties, including merchantability or fitness for any particular purpose. There will be no duty on ToshiStats Co., Ltd. and me to correct any errors or defects in the report, the codes and the software.

Beyond the Obvious: Unleashing the Fable5 AI's Blind Spot Pass as a Strategic Secret Weapon!

Anthropic’s new generative AI, Fable5, is available again and is currently being trialed worldwide. I have been taking on new challenges myself, but I often feel that even with ultra-high-performance generative AI, things don't go well if the user's prompts are vague. Rework occurs every single time, and I've constantly wondered, "Isn't there a better way to do this?" Recently, Anthropic engineer Thariq Shihipar shared a brilliant idea (1). This time, I would like to introduce the "Blind Spot Pass"—a method that helps us identify our blind spots in advance—and actually try using it.

1. Reduce the Unknowns

I believe the core of Thariq Shihipar's argument is the "unknown." When starting a project, we don't understand everything from the outset, and there are many unknowns. He categorizes our knowledge as follows:

• Known Knowns: This is essentially what is in my prompt. What do I tell the agent that I want?

• Known Unknowns: What haven't I figured out yet, but I’m aware that I haven’t?

• Unknown Knowns: What's so obvious I’d never write it down, but would recognize it if I saw it?

• Unknown Unknowns: What haven't I considered at all? What knowledge am I not aware of? Do I know how good something can be?

No matter how high-performing Fable5 is, if we—the ones giving the instructions—don't clearly understand what we want to do, we won't be able to push its capabilities to the limit. Therefore, before starting a project, we need to transition from a state of "many unknowns" on the left to a state of "few unknowns" on the right. He outlines a detailed process for this, but I would like to focus specifically on the "Blind Spot Pass," which reduces the "Unknown Unknowns."

2. How to Strategically Use a Customer Churn Prediction Model

Currently, I am developing a "customer churn prediction model" combining machine learning and generative AI, but I am pondering how best to apply it to actual business scenarios. I have thought about various approaches, but that doesn't mean there are no blind spots. So, I would like to immediately apply the "Blind Spot Pass" to Fable5 and uncover these blind spots. The actual method just requires using the following prompt. It's very simple!

“I am looking to develop a new customer churn prediction model to improve my business, but I have no prior knowledge of customer churn prediction or how to practically apply it in a business setting. Please conduct a 'Blind Spot Pass' to identify the relevant 'unknown unknowns' and help me write a better prompt.”

Within minutes, I received the following response. It's amazing!

With blind spots identified in such detail, I can proactively grasp potential stumbling blocks before actually writing the prompts, allowing me to write them much more clearly and effectively. Furthermore, when feedback comes from Fable5, I will be able to respond more accurately. Because the unknowns have been reduced, I can move forward with the project with confidence.

3. The "Blind Spot Pass" is Also Effective for Formulating Management Strategies

Because Thariq Shihipar is an engineer, his discussion centered around coding, but reducing unknowns is crucial in a variety of fields. Especially in management strategy formulation, where uncertainty is high, eliminating blind spots as early as possible is extremely important to prevent failures caused by "unforeseen circumstances." The development of the customer churn prediction model mentioned above shouldn't be viewed merely as a coding task, but rather as an action responding to the major management challenge of "increasing customer retention," making it a significant pillar of management strategy. If we consider management strategy after grasping the 11 points raised earlier, we will undoubtedly be able to build a more effective and refined strategy. I want to actively keep using this. The "Blind Spot Pass" serves as an incredibly reassuring partner, especially when taking on new challenges in uncharted territories.

What do you think? Just by tweaking your prompts slightly, the "Blind Spot Pass" seems poised to deliver tremendous results. Let me conclude with a quote from Thariq Shihipar:

"Fable is the first model where I find the quality of the work is bottlenecked by my ability to clarify its unknowns."

Here at Toshi Stats, we plan to take on various tasks using Fable5. Stay tuned!

You can enjoy our video news “ToshiStats AI Weekly Review” from this link, too!

1)  A Field Guide to Fable: Finding Your Unknowns, 4,July 2026, Thariq Shihipar, Anthropic PBC

Copyright © 2026 ToshiStats Co., Ltd. All right reserved.

Notice: This is for educational purpose only. ToshiStats Co., Ltd. and I do not accept any responsibility or liability for loss or damage occasioned to any person or property through using materials, instructions, methods, algorithms or ideas contained herein, or acting or refraining from acting as a result of such use. ToshiStats Co., Ltd. and I expressly disclaim all implied warranties, including merchantability or fitness for any particular purpose. There will be no duty on ToshiStats Co., Ltd. and me to correct any errors or defects in the report, the codes and the software.

Maximizing Customer Retention: Churn Prevention Strategies Using AI and Machine Learning

It is always sad when customers who have taken the time to purchase our products or services end up leaving. If possible, we want to catch the signs early and take action to prevent them from churning. However, identifying customers who are likely to churn beforehand is no easy task. That is why, this time, I tried creating a customer churn prediction model. I would like to take on the challenge of predicting and countering customer churn using machine learning and generative AI. For formulating the key churn prevention strategies, I used Gemini 3.5 Flash (1), which offers a fantastic balance of performance and cost. Let's get started.

Gemini 3.5 Flash

1. Customer Churn Prediction Model

Using the created customer churn prediction model, let's first take a look at a general customer.

General Customer

The churn probability is 15.0%, indicating a "high likelihood of continuation," so no countermeasures are needed at this time. That's a relief.

SHAP Analysis of a General Customer

At this point, some of you might be wondering, "But why did the model decide that the likelihood of continuation is high?" This is where "SHAP" (2), shown in the figure above, comes into play. Simply put, it is a "value that indicates which data influenced the model's decision and to what extent." The SHAP graph for this customer extends significantly to the left in the negative direction, indicating that the churn probability is low. SHAP values are assigned to individual customers and show why the model made its decision for each specific customer. It is very helpful for us when trying to understand the results.

2. How to Prevent Customer Churn

Now, let's look at a customer who is on the verge of churning. Unlike before, the churn probability is 54.5%, indicating a "high likelihood of churning," which suggests that some countermeasures are necessary.

Customer Likely to Churn

Analysis of a Customer Likely to Churn

SHAP Analysis of a Customer Likely to Churn

You can see that the SHAP graph, unlike the previous one, extends significantly to the right. In particular, tenure and MonthlyCharges are large, serving as the main factors that increased this customer's churn probability.

Also, in the explanatory text for "Individual Customer Analysis," it states:

“To retain this customer, we recommend proactive outreach with a targeted retention offer. Specifically, we can address their high monthly charges by offering a loyalty discount, or incentivize them to transition from a flexible month-to-month contract to a more stable longer-term contract.”

This is a personalized retention measure for this specific customer. It is not a generic strategy. This is because, as stated in the explanation, it was created by the generative AI, Gemini 3.5 Flash, based on the individual customer's analysis results:

“The primary factors driving up their churn risk are their tenure (SHAP: +0.2620), high monthly charges (SHAP: +0.0655), and having a month-to-month contract (SHAP: +0.0311).”

It is trustworthy precisely because it is a measure tailored to the individual customer's situation. Fantastic!

3. For Further Development

In machine learning and AI, the quantity and quality of the input data are always the key. As these increase, diverse analyses become possible, and accuracy improves. In other words, I believe it is possible to elevate this into a marketing analytics platform in the future. I am really looking forward to its future developments. As the core technologies for this product development, I used Google Gemini 3.5 Flash for natural language processing, Choice-Learn for machine learning, and Google ADK for AI agent implementation. For app development, I am using ClaudeCode. These core technologies do not need to be fixed forever; I think it is best to flexibly use or replace them as needed. Since technological advancement is fast, I plan to adopt the optimal tools available at any given time.

What did you think? I felt that with "Machine Learning + AI," we can create fantastic products where they complement each other perfectly. I'm excited about future developments. Here at Toshi Stats, we plan to continue tackling tasks in the marketing field using "Machine Learning + AI." Stay tuned!

You can enjoy our video news “ToshiStats AI Weekly Review” from this link, too!

1) Gemini 3.5 Flash Best for frontier performance across agents and coding,  Google DeepMind
2) Welcome to the SHAP documentation

Copyright © 2026 ToshiStats Co., Ltd. All right reserved.

Notice: This is for educational purpose only. ToshiStats Co., Ltd. and I do not accept any responsibility or liability for loss or damage occasioned to any person or property through using materials, instructions, methods, algorithms or ideas contained herein, or acting or refraining from acting as a result of such use. ToshiStats Co., Ltd. and I expressly disclaim all implied warranties, including merchantability or fitness for any particular purpose. There will be no duty on ToshiStats Co., Ltd. and me to correct any errors or defects in the report, the codes and the software.

Can AI Agents Invent New Economics? The Future of Theory Generation

Economics offers many theories that are highly useful in business. For example, the economic theory awarded the 2020 Nobel Prize in Economics (1) actually made a massive contribution to the design of spectrum allocation auctions in the United States, successfully creating a market worth over 100 billion dollars. Therefore, this time, I created a simple app using the mathematical proof program LEAN (2) to experiment and see if an AI agent using LEAN can be applied to economics. Let's get right into it.

1. Overview of the Developed App

Here is the app's screen. Because of my interest in building new markets, I named it the "Market Designs Verification App." It takes economic propositions and hypotheses and uses LEAN to automatically determine if there are any logical contradictions. I used Google Gemini 3.5 Flash for the natural language processing and Google ADK for the AI agent implementation. For the app development itself, I used Claude Code.

