# Mutt0-ds Notes Davide Muttoni's notes on AI, data engineering, and software This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Second Brains in the AI era: still worth it? DevFeed: [Second Brains in the AI era: still worth it?]() Original publisher: [Read original article]() Published: 2026-09-06T00:00:00Z Content type: opinion Language: en Sources: [Mutt0-ds Notes]() Topics: [Artificial Intelligence](), [context](), [AI Agent](), [Graphs](), [Obsidian]() Tags: [ai](), [ai-agent](), [context](), [knowledge-graph](), [markdown](), [obsidian]() ### AI overview The article argues that maintaining a personal knowledge base, or "second brain," is more valuable in the AI era because it gives AI assistants structured, connected context. It suggests that linked notes resemble graph memory and can help agents navigate complex information, while large unstructured collections may increase confusion and hallucinations. ### Source excerpt I've been working on my second brain(s) for years now. Brains, plural, because I had to create new ones, for example when I changed jobs...... ## How direct, context-rich prompts shape technical LLM conversations DevFeed: [How direct, context-rich prompts shape technical LLM conversations]() Original publisher: [Read original article]() Published: 2026-08-06T00:00:00Z Content type: opinion Language: en Sources: [Mutt0-ds Notes]() Topics: [Prompt Engineering](), [ChatGPT](), [Large Language Model](), [Artificial Intelligence](), [math]() Tags: [ai](), [chatgpt](), [deep-dive](), [llm](), [prompt-engineering](), [technical]() ### AI overview This opinion article examines Terence Tao's ChatGPT conversation about verifying a counterexample to the Jacobian conjecture. It argues that providing informed context and precise technical constraints can guide LLMs more effectively than elaborate prompt templates. ### Source excerpt There is something so satisfying in reading Terence Tao's ChatGPT conversation, where he and the model together verify a counterexample to... ## Microsoft, Copilot, and how to add friction DevFeed: [Microsoft, Copilot, and how to add friction]() Original publisher: [Read original article]() Published: 2026-07-09T00:00:00Z Content type: opinion Language: en Sources: [Mutt0-ds Notes]() Topics: [Microsoft](), [User Experience](), [Artificial Intelligence](), [Users](), [OpenAI]() Tags: [ai](), [copilot](), [microsoft](), [openai](), [user-experience]() ### AI overview An opinion article argues that Microsoft's Copilot products create user friction through slow performance, hallucinations, weak context handling, and confusing integration across products. It suggests that these experience problems may undermine Microsoft's AI position despite access to powerful models. ### Source excerpt I was watching with deep sadness the thousands of layoffs that Microsoft has announced in the past days, and the backlash when they removed... ## A Practical Guide to Long-Term Memory in AI Agents DevFeed: [A Practical Guide to Long-Term Memory in AI Agents]() Original publisher: [Read original article]() Published: 2026-05-09T00:00:00Z Content type: tutorial Language: en Sources: [Mutt0-ds Notes]() Topics: [Artificial Intelligence](), [context](), [consistency](), [User experience (UX)]() Tags: [agentic](), [ai](), [benchmarks](), [consistency](), [context](), [guide](), [memory](), [retention](), [ux]() ### AI overview This practical guide explains long-term memory in AI systems, including how to think about retention, relevance, recall quality, and personality consistency. It discusses custom instructions, user experience, and challenges encountered when implementing memory in production. ### Source excerpt Agentic Memory is an area of the AI world where even benchmarks are vague. How do you really measure "memory"? Retention? Relevance? Recall... ## 10 Lessons learned when building Charlie DevFeed: [10 Lessons learned when building Charlie]() Original publisher: [Read original article]() Published: 2026-04-05T00:00:00Z Content type: article Language: en Sources: [Mutt0-ds Notes]() Topics: [AI Agent](), [Development](), [Large Language Model](), [Architecture & Design](), [Testing]() Tags: [ai-agent](), [anthropic](), [architecture](), [development](), [evals](), [financial](), [llm](), [openai](), [tdd]() ### AI overview The author shares lessons from building Charlie, an AI agent designed for financial institutions. The excerpt emphasizes keeping agent systems simple, designing evaluation pipelines around real-world financial queries, and using flexible, provider-agnostic architecture. It argues that direct