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...

Multiple Claude Code agents running at the same time? That's what Conductor let's you manage, your own agent team. I'm talking to the founder, @charliebholtz , on August 22nd. You're going to want to bookmark this 💾 maven.com/p/de5b4e/th...

Everything you wanted to know about agentic coding is in this talk with @lambdapocalypse He's the Chief Architect at All Hands and is joining us for a talk on September 9th. It's going to be excellent. Sign up now - link in 🧵

Evals weren't that popular to talk about until Hamel started writing about them. Now, he is running the largest and most successful evals course in history Join to learn how he uses AI to write compelling & practical content that makes an impact maven.com/p/15c637/wr...

Hi, this is Air, the new web framework that breathes fresh air into Python web development

I'm launching Context Engineering For Coding to make AI assisted coding more efficient, and it works with Cursor, Claude Code, Copilot, all of them. Here's a 30% off discount link for early enrollers maven.com/kentro/cont...

I was kinda surprised that people joined my new discord, and got a bit excited yesterday and created and published a new website around it and started with a new free tutorial :D Check it out: kentro-learn.com/free-content...

A repository that has a retrieval MVP and a custom retrieval eval app set up is ready for you to start experimenting :D Links to the blog posts that explain & show how to create all that is in the readme if you missed them github.com/Isaac-Flath/...

What's the most important task in AI? Looking at data! This means one of the highest ROI activities is building a custom data viewer. FastHTML is unique in that you can co-locate everything into a single file that is easily understandable, using only Python! isaacflath.com/blog/blog_po...

90% of users never scroll past the first page of search results, and most only scan the top 3-5 entries before giving up. If you've spent hours creating something only to have it disappear into the void, I've got a solution. Let me show you your MVP 🧵

AnswerAI's MonsterUI as presented by @isaac-flath.bsky.social A new Python library from AnswerDotAI that makes building beautiful web UIs for FastHTML apps as simple as writing Python code. No more wrestling with CSS! monsterui.answer.ai

🎉 New FastHTML Gallery entries! ✅ Loading Content with HTMX thanks to @audreyfeldroy.bsky.social ✅ Loading indicator when HTMX requests are in flight Check them out! 1. Loading Indicator: gallery.fastht.ml/split/dynami... 2. Update Content: gallery.fastht.ml/split/dynami...

🎉 New FastHTML gallery entry! Inspired by a blog post by @danielcorin.com , @carlolepelaars.bsky.social added a multiple image upload example Check it out! gallery.fastht.ml/split/dynami...

There are lots of HTMX examples on the FastHTML Gallery thanks to fantastic community contributors 🤩 Check them out @ gallery.fastht.ml

🎉 New FastHTML Gallery entry thanks to Adnan! ✅ Add custom keybindings with HTMX

🎉 New FastHTML Gallery entry! Dynamic dropdown with: ✅ Search box in dropdown ✅ Input for users to add additional values

🎉 New FastHTML Gallery entry thanks to @carlolepelaars.bsky.social HTMX example demonstrating click to load new table row 😃

I want to give a big shout out to all the people that have helped make Shell Sage what it is today @isaac-flath.bsky.social For hacking on me during the early versions back when it was called "BashBuddy". Our pairing sessions are one of the best parts of working at @answerdotai!

ShellSage took me from swearing at AWS/GCP services to deciding to "just" set up my own server with a reverse proxy to host all my apps. I use ShellSage as a learning aid, and the boost in my learning speed in a huge unlock for me. A must have tool.

Quick TIL on rendering @scikit-learn.bsky.social pipelines with FastHTML. I will do one soon on rendering full skops model cards, which feature not only models, but can also include metrics, feature importance, plots, metadata and tables. carlo.ai/til/fasthtml...