　　　　　　　　　　　　　　　Market Designs Verification App

The proposition provided this time is as follows. It serves as an example of a simple business plan.

"I would like to report on the premise for goal setting for the next business plan. First, as for our current status, we have secured a solid baseline of at least 100 million yen in Annual Recurring Revenue (ARR). Building on this achievement, our policy for the next term is to set our target ARR at 1.7 times our current level (70% growth), aiming for further business expansion.

On the other hand, while pursuing growth, it is also necessary to develop a plan that takes into account the realistic constraints of the business environment. Considering the current framework of our internal budget and the limitations of our target market size, we do not intend to pursue an open-ended target ARR for the next term. Instead, we anticipate aiming for a realistic landing with a maximum cap of 150 million yen."

I want to verify this hypothesis using LEAN to confirm whether it is feasible. Of course, I want to avoid any hallucinations caused by the LLM.

2. Looking at the Analysis Report

When executing this app, the following report was generated in about 3 minutes. Let's take a look. First, the hypothesis, judgment, and conclusion are summarized. The bottom line is that the growth target exceeds the constraints, meaning execution is impossible.

Final Report

The actual verification process using LEAN is displayed. It is a bit complex.

A DAG (Directed Acyclic Graph) is also used. In LEAN, once the compilation finishes, the verification is complete, meaning the proof has been established. Because it is executed strictly, the results are reliable. It is reassuring because there are no hallucinations like those seen with LLMs.

3. Implications Obtained

The implications obtained are as follows:

5. Economic Implication

The three business premises cannot all hold at once. To make the plan feasible, at least one premise must be relaxed. Concretely:

• (a) Relax P1: lower the current-ARR floor 100 to ≤ 88.2353 (start from a smaller base).

• (b) Relax P2: reduce the growth multiplier to ≤ 1.5× (keep multiplier × 100 ≤ 150).

• (c) Relax P3: raise the target-ARR cap 150 to ≥ 170 (revisit budget / market-size constraints).

Based on these results, we must leverage them for business decision-making. This time, the results are well summarized, making them easy to understand. This is where the flexibility of LLMs comes into play. It is reassuring that if we can verify even complex management strategies with LEAN, we can automatically determine whether they can be executed without contradictions. In the future, this is expected to become an excellent advisor in boardroom meetings.

What did you think? It was a simple hypothesis verification, but I believe it is entirely possible to apply LEAN to economics. I felt that combining the flexibility of LLMs with the strictness of LEAN creates a wonderful system where they beautifully complement each other. I am looking forward to future developments. At Toshi Stats, we plan to continue tackling tasks in the field of economics using LLM + LEAN. Stay tuned!

You can enjoy our video news “ToshiStats AI Weekly Review” from this link, too!

1) Stanford Economists Paul Milgrom and Robert Wilson Win the Nobel in Economic Sciences, Stanford Graduate School of Business, Oct 12, 2020
2) LEAN

Copyright © 2026 ToshiStats Co., Ltd. All right reserved.

Notice: This is for educational purpose only. ToshiStats Co., Ltd. and I do not accept any responsibility or liability for loss or damage occasioned to any person or property through using materials, instructions, methods, algorithms or ideas contained herein, or acting or refraining from acting as a result of such use. ToshiStats Co., Ltd. and I expressly disclaim all implied warranties, including merchantability or fitness for any particular purpose. There will be no duty on ToshiStats Co., Ltd. and me to correct any errors or defects in the report, the codes and the software.

Logic-Powered Agents: How LLMs Evolution in Math is Shaping the Future of AGI

On June 3rd, a new research paper (1) was released by Google. It states that difficult mathematical proofs were solved by combining the LLM Gemini 3.1-pro with a mathematical proof language called LEAN (2). This time, I would like to delve into this paper and consider what kind of developments we can expect from this new AI agent in the future, beyond the framework of mathematics.

1. The Synergistic Effect of the LLM's Flexibility and LEAN's Strictness

Here is the paper, featuring an active AI agent called LEAP. It only uses Gemini 3.1-pro as the LLM, and no specific fine-tuning has been performed. It is being used straight out of the box. Even so, it is reported to demonstrate outstanding exploration capabilities in mathematical proofs. Since it doesn't require any particular additional training, it can be used immediately without doing anything, which is very convenient for practical use. Furthermore, by using LEAN in conjunction, if a proof with contradictory logic due to hallucinations is produced, an error occurs during compilation, creating a mechanism where it is automatically rejected.

　　　　　　　　　LEAP (LLM-in-Lean Environment Agentic Prover)

Since LLM responses can fluctuate probabilistically, humans need to verify them in detail when conducting rigorous arguments. However, by introducing LEAN, this process has been automated. This is very reassuring. It seems that this fantastic result was achieved by combining the flexibility of the LLM and the strictness of LEAN in this way. Let's look closer.

2. The Structure and Accuracy of LEAP

Here is the structure of LEAP. The figure on the left is the roadmap for the theorem to be proved using LEAN. Technically, it forms a structure called a DAG (Directed Acyclic Graph). Complex mathematical proofs are not completed in a single attempt; the proof progresses by going back and forth between the LLM and LEAN several times. The key here is the section in the red frame, where the LLM describes an INFORMAL BLUEPRINT in natural language and converts it into a FORMAL SKETCH in LEAN. Furthermore, a two-tier review by LEAN and the LLM awaits. LEAN verifies whether the new proof method has any contradictions, and the LLM's review verifies whether that method is genuinely effective. In other words, the LLM acts as a pilot in the search for proof methods. Even though it's just using Gemini 3.1-pro as is, its potential is truly surprising.

　　　　　　　　　　　　　　　　LEAP workflow

Now, let's look at the results of applying LEAP to an actual task. It tackled the notoriously difficult Putnam 2025. Putnam 2025 contains twelve undergraduate-level problems from the 86th William Lowell Putnam Mathematical Competition, a highly challenging North American mathematics competition.

Looking at the DAG, you can see how the proof actually progresses. In this example of Putnam 2025 Problem A6, you can see layers upon layers of connected proofs. It's certainly a difficult problem. The green indicates the parts that have already been proven.

　　　　　　　　　　　　DAG example for Putnam 2025 Problem A6

The results, as shown below, were that LEAP answered all questions correctly. An overwhelming accuracy.

　　　　　　　　　　　　　　　　Results on Putnam 2025

You can see that while the original Gemini 3.1-pro couldn't score at all, it was able to demonstrate tremendous capabilities by combining it with LEAN. I think it is truly a breakthrough.

3. Beyond Mathematical Proofs into Various Fields

What we have seen so far were tasks related to mathematical proofs. With LEAP being able to construct such perfect logic, I felt it would be a waste to keep it confined solely to mathematics. In particular, its application to economics, which is directly linked to business practices, has immense scope and depth, and I believe it can contribute to expanding the areas where LLMs can be active. Economics is also generally described using mathematical formulas, so I think it has a high affinity with LEAP. A paper (3) on its application to economics has already been published, so if you are interested, please do give it a try.

What did you think? I believe the combination of LLMs and LEAN will be expanded and improved in various ways in the future. It might be stepping closer to AGI. It's very exciting.

At Toshi Stats, we plan to take on tasks in the field of economics moving forward. Stay tuned!

You can enjoy our video news “ToshiStats AI Weekly Review” from this link, too!

1) LEAP: Supercharging LLMs for Formal Mathematics with Agentic Frameworks, 3 Jun 2026, Google
2) LEAN
3) We Can't Agree to Disagree, Formally: Aumann's Theorem and Assumption Accounting in Lean, May 27, 2026, Ruize Chen, Ben Eltschig, Ken Ono, Jujian Zhang  Axiom Math,  Scott Duke Kominers Harvard University; a16z crypto

Copyright © 2026 ToshiStats Co., Ltd. All right reserved.

Notice: This is for educational purpose only. ToshiStats Co., Ltd. and I do not accept any responsibility or liability for loss or damage occasioned to any person or property through using materials, instructions, methods, algorithms or ideas contained herein, or acting or refraining from acting as a result of such use. ToshiStats Co., Ltd. and I expressly disclaim all implied warranties, including merchantability or fitness for any particular purpose. There will be no duty on ToshiStats Co., Ltd. and me to correct any errors or defects in the report, the codes and the software.

"Root Cause Analysis" is All You Need !

Have you ever tried to automate any classification tasks using Generative AI? I do this quite often, but occasionally, as the number of classification classes increases, the accuracy gradually drops to a point where it is no longer viable for practical business use. So, this time, I will tackle the task of classifying bank customer complaints (1) based on their root causes. There are 20 cause classes in total, making it a difficult problem where a random guess would yield only about a 5% accuracy rate. In the example below, the "text" column contains the customer complaint, and the "Issue," which is the underlying cause, is classified by an AI agent.

　　　　　　　　　　　　　　Bank Customer Complaints

We are provided with a mere 100 samples. I would like to implement Root Cause Analysis (RCA) during the classification process to see just how crucial RCA is for improving accuracy. Let's get started right away.

1. What is RCA?

RCA stands for "Root Cause Analysis". When a problem occurs, it is a method used not just to resolve the superficial events (symptoms) you see, but to pinpoint the "true cause (root cause)" in order to prevent a recurrence. This time, I have designed the following RCA approach for classification failures:

Root Cause Analysis (RCA):

• Record the success/failure of each sample.

