I visit my own website because it makes me happy. AI wrote every line of code, but I directed everything. If a thoughtless prompt can make what you make, why would I come to you? I can prompt AI myself This post shows the core skill for using AI: taste isaacflath.com/writing/how-...

In the U.S., new glasses take a few days. In Japan, they took 45 minutes and $70. Transit, check-in, doors, customs, toilets all just felt nicer. I wrote about it. isaacflath.com/writing/japa...

I spent months building MonsterUI. Now, when people ask if they should use it, I hesitate. MonsterUI redefined what I love to build, yet I couldn't explain why I stopped using it. I felt uncomfortable admitting that I failed Here's what happened and what I learned isaacflath.com/writing/lear...

AI generates code faster than humans can read. When the machine outpaces the reviewer, the team loses understanding. We need to keep humans in control. Jake Levirne of SpecStory, shared how they adapt the review process to the task's risk for this elite-ai-assisted-coding.dev/p/legible-ai...

I used an AI agent to build a Discord bot. I wanted it to save images from a channel to S3. The agent wrote the code, explained deployment, and debugged it when it went silent. It's a small tool I use daily. Link: isaacflath.com/writing/disc...

I often ask: Why this way? What were the trade-offs? Was X considered? Why not Y? Ex: "Why is the react editor in the main python repo and not its own module?" AI logs and other context is a key part of answering that. Here's what I do 👇 elite-ai-assisted-coding.dev/p/how-i-use...

I quit my job ~6 months ago to focus on learning and having a bigger impact. The AI coding course with Eleanor Berger is one (of several) projects that is better than I imagined on both fronts Cohort 1 was a huge success, and Cohort 2 in January is gonna be even better 😄

My favorite thing about reducing token usage for coding agents with better search with @mixedbreadai

Multi-vector search means semantic search is back for coding agents...and it was always clear it would

60% of tokens are spent searching and exploring the codebase. Agents need better search.

mgrep helps explore complex documents and pdfs

AI coding agents burn tokens guessing keywords for grep and flood the context window with noise There's a better way. I hosted a talk by @ruithebaker, a founding engineer at @mixedbreadai, about their solution. mgrep 🧵 elite-ai-assisted-coding.dev/p/mgrep-wit...

Q: Why is semantic search for code coming back? (Cursor, mgrep, etc) A: Multi-vector architecture Q: Why do I care? MUCH less token usage + better responses if used Q: What makes it work? A: Token (not chunk) level embeddings with extreme quantization Here's what I learned 🧵

I got better quality, half the tokens, and twice the speed with MixedBread's mgrep The "trick" is a multi-vector architecture. Why now? Because the arch and quantization details are hard Join Aamir Shakir (MixedBread Founder) for a research talk on how it works 👇 maven.com/p/0c0eed/mo...

RAG isn't dead, it evolved I compared the new semantic search (RAG) against default agentic search (also RAG 😄) for coding agents. Semantic search won Rui Huang ( MixedBread ) will give an engineering talk on why, intuition, and setup Sign up 👇 maven.com/p/9c51af/th...

Using Alpine.js in Python frameworks like Air, Fasthtml, or Dash often means you end up writing code in strings Writing code inside a string is a terrible dev experience and hard to maintain. But I also kinda hate jinja TBH

This week I was fixing some basic and classic async problems: a "processing" pill that never updated to "complete." Blech. Read the details from my new newsletter 👇 isaacflath.com/newsletter/2

Faced a classic async UI bug: a "processing" pill didn't update I used AI to brainstorm to get 4 patterns (I chose self-polling pill) AI is good at giving common patterns fast so I can spend more time on decisions and considering less obvious options elite-ai-assisted-coding.dev/p/using-an-...

AI demos often get stuck in "Proof of Concept Purgatory" by jumping to agents too early. Hugo shares a framework for building AI products, by progressing through the "agentic spectrum" iteratively , starting with augmented LLMs and workflows elite-ai-assisted-coding.dev/p/stop-buil...

AI Assisted Coding Cohort 1 just ended and feedback is coming in. Really happy to hear V1 was beneficial to so many people ❤️ Feedback also means huge improvements coming for cohort 2 😁 I still have quite a lot to add, but I'm adding reviews here! isaacflath.com/course/elit...

Learn from Open Hands, a powerful open-source async agent platform, about how to build your own agents and how their agent SDK helps. maven.com/p/0fe39a/op...

RAG is how you use search to gives users what they need. My new RAG course just launched, I hope to see you there!

I love hearing feedback like this about the new RAG course ❤️ To learn more about the course go here: elite-ai-assisted-coding.dev/p/learn-rag...

80% of users won’t look past the top 5 results. If those results are bad, they leave. I just launched a RAG course, here’s a post on what you'll learn and why the concepts matter in modern AI systems elite-ai-assisted-coding.dev/p/learn-rag...

Building in prior version rollback for AI agents is a pain (code and db). Neon’s new snapshots API solves this. Save a complete snapshot of your db, schema, and data with each agent turn. It's efficiently done with copy-on-write vs full copies too. elite-ai-assisted-coding.dev/p/build-che...

I used AI to turn a hacky prototype into a full app in one day and understood every line of code This workflow is for using AI to map out a plan, make architectural decisions, implement features step-by-step. And I code and refactor where it matters elite-ai-assisted-coding.dev/p/using-ai-...

