101+ gen AI use cases with technical blueprints
📰 ai
Accelerating Large-Scale Test Migration with LLMs
Airbnb recently completed our first large-scale, LLM-driven code migration, updating nearly 3.5K React component test files from Enzyme to use React Testing Library (RTL) instead.
weeklyfoo #84 / 2025-05-12aimigration
AI Coding Agents
AI fakers exposed in tech dev recruitment: postmortem
A full-remote security startup nearly hired a backend engineer who doesn’t exist, after a candidate used an AI filter as an on-screen disguise in video interviews. Learnings for tech companies
weeklyfoo #76 / 2025-03-17recruitmentaisecurity
AI Makes Bad Managers
It’s performance-review season and I’m watching managers kneecap their careers. Gleefully they share the best prompts to have ChatGPT write their performance assessments - exactly the sort of shortcut that guarantees they’ll never get better at the job.
weeklyfoo #87 / 2025-06-02leadershipai
AI slows down open source developers. Peter Naur can teach us why.
A view on the Metr paper about developer performance using AI tools
weeklyfoo #94 / 2025-07-21aiengineeringperformance
Analyzing Database Trends Through 1.8 Million Hacker News Headlines
I used camelAI with a ClickHouse database of every HN story to do all analysis. You can use it for free with no login here to explore the data interactively yourself.
weeklyfoo #94 / 2025-07-21aidatabase
Announcing v0: Generative UI
Bash One-Liners for LLMs
Best Practices for Building Agentic AI Systems
Building a web search engine from scratch in two months with 3 billion neural embeddings
A while back, I decided to undertake a project to challenge myself: build a web search engine from scratch.
weeklyfoo #98 / 2025-08-18searchai
Building Astro sites with AI tools
This guide covers how to enhance AI tools with up-to-date Astro knowledge and provides best practices for building Astro sites with AI assistance.
weeklyfoo #94 / 2025-07-21astrtoaimcp
Building effective agents
Over the past year, we’ve worked with dozens of teams building large language model (LLM) agents across industries. Consistently, the most successful implementations weren’t using complex frameworks or specialized libraries. Instead, they were building with simple, composable patterns.
weeklyfoo #65 / 2024-12-30ai
Built With Borrowed Hands
I spent two months forcing an unnatural constraint on myself: what if I could only rely on agents writing code for a real-world production service?
weeklyfoo #97 / 2025-08-11ai
Claude can now create and edit files
Claude can now create and edit Excel spreadsheets, documents, PowerPoint slide decks, and PDFs directly in Claude.ai and the desktop app.
weeklyfoo #102 / 2025-09-15claudeai
Claude Code Unleashed
Claude Code: Best practices for agentic coding
Claude Code is a command line tool for agentic coding. This post covers tips and tricks that have proven effective for using Claude Code across various codebases, languages, and environments.
weeklyfoo #82 / 2025-04-28aiclaude
Context Engineering for Agents
Agents need context to perform tasks. Context engineering is the art and science of filling the context window with just the right information at each step of an agent’s trajectory. In this post, I group context engineering into a few common strategies seen across many popular agents today.
weeklyfoo #96 / 2025-08-04aiagent
DeepWiki: Understand Any Codebase
Eight ways I use DeepWiki to speed up real coding work
weeklyfoo #100 / 2025-09-01deepwikiaiengineering
Devin 2.0
Don’t Build AI Products The Way Everyone Else Is Doing It
If you want to build AI products that are unique, valuable, and fast, don’t do what everybody else is doing.
weeklyfoo #6 / 2023-11-12ai
Don’t Build Multi-Agents
Frameworks for LLM Agents have been surprisingly disappointing. I want to offer some principles for building agents based on our own trial & error, and explain why some tempting ideas are actually quite bad in practice.
weeklyfoo #101 / 2025-09-08aiagent
Drawing to Logo
Instructions how to use Bing chat to create a logo from a drawing
weeklyfoo #3 / 2023-10-22ailogo
Evaluating LLMs for my personal use case
Everything I Know About GitHub Copilot Instructions
Field Notes From Shipping Real Code With Claude
From Memo to Movement
The non-obvious insights, tactics and workflows Shopify used to bring an ambitious memo to life
weeklyfoo #94 / 2025-07-21aiengineering
Gemini Nano in Chrome 137
Get coding help from Gemini Code Assist — now for free
Developers worldwide now get free AI-assisted coding help with the highest usage limits available, as well as code review assistance.