• Verification: Calculate the accuracy and generate an error analysis report.

• Failure Analysis: If a classification error occurs, scrutinize the principle and conduct a Root Cause Analysis (RCA) on why it failed (e.g., confusion with similar categories, context complexity, etc.).

• Create a principle improvement report based on the failure analysis results. Send this feedback to the generator. Take care to ensure the generator does not overfit.

Now, as shown in the infographic below, let's actually take on the bank customer complaint classification task using an AI agent equipped with RCA capabilities.

　　　　　　　　　　　　　　　AI Agent with RCA Capabilities

Note that I referenced this paper (2) for this experiment. If you are interested, please definitely check it out.

2. Implementing the Bank Customer Complaint Classification AI Agent using Claude Code

Once again, I used Anthropic's Claude Code to implement and analyze the AI agent as follows. First, I set it to Plan Mode, compiled what I wanted to accomplish into a PRD (Product Requirements Document), handed it over to Claude Code, and formulated an implementation plan. This PRD incorporates the Root Cause Analysis (RCA) explained above.

　　　　　　　　　　　　　　Claude Code's Plan Mode

An implementation plan like the one below is formulated in about 5 minutes. The actual document is much longer, but I will only show the first part here. The important thing is to thoroughly review this implementation plan. It is long and can be tedious, but this stage allows you to confirm whether it aligns with the task's objectives before actually diving into coding. Anthropic's generative AI, Opus 4.7, is extremely high-performing; once it enters the implementation phase, it runs non-stop until the end. Since it is difficult for humans to intervene midway, the accuracy of the implementation plan holds the key to solving the task.

　　　　　　　　　　　　　　　Implementation Plan via Plan Mode

Since this implementation plan was well-crafted, I will proceed directly to implementation. I switch to Auto Mode as shown below and start coding. You can see the AI agent completing the implementation process step by step.

　　　　　　　　　　　　　　Implementation via Auto Mode

This time, we iterated on the analysis and improvement 9 times, which ultimately took over 10 hours, but we obtained the results below. This is the result of classifying 100 randomly sampled customer complaints into 20 classes. You can see that the accuracy gradually improves thanks to the RCA feedback.

　　　　　　　　　　　　　　　Accuracy at Each Iteration

However, it seems to have overfitted due to repeating the process for far too long. I validated it with newly sampled data, but saw no improvement from iteration 7 onwards.

　　　　　　　　　　　　　　　　　Accuracy on New Data

3. Results and Challenges This Time

In this bank customer complaint classification task, the baseline accuracy using a generative AI "out of the box" without doing anything special was under 40%. By adopting a multi-agent system with a generator and an evaluator, and incorporating RCA feedback, we achieved just under 60% accuracy even on new data, so I believe the RCA was effective. However, once the accuracy on the original data exceeded 80%, overfitting occurred, so figuring out how to improve this is a future challenge.

What did you think? This time, I explicitly stated the RCA in the PRD, implemented it as a multi-agent system, and tackled the task of classifying bank customer complaints based on their causes. While the accuracy improved from 40% to about 60%, overfitting remained an issue. To aim for an accuracy of 70% or higher on new data, another breakthrough might be necessary.

At ToshiStats, we plan to further develop RCA. Please look forward to it. Stay tuned!

You can enjoy our video news ToshiStats AI Weekly Review from this link, too!

1) Consumer Complaint Database
2) CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification, Hanrong Zhang1∗ Shicheng Fan1∗ Henry Peng Zou1 Yankai Chen2,3
Zhenting Wang2
Jiayu Zhou4 Chengze Li1 Wei-Chieh Huang1 Yifei Yao5
Kening Zheng1 Xue (Steve) Liu2,3 Xiaoxiao Li6 Philip S. Yu1
1University of Illinois Chicago 2MBZUAI 3McGill University
4Columbia University 5Zhejiang University 6University of British Columbia, April 12 2026

Copyright © 2026 ToshiStats Co., Ltd. All right reserved.

Notice: This is for educational purpose only. ToshiStats Co., Ltd. and I do not accept any responsibility or liability for loss or damage occasioned to any person or property through using materials, instructions, methods, algorithms or ideas contained herein, or acting or refraining from acting as a result of such use. ToshiStats Co., Ltd. and I expressly disclaim all implied warranties, including merchantability or fitness for any particular purpose. There will be no duty on ToshiStats Co., Ltd. and me to correct any errors or defects in the report, the codes and the software.

Unlocking Recursive Self-Improvement via Meta-Harness

Recently, discussions on how to significantly improve AI agent performance by optimizing "what information is provided to the agent and at what timing" have been gaining momentum. In this post, based on a recent research paper, we will explore the possibility of "Recursive Self-Improvement of AI Agents," where agents improve their own performance. Let’s dive in.

1. Meta-Harness: A New Methodology for Harness Construction

A paper (1) from Stanford University has introduced a novel approach that significantly boosts accuracy. I believe the two major features are as follows:

• Full access to past information

• Adoption of Claude Code

The paper defines a "harness" as follows:

The performance of large language model (LLM) systems depends not only on model weights, but also on their harness: the code that determines what information to store, retrieve, and present to the model.

Simply put, a harness is the mechanism surrounding the generative AI that controls data to maximize its performance. To build this harness using an AI agent, it seems that maximum data access is required.

By running a loop as shown below, "Recursive Self-Improvement"—where the agent learns from past failures to improve itself—becomes possible.

　　　　　　　　　　　　　　　　　　　Meta-Harness

2. Full Access to Information: The Secret to Improved Accuracy

Previously, there were various methods for constructing harnesses, but humans had to summarize or compress large amounts of information in some form. Consequently, critical information was often lost during the process, creating a bottleneck when aiming for higher accuracy.

"Meta-Harness" addresses this by granting the proposer access to all past logs and files. By allowing the agent to see all information without concealment, this structure eliminates the bottleneck. As a result, it achieved excellent performance on the Pareto frontier, as shown below.

‍　　‍　　　　　　　　　　　　　　　　Pareto Frontier

This graph illustrates the relationship between additional information (context) and accuracy. The closer a point is to the top-left, the higher the accuracy achieved with less information, which signifies superior performance.

3. The Emergence of Claude Code

The proposer plays a central role in "Meta-Harness." Let’s look at the details through pseudo-code, where P represents the proposer. Looking at the section outlined in red, we can see that a new harness is being created by the proposer.

‍　　‍　　　　　　　　　　　　　　　　　Pseudo-code

In this context, the proposer specifically refers to Claude Code. In other words, the new harness is created based on the latent capabilities of Claude Code. While Claude Code is proving active in various fields, it appears here again in a leading role. It is truly impressive. This demonstrates that future AI research will be driven by AI agents like Claude Code at its core. We are truly at the cutting edge of the era.

Conclusion

As we have seen, providing Claude Code with maximum information access enables the construction of high-performance harnesses. Of course, detailed tuning is necessary, so I highly recommend reading the full paper.

At ToshiStats, we will continue to cover harness design, which is the key to improving AI agent accuracy. Stay tuned!

You can enjoy our video news ToshiStats AI Weekly Review from this link, too!

1) Meta-Harness: End-to-End Optimization of Model Harnesses,  Yoonho Lee, Roshen Nair, Qizheng Zhang, Kangwook Lee, Omar Khattab, Chelsea Finn,  Mar 30, 2026

Notice: This is for educational purpose only. ToshiStats Co., Ltd. and I do not accept any responsibility or liability for loss or damage occasioned to any person or property through using materials, instructions, methods, algorithms or ideas contained herein, or acting or refraining from acting as a result of such use. ToshiStats Co., Ltd. and I expressly disclaim all implied warranties, including merchantability or fitness for any particular purpose. There will be no duty on ToshiStats Co., Ltd. and me to correct any errors or defects in the report, the codes and the software.

The Secret Sauce for Mastering Agentic Coding !

Since the beginning of this year, we've been hearing a lot about "agentic coding"—where AI agents handle the coding—everywhere. While we no longer write programs ourselves and instead focus entirely on giving instructions to AI agents via prompts, many people likely find themselves wondering, "What exactly should I learn to write good prompts?" So, today, I'd like to explore this topic using an experiment conducted at ETH Zurich as our guide.

1. Overview of the Experiment

The reference for this discussion is the paper titled "Computer Science Achievement and Writing Skills Predict Vibe Coding Proficiency (1)." They gathered 100 students who first took tests to measure their writing skills, computer science achievement, and general cognitive abilities. I've summarized these three foundational skills below.

‍　　‍　　　　　　　　Three Foundational Skills

Afterward, to measure their "agentic coding" proficiency, the participants reviewed a sample application, drafted prompts for an LLM-based agent, tested the generated application, and then further refined it. The final applications were evaluated by human graders.

　　　　　　　　　Measuring "Agentic Coding" Proficiency

This process reveals the relationship between the three foundational skills and agentic coding proficiency.

2. As Expected, Computer Science Skills Mattered

As the results below show, computer science skills were most strongly correlated with agentic coding proficiency, showing a correlation coefficient of 0.39. Writing skills also showed a significant correlation, with a coefficient of 0.29. Here is a summary of the results.