Code with AI smarter, not harder ⚡ This free 100+ page book is packed with pro-tips, step-by-step guides, and solutions to accelerate your workflow. Get your copy 👇 maven.com/p/aa2670/ti...

AI suggested a dependency I didn't understand. Instead of accepting or rejecting, I asked why The debate and research taught me more about my async stack than a tutorial ever could AI suggestions are opportunities to learn Details + more examples 👇 elite-ai-assisted-coding.dev/p/i-argue-w...

Join us and more than 1,600 others next week as we dive into building a coding agent from scratch! maven.com/p/b9a2df/bu...

What happens when a whole engineering team learns to use AI together? They build a common language & framework for prompts, context, tools, and automations. This mean effective collaboration, faster problem-solving, and code that is consistent across your team.

GitHub's new Copilot CLI gives: ✅ Terminal agent interface like claude code, opencode, gemini CLI ✅ A more transparent and predictable "per-request" billing model See how using it to create and use an MCP server went👇 elite-ai-assisted-coding.dev/p/github-co...

We ran an informal survey to find out what AI tools developers are using in their work 👇 elite-ai-assisted-coding.dev/p/ai-coding...

Want to truly understand how AI coding agents work? The best way is to build one. Join us for a FREE live workshop where we'll code a simple AI agent from scratch. Sign up here: maven.com/p/b9a2df/bu...

I stopped building presentations manually. My new workflow lets me focus on the story, not the mechanics. I can be more creative, try ideas and iterate on faster The result is a better story, built faster, more enjoyably Here's the process and details elite-ai-assisted-coding.dev/p/a-better-...

The code shows 'what' but AI chat logs shows 'why.' ✍️ Raw chat logs are great context for making posts b/c they include key parts of the development process. False starts, mistakes, questions, decisions, etc. How I turn that data dump into a post 👇 elite-ai-assisted-coding.dev/p/turning-a...

I got a lot of questions about a recent post, here's my answers to the highlights of CLI scripts vs. MCP servers. 🔹 Do LLM APIs know how a tool was defined? 🔹 What are the real-world differences in token usage? 🔹 MCP or a CLI for your workflow? elite-ai-assisted-coding.dev/p/llm-tool-...

I documented how I created a 74-second promo video draft for a new framework, air, in 30 minutes How to stay in control of AI: ✅ Injecting human taste ✅ Correcting AI errors ✅ Improving code examples ✅ Syncing animations to music, and more. elite-ai-assisted-coding.dev/p/from-zero...

How to add LLM to tools is an architectural decision. I break down 3 main paths: 🔹 Direct SDKs 🔹 Higher-Level Libraries 🔹 MCP Servers A guide on the trade-offs in control, speed, and portability elite-ai-assisted-coding.dev/p/the-3-arc...

I've been using Warp more nnd more. Cursor's integrated terminal Cmd+K feature is nice, but Warp takes it further. And agent mode is great for quick stuff and keeps me from context switching @intellectronica wrote deep-dive on Warp and its agent elite-ai-assisted-coding.dev/p/warp-term...

Use `trash` instead of `rm` for some peace of mind with agents. It moves files to the recycle bin instead of permanently deleting them. It's a simple way to prevent catastrophic mistakes by an autonomous agent. Here's how to configure it elite-ai-assisted-coding.dev/p/use-trash...

The single biggest productivity lever for dev teams is a shared system When your entire team can turn generic AI assistants into personalized partners that deeply understand your codebase, the results compound Here we explain how to build that system elite-ai-assisted-coding.dev/p/the-singl...

Continuous AI leverages asynchronous, autonomous agents running in the background It can automate code reviews, keep documentation fresh, and enforce best practices, freeing you up to solve bigger problems A practical guide to getting started: elite-ai-assisted-coding.dev/p/adventure...

LLMs excel at Markdown but can be limited with other formats. markitdown-mcp fixes this by converting virtually any file (PDF, Word, Excel, images, audio & more) into clean, AI-friendly Markdown. elite-ai-assisted-coding.dev/p/markitdow...

Claude is powerful, but it can't do everything. What if you need reactive programming, dynamic UI, and truly custom agents that access runtime variables? Explore how Marimo notebooks & Bespoken agents give you that elite-ai-assisted-coding.dev/p/agents-to...

Are you really set up and ready to do AI-assisted software development in the most productive way possible? Find out in this free test: maven.com/p/53a27c/se...

Logfire MCP from Pydantic is a powerful tool for connecting AI agents to to observability data Pydantic founder Samuel Colvin is joining mefor a live chat on September 4th. More details in next post: maven.com/p/793af4/lo...

"Everyone can code now with AI. ...but people are building the wrong things." Join Greg Ceccarelli and Jake Levirne on August 19th for a talk on Product Thinking for Agentic Development maven.com/p/395a4d/pr...

Sometimes one-time throwaway code is great Stefanie Hetjens from EVERYWOW is going to show how she created a broadcasting graphics solution in 6 hours You'll learn when it's smarter to code a one-time solution to your engineering problem

I haven't seen anything like this anywhere else. Join the live talk (or sign up for the recording after) maven.com/p/de5b4e/th...

If you're not leveraging Just and UV scripts in your daily workflow, you're missing out on a lot. They "just" work too well together This is how I build a control panel for personal productivity, the easy way, with Uv Scripts, Just, and AI Agents Link: elite-ai-assisted-coding.dev/p/isaac-per...