retrieval-to-explanation paths can be more robust and faster for many questions, while evaluations must reflect the system's actual context and edge cases. ### Source excerpt Last week, we launched Charlie, our first AI Agent, specifically designed and tailored for financial institutions. While designing and... ## AI-Assisted Code Review Tools: Useful First-Line Checks, Not a Replacement for Humans DevFeed: [AI-Assisted Code Review Tools: Useful First-Line Checks, Not a Replacement for Humans]() Original publisher: [Read original article]() Published: 2026-03-01T00:00:00Z Content type: opinion Language: en Sources: [Mutt0-ds Notes]() Topics: [Code review](), [Artificial Intelligence](), [AI Agent](), [Pull Request](), [CI/CD]() Tags: [ai](), [ai-agent](), [ci-cd](), [code-review](), [code-reviews](), [pull-request]() ### AI overview This subjective article examines the author's experience using AI-assisted code review tools such as CodeRabbit in day-to-day development and a CI/CD pipeline. It argues that these tools can catch bad practices and obvious issues early, but still miss deeper architectural bugs and should not replace human reviewers. ### Source excerpt AI-assisted code reviews: are they actually helpful, or just more noise in an already crowded inbox? Today I want to talk about my... ## How Evals Help Build Reliable AI DevFeed: [How Evals Help Build Reliable AI]() Original publisher: [Read original article]() Published: 2026-01-18T00:00:00Z Content type: article Language: en Sources: [Mutt0-ds Notes]() Topics: [Artificial Intelligence](), [test](), [Test-driven development]() Tags: [agent](), [ai](), [development](), [evals](), [orchestration](), [prompt](), [regression](), [tests]() ### AI overview The article explains how eval-driven development can help teams build more reliable AI tools. It describes evals as non-deterministic tests that pair questions with expected behavior and can detect regressions after changes to prompts, agent logic, tool definitions, or orchestration code. ### Source excerpt I finished 2025 with a negative AI post, so let's start 2026 with a positive one. I'm leading a project for an AI-based tool, and something... ## On AI Slop DevFeed: [On AI Slop]() Original publisher: [Read original article]() Published: 2025-12-24T00:00:00Z Content type: opinion Language: en Sources: [Mutt0-ds Notes]() Topics: [Artificial Intelligence](), [communications](), [Large Language Model](), [ChatGPT]() Tags: [ai](), [communication](), [llm](), [messages](), [trust](), [writing]() ### AI overview The author argues that unreviewed AI-generated text, especially in personal messages, is often recognizable as generic, verbose, and impersonal. They acknowledge useful applications for AI, but recommend reviewing generated text before sending it because careless communication can waste readers' time and weaken trust. ### Source excerpt I've started to notice a very predictable trend: AI-generated messages in my inbox. What finally pushed me to write this was how casually... ## Testing 100k-Line Nested JSON Trees for Missing Scenarios DevFeed: [Testing 100k-Line Nested JSON Trees for Missing Scenarios]() Original publisher: [Read original article]() Published: 2025-08-11T00:00:00Z Content type: article Language: en Sources: [Mutt0-ds Notes]() Topics: [JSON](), [test]() Tags: [bugs](), [compliance](), [json](), [test](), [trees]() ### AI overview The article describes the challenge of reliably testing massive, deeply nested JSON logic files used by StoryTeller, a tool for generating personalized financial reports. Missing scenarios can cause reports to crash, and the article explains how the system's size and intertwined conditions make omissions difficult to detect. ### Source excerpt Today I want to share an interesting challenge that's been bugging me since I joined InvestSuite last December. It's stories like this that... ## No, AI is not replacing Data Engineers. DevFeed: [No, AI is not replacing Data Engineers.]