‍　　‍　　　　　　　　Skills Correlated with Agentic Coding Proficiency

Now, some of you might find this a bit puzzling. Computer science skills are primarily centered around programming, whereas in agentic coding, humans don't actually write code directly. So, why did computer science skills show such a high correlation? The research paper explains it as follows:

"It may have contributed through problem decomposition or mental models of control flow and state."

It's certainly true that people hone these kinds of abilities through the practice of programming. If that's the case, it makes perfect sense that individuals with strong computer science skills would perform well, even in natural language-driven agentic coding.

3. How Those with No Programming Experience Can Become Excellent Agentic Coders

Based on our discussion so far, I'd like to explore a new approach on "how people with no programming experience can become excellent agentic coders." As agentic coding becomes more widespread, it might be inevitable that the incentive to learn traditional programming will fade. However, the following skills are still absolutely essential for mastering agentic coding:

• The ability to decompose tasks

• The ability to understand system flows

• The ability to expand your vocabulary and accurately define requirements in writing

For those without programming experience, deliberately focusing on and studying these specific points alongside your regular prompt writing practice will likely accelerate your improvement. This is something you can start doing right away today. I highly recommend it!

What do you think? While we focused on "agentic coding" today, the insights we've gained go far beyond just "coding"—they can be seen as universal skills for unlocking the true potential of AI agents. As AI agents become integrated into various fields in the future, these skills will essentially become mandatory subjects for all of us. Here at ToshiStats, we will continue to discuss the collaboration between business professionals and AI agents. Stay tuned!

You can enjoy our video news ToshiStats AI Weekly Review from this link, too!

1) Computer Science Achievement and Writing Skills Predict Vibe Coding Proficiency, Sverrir Thorgeirsson, Theo B. Weidmann, Zhendong Su. 14 Mar 2026

Notice: This is for educational purpose only. ToshiStats Co., Ltd. and I do not accept any responsibility or liability for loss or damage occasioned to any person or property through using materials, instructions, methods, algorithms or ideas contained herein, or acting or refraining from acting as a result of such use. ToshiStats Co., Ltd. and I expressly disclaim all implied warranties, including merchantability or fitness for any particular purpose. There will be no duty on ToshiStats Co., Ltd. and me to correct any errors or defects in the report, the codes and the software.

The End of Traditional Research: How "autoresearch" is Changing Everything

"It would be wonderful to have a system where you could give instructions to an AI agent before going to bed, and while you sleep, the AI agent executes the program so that a finished product is ready by the time you wake up in the morning." This is not a story about the future. It is an application called "autoresearch" (1) released on March 6, 2026, and anyone can use it for free. Let’s take a look right away.

1. What is "autoresearch"?

This is a project by the renowned AI researcher Andrej Karpathy. According to his GitHub, it is described as "AI agents running research on single-GPU nanochat training automatically," meaning he has created AI agents that automatically train nanochat (2). Nanochat is a small yet high-performance large language model (LLM) that he developed. Usually, he trains nanochat while manually tuning it, but this is a very ambitious project to automate that process using "autoresearch." According to him, even though it has just begun, "autoresearch" has worked very well. For details, please see his post on X (3).

2. Simple is Best

When you hear about automating the training of a large language model, you might imagine a very complex system, but there are only three basic files. Furthermore, the only file a human needs to write directly is program.md. In this file, you write in natural language, such as English or Japanese, "what kind of research team we want to form by launching multiple AI agents and what we want them to do." No programming is required. The AI agent that receives these instructions autonomously writes code in train.py to improve the accuracy of nanochat. The final file, prepare.py, is never updated during training. It serves as the foundation for the experiment, so it remains the same until the end. It is a very simple structure. I highly recommend checking Andrej Karpathy’s GitHub for the contents of each file; it will be very informative. I have summarized the overview briefly below.

This is the autoresearch repository for Mac that I executed this time. You can certainly see the three files I introduced. The file structure is extremely simple, and I believe anyone can handle it.

3. Running on a MacBook Air

Now, let's run it on my MacBook Air. This Mac was purchased exactly one year ago and is equipped with an M4 chip and 24GB of RAM. Claude Code is active as the development environment once again. It is on duty at our company almost every day.

Claude Code

When I asked Claude Code to draw a diagram, it looked like the one below. It is simple and easy to understand. On the second from the right, it says MLX Train 5m, which means repeating a 5-minute training session many times. It can be executed about 12 times in one hour. On the far right, Evaluate val_bpb means "evaluate the metric val_bpb (validation bits per byte) and check if the value is steadily decreasing." If the value decreases, it means the accuracy is improving. If not, that session is discarded, and training continues from the previous state. If you let this run while you sleep, you can conduct 100 experiments in a single night.

autoresearch Training Process

Andrej Karpathy describes this design as follows: ‘Self-contained. No external dependencies beyond PyTorch and a few small packages. No distributed training, no complex configs. One GPU, one file, one metric.‘

Since I wanted to confirm if it would work properly this time, I ran the loop only three times. As seen below, the evaluation metric did indeed decrease, showing that the training progressed smoothly. During this time, I gave no instructions at all. It’s amazing. It truly is "autoresearch"!

Trends in Evaluation Metric Values

What did you think? Andrej Karpathy stated on his X (3) account:

“All LLM frontier labs will do this. “,

“any metric you care about that is reasonably efficient to evaluate (or that has more efficient proxy metrics such as training a smaller network) can be autoresearched by an agent swarm. It's worth thinking about whether your problem falls into this bucket too.”

You, too, might be able to create your own AI lab using a Mac. It is a wonderful thing. At ToshiStats, we will continue to conduct experiments incorporating cutting-edge technology. Stay tuned!.

You can enjoy our video news ToshiStats AI Weekly Review from this link, too!

1) autoresearch, Andrej karpathy, March 6, 2026
2) nanochat, Andrej karpathy, Oct13,2025
3) https://x.com/karpathy/status/2031135152349524125

Notice: This is for educational purpose only. ToshiStats Co., Ltd. and I do not accept any responsibility or liability for loss or damage occasioned to any person or property through using materials, instructions, methods, algorithms or ideas contained herein, or acting or refraining from acting as a result of such use. ToshiStats Co., Ltd. and I expressly disclaim all implied warranties, including merchantability or fitness for any particular purpose. There will be no duty on ToshiStats Co., Ltd. and me to correct any errors or defects in the report, the codes and the software.

Many-Shot In-Context Learning: The Game Changer of the Long-Context AI Era

Recently, OpenAI released its newest AI model, GPT-5.4 (1). While much of the praise has focused on its overall performance, I want to highlight its context window length. The context window refers to the amount of information a generative AI can process in a single go. GPT-5.4 now supports 1M (one million) tokens. With its rival Opus 4.6 also at 1M and Google Gemini having achieved 1M two years ago, all frontier models from the "Big Three" now possess 1M-token context windows. We can officially say that AI has entered the Long-Context Era.

How will this impact the development of AI agents? Let’s explore.

1. What is Many-Shot In-Context Learning?

When you ask ChatGPT, "What is the capital of Japan?" and it replies, "Tokyo," that question or instruction is called a prompt. However, you can input much more than just a short prompt.

For example, if you provide examples first—such as "Where was the World Expo held in Japan?" followed by "Osaka"—and then ask your actual question, the accuracy is known to improve. This technique is called In-Context Learning. When the number of examples exceeds roughly 10 and you provide a massive amount of data, it is referred to as Many-Shot In-Context Learning. Here is a brief summary.

In-Context Learning

2. Challenging a 20-Class Classification Task Using Bank Complaint Data

To measure the effectiveness of Many-Shot In-Context Learning, I decided to tackle a difficult 20-class classification task using bank complaint data (2). This dataset contains an "issue" column describing why a complaint occurred. The goal is to read the "text" column and select the correct cause from 20 possible categories. For this, I used Gemini 3.1 Flash-Lite (3).

　　　　　Banking complaints dataset

Rather than using a simple prompt like "Please classify this," I asked the AI itself to "create the optimal prompt," resulting in a highly detailed set of instructions—what you might call a "Prompt Powered by AI."

prompt powered by AI

I first attempted this using Zero-shot (providing no examples), even with this enhanced prompt. Unfortunately, the accuracy was only 46%. Since it gets it wrong more than half the time, it isn't yet viable for practical business use.

Zero-Shot accuracy

3. Executing Many-Shot In-Context Learning with 1,000 Samples

Next, I implemented Many-Shot In-Context Learning by providing 1,000 examples alongside the prompt. While the underlying process remains the same as the Zero-shot approach, the volume of information is massive. The following are the first five examples.

Many-Shot samples

The results were dramatic: accuracy jumped to 70%. This clearly demonstrates the sheer power of the "Many-Shot" approach.

Many-Shot accuracy

However, with a 30% error rate, there is still room for improvement. I had an AI Agent analyze why the errors occurred and generate a report. The insights gained from this analysis are highly valuable for further refinement.

Root cause analysis

Conclusion

There are several ways to improve the accuracy of generative AI, but as 1M-token context windows become the standard, Many-Shot In-Context Learning is set to become a major focal point. At ToshiStats, we plan to continue evolving this methodology.

Stay tuned!

You can enjoy our video news ToshiStats AI Weekly Review from this link, too!

1) Introducing GPT‑5.4, Open AI, March 5, 2026
2) Consumer Complaint Database
3 )Gemini 3.1 Flash-Lite: Built for intelligence at scale, Google, Mar 03, 2026

Copyright © 2026 ToshiStats Co., Ltd. All right reserved.

