Read "How I Built My Website" - Technical writing by Isaac Flath on software development, AI, and machine learning.

Read "The Future is Already Here (and it's in Japan)" - Technical writing by Isaac Flath on software development, AI, and machine learning.

Read "Learning from Failure: MonsterUI" - Technical writing by Isaac Flath on software development, AI, and machine learning.

Step-by-step example of the tool I use, how I use the UI, and how I use it agentically.

The Problem with grep for AI Agents

Mixedbread showed in their launch how much faster/better semantic search could make Claude code. Cursor also just announced semantic embedding support, and other agents are soon to follow. I got better quality with 1/2 tokens and almost 2x faster with mixedbread search. Learn what changed from the leading researchers in the space.

RAG famously (and incorrectly) written off as dead by many when agentic search became more popular for agentic coding. Recent advances in semantic search have dramatically outperformed agentic search. This engineering talk gives you the intuition and information to be an expert user.

Hey this is Isaac, This week I was fixing some basic and classic async problems: a

I ran into a classic background task UI problem in my app this week.

I was excited to host Hugo in our course for a talk.

Learn to build better software and learn more with LLMs and AI agents.

OpenHands (and All Hands, the company behind it) set to push the envelope with an agentic software development platform, all while remaining fully committed to their open-source origins.

Search isn’t magic. It’s engineering. 80% of users won’t look past the top 5 results. If those results are bad, they leave.

If you build apps with an AI agent, you probably want a way to go back in time to prior agent turns.

I had an idea, and a hacky prototype I wanted to build.

Over 100 pages of answered questions, guides, and tips and tricks from Isaac Flath and Eleanor Berger!

Sometimes AI teaches me something and sometimes AI is a better rubber duck. Both are useful

In the spirit of Feynman’s “What I cannot create, I do not understand,” this optional outtake from our course is a live mini-build: we’ll code a simple AI coding agent together to form a real mental model and better understand the tools we use. We’ll practice context management, clear specs, small steps, and interactive + structured flows. Join to watch — or hack along.

Your Copilot subscription now comes with a dedicated terminal-based agent

What Developers Are Actually Using for AI Coding in 2025

In the spirit of Feynman’s “What I cannot create, I do not understand,” this optional outtake from our course is a live mini-build: we’ll code a simple AI coding agent together to form a real mental model and better understand the tools we use. We’ll practice context management, clear specs, small steps, and interactive + structured flows. Join to watch — or hack along.

Creating presentations agnatically with AI

Using stored chat history as context to create richer more complete blog posts drafts

In the last post, we covered the three architectures for reusable LLM tools. That post prompted some great follow-up questions about the practical differences between these approaches, especially how using command-line (CLI) scripts as tools fits into the picture.

How to retain creative control and direction over AI when you aren't writing much of the code

How you define tools is an architectural choice with trade-offs between control, development speed, and portability.

The Terminal Reimagined as an AI-Powered Coding Agent

When working with AI coding agents in environments without explicit command approvals or sandboxes, file deletion commands pose a significant risk.

A significant trend is emerging among top engineering leaders.

A Practical Guide to Automating Software Development with AI Agents

While some LLMs can read certain file formats like PDFs directly, all LLMs excel at processing Markdown. This makes Markdown the ideal format for feeding documents and information to AI coding agents. By configuring your agent with the markitdown-mcp

Beyond Claude: AI Features in Marimo Notebooks and Bespoke Agents

Are you making the most of AI-assisted development? Take this 5-part self-assessment to rate capabilities across foundational knowledge, interactive use, context & environment, development process, and governance. Get a readiness score plus personalized priorities and learning resources.

Unlock powerful AI debugging workflows by connecting your agents directly to observability data. Pydantic Logfire's MCP integration enables LLMs to query traces, metrics, and logs in real-time, transforming how you monitor and troubleshoot AI applications.

AI agents have solved the building problem. Now everyone can code. But most people build the wrong things, faster. At SpecStory, we combine rigorous product thinking with agentic dev. It's how we replaced AshbyHQ, TypeForm and build Micro-SaaS that people actually pay for (above and beyond our core Products). This will be hands-on and leave you practical examples so you can do it yourself.

Charlie will walk you through how to run Claude Code in parallel and how to maximize the benefits of your new AI employees, and demonstrate how to leverage agent orchestration environments to enhance throughput.