() Original publisher: [Read original article]() Published: 2025-05-29T00:00:00Z Content type: opinion Language: en Sources: [Mutt0-ds Notes]() Topics: [AI, ML & Data Engineering](), [data observability](), [Claude](), [ChatGPT](), [Python]() Tags: [ai](), [ai-tools](), [chatgpt](), [claude](), [data-engineering](), [python]() ### AI overview An opinion article argues that AI is not replacing data engineers, focusing on the continued importance of greenfield prototyping in data engineering. It describes messy, real-world work involving APIs, spreadsheets, data cleaning, and Python scripts, contrasting it with AI demonstrations and synthetic coding benchmarks. ### Source excerpt Claude 4 landed, and as usual, it kicked off the usual hype cycle. "Best coding model ever" "It writes stories!" "AI is replacing... ## 45 Minutes, 100% AI-Generated Code DevFeed: [45 Minutes, 100% AI-Generated Code]() Original publisher: [Read original article]() Published: 2025-04-19T00:00:00Z Content type: article Language: en Sources: [Mutt0-ds Notes]() Topics: [Vibe coding](), [AI tools for developers](), [Artificial Intelligence](), [AI Agent](), [cursor](), [dashboards](), [Next.js](), [web applications](), [Figma]() Tags: [ai](), [ai-agent](), [ai-tools-for-developers](), [coding](), [cursor](), [figma](), [next-js](), [prompting]() ### AI overview The author describes building an interactive StoryTeller dashboard with an AI agent in 45 minutes using entirely AI-generated code. The article argues that AI tools accelerate research and prototyping but still require critical thinking, while blindly accepting generated code can create technical debt. ### Source excerpt Last Saturday, I woke up with an idea: what if StoryTeller, the product I work on, had an interactive dashboard with an AI agent that could... ## Simplicity speaks louder than Complexity DevFeed: [Simplicity speaks louder than Complexity]() Original publisher: [Read original article]() Published: 2025-03-08T00:00:00Z Content type: opinion Language: en Sources: [Mutt0-ds Notes]() Topics: [implementation](), [API](), [structure](), [data-engineering]() Tags: [api](), [architecture](), [complexity](), [data-engineering](), [documentation](), [implementation](), [presentation](), [prototyping]() ### AI overview The author describes preparing a technical presentation about StoryTeller, a financial reporting product with an API for generating personalized portfolio reports. The article argues that complex products should initially be explained from the customer's perspective, focusing on structure, interaction, and common errors rather than every technical or mathematical detail. ### Source excerpt A few days ago, I had my first technical presentation at my new company. I joined InvestSuite 3 months ago and it was finally time to... ## How I created my first Course with Datacamp DevFeed: [How I created my first Course with Datacamp]() Original publisher: [Read original article]() Published: 2025-01-22T00:00:00Z Content type: article Language: en Sources: [Mutt0-ds Notes]() Topics: [Microsoft](), [Security](), [Deployment](), [configuration](), [version](), [version-control](), [data analytics]() Tags: [configuration](), [course](), [data-analytics](), [deployment](), [microsoft](), [security](), [version]() ### AI overview The author describes creating and publishing a DataCamp course on advanced Microsoft Fabric topics, including security, configuration, version control, and deployment. The article explains how DataCamp's Fabric sandbox supports hands-on exercises and outlines the course-development process. ### Source excerpt I just published an online course! covering advanced Microsoft Fabric topics like security, deployment, admin settings, and version... ## Building a Full-Stack Sales Forecasting Web App from a Legacy Excel Tool DevFeed: [Building a Full-Stack Sales Forecasting Web App from a Legacy Excel Tool]() Original publisher: [Read original article]() Published: 2024-11-13T00:00:00Z Content type: tutorial Language: en Sources: [Mutt0-ds Notes]() Topics: [Full-Stack](), [Full Stack Development](), [Web app](), [Development](), [data-engineering](), [Data Science](), [Back end](), [Front end](), [Database](), [legacy]() Tags: [backend](), [data-engineering](), [data-science](), [database](), [development](), [frontend](), [full-stack](), [full-stack-development](), [legacy](), [web-app]() ### AI overview This article describes the author's experience building a prototype full-stack sales forecasting web app to replace a legacy Excel tool powered by VBA macros. It explains the application's frontend, backend, database, calculations, data movement, and security components while acknowledging that some project details remain vague. ### Source excerpt 🧠 Breaking Down Full Stack Development This post has been sitting in my drafts for over 7 months for two reasons: First, since the project... ## Data Culture - How we promoted Power BI in a Corporate Environment \[🎙 Power BI Ticino 2024\] DevFeed: [Data Culture - How we promoted Power BI in a Corporate Environment \[🎙 Power BI Ticino 2024\]]() Original publisher: [Read original article]() Published: 2024-10-22T00:00:00Z Content type: article Language: en Sources: [Mutt0-ds Notes]() Topics: [data](), [.NET Conf]() Tags: [conference](), [corporate](), [data](), [technologies]() ### AI overview The article describes a Power BI Champions program at Acer that used early adopters to promote Power BI and data culture across the corporate team. It also covers the author's presentation of the project at the Power BI Ticino Conference. ### Source excerpt Last Friday, I took the stage at the Power BI Ticino Conference to share one of my favorite projects at Acer: our Power BI Champions... ## Automating Power BI Measure and Column Descriptions with a Tabular Editor Script DevFeed: [Automating Power BI Measure and Column Descriptions with a Tabular Editor Script]() Original publisher: [Read original article]() Published: 2024-08-09T00:00:00Z Content type: tutorial Language: en Sources: [Mutt0-ds Notes]() Topics: [Development](), [Script](), [Documentation](), [business logic](), [DevOps]() Tags: [business-logic](), [code](), [dev](), [devops](), [documentation](), [script](), [tutorial]() ### AI overview This tutorial presents a Tabular Editor script in C# that copies DAX code into the Description field for Power BI measures and calculated columns. It also discusses adding comments and ticket IDs for context, and describes a possible TMDL and DevOps pipeline alternative. ### Source excerpt "How does this MEASURE/COLUMN work?" This is one of the most frequent requests I was receiving. And it's easy to see why. In complex Power... ## Personal Notes about Simply Said DevFeed: [Personal Notes about Simply Said]() Original publisher: [Read original article]() Published: 2024-07-12T00:00:00Z Content type: article Language: en Sources: [Mutt0-ds Notes]() Topics: [communications](), [meetings]() Tags: [book](), [communication-skills](), [deep-dive](), [personal](), [practical](), [tips]() ### AI overview Personal notes and a condensed summary of Jay Sullivan's book "Simply Said," focusing on the principle of focusing on others and practical guidance for presentations, oral and written communication, meetings, leadership, and planning. ### Source excerpt "Simply Said" is the best communication book I've read recently. I discovered it thanks to Jordan Cutler (who runs an amazing tech... ## Giving our AI superpowers with OpenAI Tools DevFeed: [Giving our AI superpowers with OpenAI Tools]() Original publisher: [Read original article]() Published: 2024-06-03T00:00:00Z Content type: tutorial Language: en Sources: [Mutt0-ds Notes]() Topics: [OpenAI](), [Artificial Intelligence](), [function calling](), [Azure OpenAI](), [Databases](), [API](), [SQL](), [LangChain](), [Retrieval Augmented Generation (RAG)]() Tags: [ai](), [ai-tools](), [api](), [azure-openai](), [function-calling](), [langchain](), [openai](), [retrieval-augmented-generation-rag]() ### AI overview This article explains how the author used OpenAI Tools, also called Function Calling, with Azure OpenAI to build an AI Analyst connected to a complex order database. It contrasts this approach with earlier GPT-3.5, LangChain, SQL, and DAX-based methods, and distinguishes tool calling from Retrieval Augmented Generation. ### Source excerpt In recent months, I have been experimenting with AI tools to leverage new, powerful technologies and create value. Like you, I am inundated... ## The 3 (+2) ways to Get Data in Power BI, simply explained DevFeed: [The 3 (+2) ways to Get Data in Power BI, simply explained]() Original publisher: [Read original article]() Published: 2024-04-01T00:00:00Z Content type: tutorial Language: en Sources: [Mutt0-ds Notes]() Topics: [data](), [datasets](), [Database]() Tags: [data](), [database](), [dataset](), [excel](), [live-data](), [performance](), [query](), [semantic](), [tutorials]() ### AI overview This tutorial explains how Power BI Desktop stores and retrieves report data through Import Mode, DirectQuery, Live Connection, and Composite Models. It describes the trade-offs between local copied data and live queries, including refresh needs, scalability, and performance. ### Source excerpt There's quite a bit of confusion swirling around about how Power BI reports gather data. Where is the data actually stored? How frequently... ## My AI-tweaked Data Saturdays 23 Notes DevFeed: [My AI-tweaked Data Saturdays 23 Notes]() Original publisher: [Read original article]() Published: 2023-11-19T00:00:00Z Content type: article Language: en Sources: [Mutt0-ds Notes]() Topics: [Microsoft](), [Azure](), [sql-server](), [paas and iaas](), [Cloud](), [Databases]() Tags: [azure](), [blog-post](), [chatgpt](), [database](), [event](), [microsoft](), [mssql](), [ocr]() ### AI overview