Notice: This is for educational purpose only. ToshiStats Co., Ltd. and I do not accept any responsibility or liability for loss or damage occasioned to any person or property through using materials, instructions, methods, algorithms or ideas contained herein, or acting or refraining from acting as a result of such use. ToshiStats Co., Ltd. and I expressly disclaim all implied warranties, including merchantability or fitness for any particular purpose. There will be no duty on ToshiStats Co., Ltd. and me to correct any errors or defects in the report, the codes and the software.

Which AI Model Should You Use Daily? Why Gemini 3.1 Flash-Lite is the Top Choice!

I’ve been using Opus 4.6 for coding lately, but I've realized that the costs can really add up when running it via API. This led me to think that for tasks where absolute peak precision isn't the only priority, a more budget-friendly model would be a better fit. Right on cue, Google announced the gemini-3.1-flash-lite-preview—a model built for speed and affordability (1). I decided to put it to the test immediately.

1. The Perfect Balance of Speed, Cost, and Performance

The Flash-Lite series is the most affordable tier in the Gemini lineup. It’s likely the engine behind many of Google’s own internal services. Speed, in particular, seems to be its standout feature.

When compared to its rivals, the processing speed is remarkably fast. Its cost-efficiency is equally impressive: at $0.25 per 1 million input tokens, it is poised to be a powerhouse for tasks involving massive amounts of data. For a startup like ours, this is incredibly encouraging.

　　　　　　　　　　　　　　　Comparison with Rival AI Models

Affordability hasn't come at the expense of performance, however. As shown in the Leaderboard (2), it boasts a score exceeding 1430. Given that the top-tier frontier models are currently competing around the 1500 mark, a score of 1430 for a lightweight model is truly outstanding.

　　　　　　　　　　　　　　　　　Leaderboard Standings

2. Performance Evaluation: Banking Complaint Classification

To see what it can really do, I tested the model on a banking complaint classification task. Using this dataset (3), I provided the model with customer complaints from the "text" column and asked it to select the most relevant category from six financial products listed in the "Product" column. I ran this test on 100 samples to see how accurately it could categorize each complaint.

　　　　　　　　　　　　　　　　　Banking Complaint Data

Here is the detailed prompt I used.

The Prompt

The results were fantastic, achieving a 92% accuracy rate. The entire process finished in about 60 seconds, demonstrating its high-speed processing capabilities. I’ve attempted this specific task several times in the past, but this is the first time a model has exceeded 90% accuracy without any fine-tuning. Truly impressive!

Task Accuracy Results

3. A High-Speed Model You Can Use Without Budget Anxiety

For the past few months, I’ve relied on Opus 4.6 for its sheer coding power. While its performance is top-notch, the costs are substantial. When you want to run various experiments where success isn't guaranteed, the budget can become a significant hurdle.

That’s where gemini-3.1-flash-lite-preview shines. Its balance of performance and cost makes it easy to iterate and experiment freely. It’s the perfect "partner" for development, and I plan to integrate it into my workflow even more moving forward.

What do you think? It looks like Google will continue to roll out new AI models one after another. We might even see some open-source models soon, so it's definitely something to keep an eye on. Here at ToshiStats, we’ll keep testing and integrating various AI models into our workflow. Stay tuned!

You can enjoy our video news ToshiStats-AI from this link, too!

1) Gemini 3.1 Flash-Lite: Built for intelligence at scale,  Google,  Mar 03, 2026
2) Arena
3) Consumer Complaint Database

Copyright © 2026 ToshiStats Co., Ltd. All right reserved.

Notice: This is for educational purpose only. ToshiStats Co., Ltd. and I do not accept any responsibility or liability for loss or damage occasioned to any person or property through using materials, instructions, methods, algorithms or ideas contained herein, or acting or refraining from acting as a result of such use. ToshiStats Co., Ltd. and I expressly disclaim all implied warranties, including merchantability or fitness for any particular purpose. There will be no duty on ToshiStats Co., Ltd. and me to correct any errors or defects in the report, the codes and the software.

The Rise of the AI Strategist: Can AI Agents Master Corporate Strategy?

Claude Code, the coding assistant that's exploding in popularity worldwide—did you know you can use Agent teams (1) to run AI agents as a team? The idea is to run multiple AI agents simultaneously according to their purpose, achieving performance that a single agent couldn't deliver. This time, we'd like to test whether we can use Agent Teams to develop corporate strategy. Let's get started!

1. Implementing Five Forces Analysis with Agent Teams

There's a well-known framework in competitive strategy called Five Forces Analysis (2). This time, we'd like to apply it to the Japanese digital payment market and explore the possibility of market entry. We'll analyze from the following five perspectives, setting up an AI agent for each one.

　　　　　　　　　　　　　　　　　　Five Forces Analysis

We entered the following prompt into Claude Code, which you're all familiar with by now. There's nothing particularly difficult about it. Of course, no programming is required. However, if this is your first time using Agent Teams, you'll need to configure the settings, so don't forget (1).

　　　　　　　　　　　　　　　　　　　　Claude Code

The multi-agent system we'll actually build looks like the following. A total of seven AI agents will be running, but the key point is the loop involving Agent 6 and Agent 7. After Agent 6 creates a report summarizing the research findings, Agent 7, positioned independently, verifies that report. The report isn't complete until Agent 7 approves it and gives the go-ahead. Quite rigorous, isn't it?

　　　　　　　　　　　　　　　　Strategic Analysis Multi-Agent System

2. The Report Creation Process

Now let's follow the report creation process on the actual screen. As you can see below, seven AI agents have indeed been configured. You can also see that the crucial verification loop has been created.

　　　　　　　　　　　　　　　　　　　　Seven AI Agents

First, Phase 1. The five research AI agents begin by pulling information from the web. They gather information about the Japanese digital payment market from the five perspectives of Five Forces Analysis. Each AI agent operates independently and processes in parallel, making it very efficient.

Work has progressed, and it appears four of the research tasks are complete. The competitive landscape from each perspective is documented as well. Just a little more to go.

The research by all five AI agents is complete, and we move into Phase 2: creating the integrated report. I'm excited to see what kind of report it will be.

Then we enter the most important phase—Phase 3: the verification loop. Here, the goals are: 1) fact-checking through search, 2) identifying logical inconsistencies, and 3) identifying hallucinations, all aimed at improving the quality of the integrated report.

It appears eight errors were identified and corrected.

The report is finally complete. As shown below, there are six types of reports. We compiled all six into a single PDF file, and it spans 60 pages of content. Impressive, isn't it?

3. Structure of the Generated Analysis Report

The structure of the consolidated report is as follows. It's written in accordance with the Five Forces Analysis framework.

Structure of the analysis Report

We can't present everything here, but the summary in Chapter 1 looks like the following—I think it's very clearly organized. Please note that this summary is for educational purposes only and should not be directly applied to business decisions or the like.

　　　　　　　　　　　　　　notice : This is for educational purpose only

So, what did you think? We carried out corporate strategy development using Five Forces Analysis, and the AI agents produced an excellent report. While further verification is needed, it could potentially be used as a starting point for discussion. I should note that Agent Teams is currently in an experimental phase, so changes to specifications are possible going forward (1). At Toshi Stats, we'll continue applying multi-agent systems across various fields. Stay tuned!

You can enjoy our video news ToshiStats-AI from this link, too!

1) Orchestrate teams of Claude Code sessions, Anthropic
2) Porter's five forces analysis, Wikipedia

Copyright © 2026 ToshiStats Co., Ltd. All right reserved.

Notice: This is for educational purpose only. ToshiStats Co., Ltd. and I do not accept any responsibility or liability for loss or damage occasioned to any person or property through using materials, instructions, methods, algorithms or ideas contained herein, or acting or refraining from acting as a result of such use. ToshiStats Co., Ltd. and I expressly disclaim all implied warranties, including merchantability or fitness for any particular purpose. There will be no duty on ToshiStats Co., Ltd. and me to correct any errors or defects in the report, the codes and the software.

What Awaits Us in 2026? Bold Predictions for AI Agents & Machine Learning

Happy New Year!

As we finally step into 2026, I am sure many of you are keenly interested in how AI agents will develop this year. Therefore, I would like to make some bold predictions by raising three key points, while also considering their connection to machine learning. Let's get started.

1. A Dramatic Leap in Multimodal Performance

I believe the high precision of the image generation AI "Nano Banana Pro (1)," released by Google on November 20, 2025, likely stunned not just AI researchers but the general public as well. Its ability to thoroughly grasp the meaning of a prompt and faithfully reproduce it in an image is magnificent, possessing a capability that could be described as "Text-to-Infographics."

Furthermore, its multilingual capabilities have improved significantly, allowing it to perfectly generate Japanese neon signs like this: "明けましておめでとう 2026" (Happy New Year 2026)

"明けましておめでとう 2026" (Happy New Year 2026)

This model is not a simple image generation AI; it is built on top of the Gemini 3 Pro frontier model with added image generation capabilities. That is why the AI can deeply understand the user's prompt and generate images that align with their intent. Google also possesses AI models like Genie 3(2) that perform simulations using video, leading the industry with multimodal models. We certainly cannot take our eyes off their movements in 2026.

2. The Explosive Popularity of "Agentic Coding"

Currently, coding by AI agents—"Agentic Coding"—has become a massive global movement. However, for complex code, it is not yet 100% perfect, and human review is still necessary. Additionally, humans still need to create the Product Requirement Document (PRD), which serves as the blueprint for implementation.

I have built several default prediction models used in the financial industry, and I always feel that development is more efficient when the human side first creates a precise PRD. By doing so, we can largely entrust the actual coding to the AI agent. This is an example of default prediction model.

However, the speed of evolution for frontier models is tremendous. In the latter half of 2026, we expect updates like Gemini 4, GPT-6, and Claude 5, and frankly, it is difficult to even imagine what capabilities AI agents will acquire as a result.

Alongside the progress of these models, the toolsets known as "code assistants" are also likely to significantly improve their capabilities. Tools like Claude Code, Gemini CLI, Cursor, and Codex have become indispensable for programmers today, but in 2026, these code assistants will likely play an active role in fields closer to business, such as machine learning and economic analysis.

At this point, calling them "code assistants" might be off the mark; a broader name like "Thinking Machine for Business" might be more appropriate. The day when those who don't know how to code can master these tools may be close at hand. It is very exciting.

3. AI Agents and Governance

As mentioned above, it is predicted that in 2026, AI agents will increasingly permeate large organizations such as corporations and governments. However, there is one thing we must be careful about here.

The behavior of AI agents changes probabilistically. This means that different outputs can be produced for the same input, which is vastly different from current systems. Furthermore, if an AI agent possesses the ability for Recursive Self-Improvement (updating and improving itself), it means the AI agent will change over time and in response to environmental changes. In 2026, we must begin discussions on governance: how do we structure organizational processes and achieve our goals using AI agents that possess characteristics unlike any previous system? This is a very difficult theme, but I believe it is unavoidable if humanity is to securely capture the benefits and gains from AI agents. I previously established corporate governance structures in the financial industry, and I hope to contribute even a little based on that experience.

What did you think? It looks like AI evolution will accelerate even further in 2026. I hope we can all enjoy it together. I look forward to another great year with you all.

You can enjoy our video news ToshiStats-AI from this link, too!

1) Introducing Nano Banana Pro, Google, Nov 20, 2025
2) Genie 3: A new frontier for world models, Jack Parker-Holder and Shlomi Fruchter, Google DeepMind, August 5, 2025

Copyright © 2026 Toshifumi Kuga. All right reserved

Notice: ToshiStats Co., Ltd. and I do not accept any responsibility or liability for loss or damage occasioned to any person or property through using materials, instructions, methods, algorithms or ideas contained herein, or acting or refraining from acting as a result of such use. ToshiStats Co., Ltd. and I expressly disclaim all implied warranties, including merchantability or fitness for any particular purpose. There will be no duty on ToshiStats Co., Ltd. and me to correct any errors or defects in the codes and the software.

Gemini 3 Flash: The Multi-modal Powerhouse Dominating the 2026 AI Scene!

Gemini 3 Flash (1) — likely the final major AI model debut of 2025 — is currently making waves. Despite being positioned as an affordable, mid-tier model, its performance is reportedly on par with flagship models. Today, I want to put Gemini 3 Flash to the test and see just how much its multimodal capabilities have evolved. Let’s dive right in.

1. App Development

To conduct our experiments, I wanted to create a simple application using Google AI Studio. By simply entering a prompt into the interface, the app was ready in an instant. No Python was used at all. This level of accessibility means even non-engineers can build functional apps now. Things have truly become incredibly convenient.

2. Object Counting

First, I challenged the model with a task that has historically been difficult for AI: counting objects. I asked the AI to count the number of cans and cars in an image. I counted them myself as well, and the AI’s response was spot on. At this level of accuracy, we might no longer need specialized object detection models for general tasks.

3. Economic Analysis from Charts

Next, let’s try a task that requires a higher level of intelligence: interpreting economic indicators from charts and generating an analytical report. Japan has entered a super-aging society faster than any other developed nation, and the labor force is steadily declining. For this test, I provided charts for the labor force population, unemployment rate, and Manufacturing Sector hourly wages. I then instructed the AI to read these charts, synthesize the data, and produce a comprehensive analysis.

labor force population

unemployment rate

　　　　　　　　　　　　　　　　Manufacturing Sector hourly wages

In 30 seconds, the economic report was generated. Below is an excerpt. I was genuinely impressed by the depth of analysis derived from just three charts. Gemini 3 Flash is truly formidable!

Conclusion

What do you think? Gemini 3 Flash is a fantastic value, being significantly cheaper than rival flagship models. Given that its multimodal performance is top-tier, I believe this will become the "go-to" model for many users. For AI startups like ours, having a model that allows for extensive experimentation with high token volumes without breaking the bank is incredibly reassuring. I highly recommend giving it a try!

Stay tuned!

You can enjoy our video news ToshiStats-AI from this link, too!

1) Gemini 3 Flash: frontier intelligence built for speed, Dec 17, 2025, Google

Copyright © 2025 Toshifumi Kuga. All right reserved
Notice: ToshiStats Co., Ltd. and I do not accept any responsibility or liability for loss or damage occasioned to any person or property through using materials, instructions, methods, algorithms or ideas contained herein, or acting or refraining from acting as a result of such use. ToshiStats Co., Ltd. and I expressly disclaim all implied warranties, including merchantability or fitness for any particular purpose. There will be no duty on ToshiStats Co., Ltd. and me to correct any errors or defects in the codes and the software.

Improving ML Vibe Coding Accuracy: Hands-on with Claude Code's Plan Mode

2025 was a year where I actively incorporated "Vibe Coding" into machine learning. After repeated trials, I encountered situations where coding accuracy was inconsistent—sometimes good, sometimes bad.

Therefore, in this experiment, I decided to use Claude Code "Plan Mode" (1) to automatically generate an implementation plan via an AI agent before generating the actual code. Based on this plan, I will attempt to see if a machine learning model can be built stably using "Vibe Coding." Let's get started!

1. Generating an Implementation Plan with Claude Code "Plan Mode"

Once again, I would like to build a model that predicts in advance whether a customer will default (on a loan, etc.). I will use publicly available credit card default data (2). For the code assistant, I am using Claude Code, and for the IDE, the familiar VS Code.

To provide input to the Claude Code AI agent, I summarized the task and implementation points into a "Product Requirement Document (PRD)." This is the only document I created.

I input this PRD into Claude Code "Plan Mode" and instructed it to: "Create a plan to create predictive model under the folder of PD-20251217".

Within minutes, the following implementation plan was generated. Comparing it to the initial PRD, you can see how refined it is. Note that I am only showing half of the actual plan generated here—a truly detailed plan was created. I can only say that the ability of the AI agent to envision this far is amazing.

2. Beautifully Visualizing Prediction Accuracy

When this implementation plan is approved and executed, the prediction model is generated. Naturally, we are curious about the accuracy of the resulting model.

Here, it is visualized clearly according to the implementation plan. While these are familiar metrics for machine learning experts, all the important ones are covered and visualized in an easy-to-understand way, summarized as a single HTML file viewable in a browser.

The charts below are excerpts from that file. It includes ROC curves, SHAP values, and even hyperparameter tuning results. This time, the total implementation time was about 10 minutes. If it can be generated automatically to this extent in that amount of time, I’d rather leave it to the AI agent.

3. Meta-Prompting with Claude Code "Plan Mode"

A Meta-Prompt refers to a "prompt (instruction to AI) used to create and control prompts."

In this case, I called Claude Code "Plan Mode" and instructed it to "generate an implementation plan" based on my PRD. This is nothing other than executing a meta-prompt in "Plan Mode."

Thanks to the meta-prompt, I didn't have to write a detailed implementation plan myself; I only needed to review the output. It is efficient because I can review it before coding, and since that implementation plan can be viewed as a highly precise prompt, the accuracy of the actual coding is expected to improve.

To be honest, I don't have the confidence to write the entire implementation plan myself. I definitely want to leave it to the AI agent. It has truly become convenient!

How was it? Generating implementation plans with Claude Code "Plan Mode" seems applicable not only to machine learning but also to various other fields and tasks. I definitely intend to continue trying it out in the future. I encourage everyone to give it a challenge as well.

That’s all for today. Stay tuned!

You can enjoy our video news ToshiStats-AI from this link, too!

1) How to use Plan Mode,  Anthropic

2) Default of Credit Card Clients

Copyright © 2025 Toshifumi Kuga. All right reserved
Notice: ToshiStats Co., Ltd. and I do not accept any responsibility or liability for loss or damage occasioned to any person or property through using materials, instructions, methods, algorithms or ideas contained herein, or acting or refraining from acting as a result of such use. ToshiStats Co., Ltd. and I expressly disclaim all implied warranties, including merchantability or fitness for any particular purpose. There will be no duty on ToshiStats Co., Ltd. and me to correct any errors or defects in the codes and the software.

This Is What Happens When an AI Agent Runs Our 2025 Autumn Marketing!

Hello, the high temperature in Tokyo has dropped to 16°C, and it's starting to feel very much like autumn. For those unfamiliar with autumn in Japan, this is the season when the leaves on the mountains change from green to orange. The entire mountainside is dyed orange, creating a beautiful and spectacular view. Therefore, I decided to use orange as the background color for this marketing campaign's promotional video. The challenge is: "To devise a campaign to sell cakes to women in Ashiya, an affluent residential area in the Kansai region." What happens when we entrust this task to an AI agent? Let's find out.