A blog post presents AI-assisted and manually checked notes from Data Saturdays 37 in Parma, covering Microsoft data platform technologies and SQL Server deployment options in Azure, including single databases, elastic pools, managed instances, purchase models, serverless operation, and Hyperscale. ### Source excerpt Last Saturday I had the privilege of attending Data Saturdays 37 at Parma, an event series focused on Microsoft data platform technologies.... ## Analyzing Swiss Car Accident Data to Inform Commute Timing with a Power BI Dashboard DevFeed: [Analyzing Swiss Car Accident Data to Inform Commute Timing with a Power BI Dashboard]() Original publisher: [Read original article]() Published: 2023-10-20T00:00:00Z Content type: tutorial Language: en Sources: [Mutt0-ds Notes]() Topics: [data](), [dashboards](), [Google Maps]() Tags: [car](), [dashboard](), [data](), [google-maps]() ### AI overview This article analyzes a decade of Swiss car accident data to understand when accidents are more likely and how that information may inform commute planning. It describes obtaining the data from a Swiss government dashboard, preparing multilingual fields, and working with Swiss coordinate data. The author emphasizes that the analysis is a general framework and cannot predict or prevent accidents or account for everyday disruptions. ### Source excerpt I want to express my gratitude for the positive feedbacks I received a few months ago when I used Google Maps data to determine the best... ## My Second Brain... 6 Months later: Obsidian update DevFeed: [My Second Brain... 6 Months later: Obsidian update]() Original publisher: [Read original article]() Published: 2023-09-13T00:00:00Z Content type: article Language: en Sources: [Mutt0-ds Notes]() Topics: [Obsidian](), [Markdown](), [Automation](), [Documentation](), [Python]() Tags: [automation](), [code](), [documentation](), [markdown](), [notes](), [obsidian](), [ocr](), [plugins](), [repository](), [scripts](), [search](), [security](), [update]() ### AI overview The author provides a six-month update on using Obsidian as a secure, structured repository for team documentation and personal notes. They describe collecting and organizing varied information, linking orphaned notes, storing code snippets, and experimenting with automation, including OCR-based conversion of PowerPoint and Word content into searchable Markdown. ### Source excerpt It's been quite the journey since I first delved into Second Brain technologies for organizing my team's documentation. I previously shared... ## Analyzing My Commute Data to Find the Best Time to Go to Work DevFeed: [Analyzing My Commute Data to Find the Best Time to Go to Work]() Original publisher: [Read original article]() Published: 2023-07-07T00:00:00Z Content type: article Language: en Sources: [Mutt0-ds Notes]() Topics: [Google Maps](), [API](), [Google Cloud Platform (GCP)](), [Simulation](), [data]() Tags: [api](), [data](), [google-cloud-platform](), [google-maps](), [simulation]() ### AI overview This article analyzes personal commute data using Google Maps traffic predictions and the Google Distance Matrix API. It simulates departure times in five-minute intervals across morning and evening travel windows, finding that the results generally align with the author's prior experience while noting seasonal traffic limitations. ### Source excerpt When my commute buddy and I find ourselves stuck in traffic during our car journeys, we often daydream about finding the ideal route and... ## The unnecessary hype strategy behind Microsoft Fabric DevFeed: [The unnecessary hype strategy behind Microsoft Fabric]() Original publisher: [Read original article]() Published: 2023-05-29T00:00:00Z Content type: opinion Language: en Sources: [Mutt0-ds Notes]() Topics: [Microsoft](), [data-engineering](), [Azure](), [Cloud](), [data lake](), [data-processing](), [etl](), [AI, ML & Data Engineering]() Tags: [azure](), [cloud](), [copilot](), [data](), [data-engineering](), [data-lake](), [data-processing](), [etl](), [microsoft](), [microsoft-azure](), [technical]() ### AI overview An opinion article examines Microsoft Fabric, a unified data platform announced at Microsoft Build. It describes Fabric's integration of data storage, processing, ETL, analytics, and business intelligence tools, while criticizing Microsoft's secrecy and hype-oriented launch strategy and noting that the platform was still in beta. ### Source excerpt If you are into Data Engineering in Microsoft Azure Cloud Environment, you probaly heard about Microsoft Fabric being announced last week... [Next page]()