1. Creating an AI Marketing Agent with "Google Opal"

This time, I'm creating an AI marketing agent using Google Opal (1). As the description says, "Opal, our no-code AI mini-app builder," you can easily develop an AI agent app like the one below.

For this AI agent's development, I only entered the following prompt: "You are an expert in marketing campaigns. You will be given the following information: 1. The product/service to sell, 2. The target customer, 3. The location/region, 4. The time/season of the campaign, 5. The desired brand image color, 6. A photo of the facilitator. Using this information, please create the following: a. A marketing strategy, b. A marketing campaign name, c. A logo based on the name, d. A promotional video featuring the facilitator, complete with BGM."

Just by executing this, you can create a workflow like the one shown above using the AI agent. After that, you just switch to the app and answer questions related to your task, and the marketing campaign is created. Amazing, isn't it!

2. Marketing Strategy and Logo

Once you input all the necessary information, you get the results back immediately. First is the marketing strategy. In reality, a more detailed discussion followed. This time, I'll just introduce the beginning. Even though I didn't input very detailed information about the campaign at the initial stage, I think this marketing strategy is well-done.

　　　　　　　　　　　　　　　　　　Marketing Strategy

Next is the marketing campaign name and logo. What it generated was a cool, French-style logo. I'd love to try using it sometime.

　　　　　　　　　　Logo

3. Three Short Promotional Videos

First, I provide the AI agent with a base image of a woman. Then, using this image as a starting point and based on the created marketing strategy, an approximately 8-second short video is generated. It's exciting to see what kind of video the AI agent will produce. This time, it created three videos with BGM. All of them are based on the theme of "Autumn Cakes." It's hard to pick a winner; they are all excellent. After actually creating the videos, I felt that even 8 seconds is enough to convey the image clearly. Which one did you like the best?

What did you think? Although this was just a demo AI agent, I was astonished at what it could accomplish with no code, no programming. It seems like it will become a powerful ally for marketers. Of course, there are limitations, but what I created this time can be done for free with just a Google account. I highly recommend giving it a try. ToshiStats will continue to share more about AI agents. Stay tuned!

You can enjoy our video news ToshiStats-AI from this link, too!

1) Opal is now available in more than 160 countries, Google, 7 Nov 2025

Copyright © 2025 Toshifumi Kuga. All right reserved

Notice: ToshiStats Co., Ltd. and I do not accept any responsibility or liability for loss or damage occasioned to any person or property through using materials, instructions, methods, algorithms or ideas contained herein, or acting or refraining from acting as a result of such use. ToshiStats Co., Ltd. and I expressly disclaim all implied warranties, including merchantability or fitness for any particular purpose. There will be no duty on ToshiStats Co., Ltd. and me to correct any errors or defects in the codes and the software.

Your Guide to AI Agents: Insights from Andrew Ng's Latest Course

A new online course called "Agentic AI" (1) has been released by DeepLearning AI. The creator is Andrew Ng, an adjunct professor at Stanford University, who is also famous for his past machine learning-related courses. For me, this is the first course I've taken from him since the Deep Learning Specialization in 2018. I've just completed it, and I'd like to share my thoughts and a recommendation.

1. Course Overview

The course is divided into five modules, each consisting of 5-7 short videos (about 5-10 minutes each), a quiz, and coding tasks using jupyter notebook. By passing each assignment, you are ultimately awarded a certificate of completion. The level is listed as intermediate; while a basic knowledge of Python is necessary, I believe that even those without specialized knowledge in AI can progress through the material and naturally come to understand it. The main topics are as follows:

Reflection: AI critiques its own work and iterates to improve quality—like code review, but automated.

Tool Use: Connect AI to databases, APIs, and external services so it can actually perform actions, not just generate text.

Planning: Break complex tasks into executable steps that AI can follow and adapt when things don’t go as expected.

Multi-Agent: Coordinate multiple specialized AI systems to handle different parts of a complex workflow.

Created by Andrew Ng, who teaches at Stanford while concurrently doing practical consulting work, I found the course to have a wonderful balance between theory and practice.

2. Reflection and Tool Use

The second and third modules are critical technologies for the future realization of AGI. In particular, "Reflection," where an AI improves itself, is also known as Recursive Self Improvement and is a field being researched worldwide. This module introduces a method that allows even non-experts to incorporate reflection functionality, which I am very eager to try implementing. Additionally, using tools allows a generative AI to incorporate information that is difficult to acquire on its own, thereby enhancing the AI agent's capabilities. Furthermore, this information can be applied to the "Reflection" process, promising a synergistic effect. I'm also keen to implement this and see what kind of information can be integrated.

3. Error Analysis

As Andrew Ng states, this fourth module is, in my opinion, the most important and valuable content in the course. Generative AI is excellent, but it is not perfect. There is still a considerable possibility that it will produce incorrect answers. Therefore, to raise its accuracy to a practical level, the course emphasizes the importance of adopting a strategy that quickly identifies the parts of the overall process with the lowest performance and allocates resources to improving those areas. I can certainly see how for a complex AI agent that may contain numerous sub-agents, identifying and prioritizing the reinforcement of its weaknesses is incredibly important in practical applications.

So, what did you think? With a flood of AI-related news every day, many people are likely wondering, "How should I proceed with my AI projects from now on?" I believe this course provides a valuable perspective for thinking in the medium to long term. While it is a paid course, it is not as expensive as university tuition, and I highly recommend trying it. Incidentally, because I studied intensively, I was able to receive my certificate in about three days. It's certainly possible for a business professional to complete it over a long weekend.

Well, that's all for today. Stay tuned!

You can enjoy our video news ToshiStats-AI from this link, too!

1) Agentic AI, Andrew Ng,  DeepLearning AI, Oct 2025 

Copyright © 2025 Toshifumi Kuga. All right reserved

Notice: ToshiStats Co., Ltd. and I do not accept any responsibility or liability for loss or damage occasioned to any person or property through using materials, instructions, methods, algorithms or ideas contained herein, or acting or refraining from acting as a result of such use. ToshiStats Co., Ltd. and I expressly disclaim all implied warranties, including merchantability or fitness for any particular purpose. There will be no duty on ToshiStats Co., Ltd. and me to correct any errors or defects in the codes and the software.

The Secret to High-Accuracy AI: An Exploration of Machine Learning engineering agent

In a previous post, I explained Google's research paper, "MLE STAR" (1), and uncovered the mechanism by which an AI can build its own high-accuracy machine learning models. This time, I'm going to implement that AI agent using the Google ADK and experiment to see if it can truly achieve high accuracy. For reference, the MLE STAR code is available as open source (2).

1. The Information I Provided

With MLE STAR, humans only need to handle the data input and task definition. The data I used for this experiment comes from the Kaggle competition "Home Credit Default Risk" (3). While the original data consists of 8 files, I combined them into a single file for this experiment. I reduced the training data to 10% of the original, resulting in about 30,000 samples, and kept the original test data of 48,700 samples.

The task was set as follows: "A classification task to predict default." Note that to speed up the experiment, the number of iterative loops was set to a minimum.

　　　　　　　　　　　　　　　　　　　　　Task Setup

2. Deciding Which Model to Use

MLE STAR uses a web search to select the optimal model for the given task. In this case, it ultimately chose LightGBM. To finish the experiment quickly, I configured it to select only one model. If I had set it to select two, it likely would have also chosen something like XGBoost. Both are models frequently used in data science competitions.

　　　　　　　　　　　　　　　　Model Selection by MLE STAR

It generated the initial script below. As a frequent user of LightGBM, the code looks familiar, but the ability to generate it in an instant is something only an AI can do. It's amazing!

3. Identifying Key Code Blocks with "Ablation Studies"

Next, it uses ablation studies to identify which code blocks should be improved. In this case, ablation2 showed that removing Early Stopping worsened the model's performance, so this feature was kept in the training process from then on.

　　　　　　　　　　　　　　　Ablation Studies Results by MLE STAR

4. Iteratively Improving the Model

Based on the ablation studies, MLE STAR decided to improve the model using the following two techniques: K-fold target encoding and binary encoding. These techniques themselves are common in machine learning and are not particularly unusual.

　　　　　　　　　　　　　　　　　　　K-fold Target Encoding

　　　　　　　　　　　　　　　　　　　　　Binary Encoding

This ability to "use ablation studies to identify which code blocks to improve" is likely a major reason for MLE STAR's high accuracy. I look forward to seeing how this functionality evolves in the future.

5. The Results Are In. Unfortunately, I Lost.

For its final step, MLE STAR ensembles the models to create the final version. For more details, please see the research paper. It also generates a CSV file with the default predictions, which I slightly modified and promptly submitted to Kaggle. This task is evaluated using AUC, where a score closer to 1 indicates higher accuracy.

The top score is the result I achieved using my own LightGBM model. The score in the red box at the bottom is the one automatically generated by MLE STAR. With a difference of more than 0.01 on both the Public and Private scores, it was my complete defeat.

　　　　　　　　　　　　　Kaggle Prediction Accuracy Evaluation (AUC)

Improving the AUC by 0.01 is quite a challenge, which gives a glimpse into how excellent MLE STAR is. I didn't perform any extensive tuning on my LightGBM model, so I believe my score would have improved if I had spent time tuning it manually. However, MLE STAR produced its result in about 7 minutes from the start of the computation, so from an efficiency standpoint, I couldn't compete.

So, what did you think? Although this was a limited experiment, I feel I was able to grasp the high potential of MLE STAR. I was truly impressed by the power of its Recursive Self-Improvement, which identifies specific code blocks and improves upon them autonomously.

Here at Toshi Stats, I plan to continue digging into MLE STAR. Stay tuned!

You can enjoy our video news ToshiStats-AI from this link, too!

1) MLE-STAR: Machine Learning Engineering Agent via Search and Targeted Refinement
Jaehyun Nam1 2 *, Jinsung Yoon1, Jiefeng Chen1, Jinwoo Shin2, Sercan Ö. Arık1 and Tomas Pfister1, Google Cloud1, KAIST2,  23, Aug 2025

2) Machine Learning Engineering with Multiple Agents (MLE-STAR) , Google

3) Home Credit Default Risk, kaggle

Copyright © 2025 Toshifumi Kuga. All right reserved

Notice: ToshiStats Co., Ltd. and I do not accept any responsibility or liability for loss or damage occasioned to any person or property through using materials, instructions, methods, algorithms or ideas contained herein, or acting or refraining from acting as a result of such use. ToshiStats Co., Ltd. and I expressly disclaim all implied warranties, including merchantability or fitness for any particular purpose. There will be no duty on ToshiStats Co., Ltd. and me to correct any errors or defects in the codes and the software.

Is an AI Machine Learning Assistant Finally a Reality? I Looked Into It, and It's Incredible!

I often build machine learning models for my job. The process of collecting data, creating features, and gradually improving the model's accuracy takes time, specialized knowledge, and programming skills in various libraries. I've always found it to be quite a challenge. That's why I've been hoping for an AI that could skillfully assist with this work, and recently, a potential candidate has emerged. I'd like to take a deep dive into it right away.

1. A Basic Three-Layer Structure

This AI assistant is called MLE-STAR, and according to a research paper (1), it has the following structure. Simply put, it first searches the internet for promising libraries. Next, after writing code using those libraries, it identifies which parts, called "code blocks," should be improved further. Finally, it decides how to improve those code blocks. Let's explore each of these steps in detail.

2. Selecting the Optimal Library with a Search Function

To create a high-accuracy machine learning model, you first need to decide "what kind of model to use." This means you have to select a library to implement the model. This is where the search function comes in. For example, in a finance task to calculate default probability, many methods are possible, but gradient boosting is often used in competitions like Kaggle. I also use gradient boosting in most cases. It seems MLE-STAR can use its search function to find the optimal library on its own, even without me specifying "use gradient boosting." That's amazing! This would eliminate the need for humans to research everything, leading to greater efficiency.

3. Finding Where to Improve the Code and Steadily Making Progress

Once the library is chosen and a baseline script is written, it's time to start making improvements to increase accuracy. But it's often difficult to know where to begin. MLE-STAR employs an ablation study to understand how accuracy changes when a feature is added or removed, thereby identifying the most impactful code block. This part of the process typically relies on human experience and intuition, involving a lot of trial and error. By using MLE-STAR, we can make data-driven decisions, which is incredibly efficient.

4. Iterating Until Accuracy Actually Improves

Once the code block for improvement is identified, the system gradually changes parameters and confirms the accuracy improvements. This is also done automatically within a loop, without requiring human intervention. The accuracy is calculated at each step, and as a rule, only changes that improve performance are adopted, ensuring that the model's accuracy steadily increases. Incredible, isn't it? In fact, a graph comparing the performance of MLE-STAR with past AI assistants shows that MLE-STAR won a "gold medal" in approximately 36% of the tasks, highlighting its superior performance.

So, what did you think? This new framework for an AI assistant looks extremely promising. In particular, its ability to identify which code blocks to improve and then actually increase the accuracy is likely to become even more powerful as the performance of foundation models continues to advance. I'm truly excited about future developments.

Next time, I plan to apply it to some actual analysis data to see what kind of accuracy it can achieve. Stay tuned!

You can enjoy our video news ToshiStats-AI from this link, too!

1) MLE-STAR: Machine Learning Engineering Agent via Search and Targeted Refinement
Jaehyun Nam1 2 *, Jinsung Yoon1, Jiefeng Chen1, Jinwoo Shin2, Sercan Ö. Arık1 and Tomas Pfister1, Google Cloud1, KAIST2,  23, Aug 2025

Copyright © 2025 Toshifumi Kuga. All right reserved

Notice: ToshiStats Co., Ltd. and I do not accept any responsibility or liability for loss or damage occasioned to any person or property through using materials, instructions, methods, algorithms or ideas contained herein, or acting or refraining from acting as a result of such use. ToshiStats Co., Ltd. and I expressly disclaim all implied warranties, including merchantability or fitness for any particular purpose. There will be no duty on ToshiStats Co., Ltd. and me to correct any errors or defects in the codes and the software.

A Sweet Strategy: Selling Cakes in Wealthy Residential Areas !

Has everyone ever thought about starting a cake shop? As a cake lover myself, I often find myself wondering, "What kind of cake would be perfect?" However, developing a concrete business strategy is a real challenge. That's why this time, I'd like to conduct a case study with the support of an "AI marketing-agency." Let's get started.

1. Selling Cakes in an Upscale Kansai Neighborhood

The business scenario I've prepared for this case is a simple one:

Goal: To sell premium fruit cakes in the Kansai region.

• Cake Features: Premium shortcakes featuring strawberries, peaches, and muscat grapes.

• Target Audience: Women in their 20s to 40s living in upscale residential areas.

• Stores: 3 cafes near Yamate Dentetsu Ashiya Station, 1 cafe near Kaigan Dentetsu Ashiya Station.

• Direct Sales Outlet: 1 store inside the Yamate Dentetsu Ashiya Station premises.

• Branding: The brand's primary color will be blue, with the website and logo also unified in blue.

• Current Plan: In the process of planning a sales promotion for the autumn season.

From here, what kind of concrete business strategy can we derive? First, I'll input the business scenario into the AI marketing-agency.

The first thing it does is automatically generate 10 cool domain names.

It's hard to choose, but for now, I'll proceed with branding using "PremiumAshiyaCake.com".

2. A Practical Business Strategy

Now, let's ask the AI marketing-agency to formulate a business strategy for selling our premium fruit cakes in Kansai. When prompted to input the necessary information, I re-entered the business scenario, and the following business strategy was generated in about two minutes. Amazing!

It's a long document, over five pages, so I can't share it all, but here is the "Core of the Marketing Strategy."

• Overall Approach: Direct Response that Inspires Aspiration

  • We will build an aspirational, luxury brand image through beautiful content, and then convert that desire into immediate store visits using precisely targeted calls-to-action (CTAs).

• Core Message and Positioning:

  • Positioning Statement: For the discerning women of Kansai, Premium Ashiya Cake is the patisserie that transforms a moment into a cherished memory with its exquisitely crafted seasonal shortcakes.

  • Tagline / Core Message: "Premium Ashiya Cake: An exquisite moment, crafted for you."

• Key Pillars of the Strategy:

  • Visual Elegance and a "Blue" Signature: All visuals must be of professional, magazine-quality. The brand color "blue" will be used as a sophisticated accent in styling—such as on blue ribbons, parts of the tableware, or as background elements—to create a recognizable and unique visual signature.

  • Hyper-local Exclusivity: Marketing efforts will be geographically and demographically laser-focused on the target audience residing in Ashiya and its surrounding affluent areas. This creates an "in-the-know" allure for locals.

  • Seasonal Storytelling: Treat each season's campaign as a major event. We will build a narrative around the star ingredients, such as Shine Muscat grapes from a specific partner farm, to build anticipation and justify the premium price point.

This is wonderfully practical content. The keywords I provided—"blue," "Ashiya," and "muscat"—have been skillfully integrated into the strategy.

3. The Logo is Excellent, Too—This is Usable!

Because I specified in the initial business scenario that I wanted to "unify the color scheme based on blue," it created this cool logo for me. It really looks like something I could use right away. Google's image generation AI, Imagen 3.0, is used here. The quality of this AI is always highly rated, so it's no surprise that the logo generated this time is also of outstanding quality.

So, what did you think of the AI marketing-agency? The business strategy is professional, and it's amazing how it automatically created the domain names and logo with such excellent results. Although I couldn't introduce it this time, it also includes a website creation feature. It's surprising that a tool this high-performance is actually available for free. A development kit called "Google ADK" is provided as open-source, and the AI marketing-agency from this article can be downloaded and used for free as Sample (1). For those who can use Python, I think you'll get the hang of it with a little practice. The operational costs are also limited to the usage fees for Google Gemini 2.5 Pro, so the cost-effectiveness is outstanding. I encourage you all to give it a try.

Please note that this story is a work of fiction and does not represent anything that actually exists. That's all for today, stay tuned!

You can enjoy our video news ToshiStats-AI from this link, too!

1) Marketing Agency, Google, May 2025

Copyright © 2025 Toshifumi Kuga. All right reserved

Notice: ToshiStats Co., Ltd. and I do not accept any responsibility or liability for loss or damage occasioned to any person or property through using materials, instructions, methods, algorithms or ideas contained herein, or acting or refraining from acting as a result of such use. ToshiStats Co., Ltd. and I expressly disclaim all implied warranties, including merchantability or fitness for any particular purpose. There will be no duty on ToshiStats Co., Ltd. and me to correct any errors or defects in the codes and the software.