weeklyfoo #74 / 2025-03-03aigemini
GitHub Copilot now available in github.com for Copilot Individual and Copilot Business plans
With this public preview, we’re unlocking the context of your code and collaborators—and taking the next step in infusing AI into every developer’s workflow.
weeklyfoo #52 / 2024-09-30aigithubcopilot
GitHub Copilot Workspace
GitHub Spark lets you build web apps in plain English
Goodbye Upgrade Fatigue — How Cursor Upgraded Our Storybook in Just 2 Hours!
Upgrading dependencies is the kind of task everyone tries to avoid — especially when it involves a library like Storybook, known for frequent updates and breaking changes.
weeklyfoo #90 / 2025-06-23cursorai
Grok API Public Beta
Starting today, developers can build on our Grok foundation models using our newly released API.
weeklyfoo #58 / 2024-11-11grokai
How and where will agents ship software?
How I Code with AI on a budget/free
You don’t have to spend hundreds of dollars on AI tools to get started.
weeklyfoo #98 / 2025-08-18aibudget
How I Effectively Use Roo Code for AI-Assisted Development
Roo Code — formerly Roo Cline, a fork of Cline — is an autonomous coding agent that I’ve been getting a lot of use from over the past few months.
weeklyfoo #84 / 2025-05-12ai
How I Use Claude
Claude is Anthropic’s AI, like ChatGPT but more capable. I was a casual user until the 23 October release (informally “Claude 3.6”), when it crossed a quality threshold I didn’t even know was there. It is really, really good. I have been using it a lot more since, and I got curious as to how much more.
weeklyfoo #66 / 2025-01-06ai
How I'm Posting This Article Using Model Context Protocol (MCP)
How might AI change programming?
How to Design APIs for an AI World
A thorough analysis of how AI changes what is needed from a good API, with real-world examples + some speculations about the future.
weeklyfoo #89 / 2025-06-16apisaidesign
How to Vibe Code as a Senior Engineer
Over the past few months, I’ve rediscovered my love for building software.
weeklyfoo #91 / 2025-06-30aivibe-coding
How we built Product Intelligence
Last month we launched Product Intelligence to help product teams handle incoming issues and put them in the right place in the backlog.
weeklyfoo #102 / 2025-09-15ailinear
How we revamped our Docs for AI
Ingesting Millions of PDFs and why Gemini 2.0 Changes Everything
Chunking PDFs—converting them into neat, machine-readable text chunks—is a major headache for any RAG systems. Both open-source and proprietary solutions exist, but none have truly achieved the ideal combination of accuracy, scalability, and cost-effectiveness.
weeklyfoo #71 / 2025-02-10aigemini
Inside OpenAI: How does ChatGPT Ship So Quickly?
Since it arrived a year ago, ChatGPT has been shipping at breakneck speed.
weeklyfoo #7 / 2023-11-19aiopenai
Introducing ChatGPT search
Get fast, timely answers with links to relevant web sources.
weeklyfoo #57 / 2024-11-04searchai
Introducing Codex
A cloud-based software engineering agent that can work on many tasks in parallel, powered by codex-1.
weeklyfoo #86 / 2025-05-26openaiai
Introducing GitHub Models - A new generation of AI engineers building on GitHub
We are enabling the rise of the AI engineer with GitHub Models–bringing the power of industry leading large and small language models to our more than 100 million users directly on GitHub.
weeklyfoo #46 / 2024-08-19ai
Introducing Pitch 2.0: The future of visual business
Introducing the Prompt Engineering Toolkit
It’s Humans All the Way Down
Good quick read about that AI won’t easily replace all the humans.
weeklyfoo #15 / 2024-01-14ai
Langchain Templates
LangChain Templates are the easiest and fastest way to build a production-ready LLM application.
weeklyfoo #5 / 2023-11-05ailangchaintemplates
Leading your engineers towards an AI-assisted future
Leaked GPTs
Let’s kill vibe coding and bring back prompt engineering
levered beta is all you need
MacOS meets van Gogh
MCP UI
MCP Vulnerabilities Every Developer Should Know
This post covers the biggest risks (with real examples) and how to think about MCP securely.
weeklyfoo #98 / 2025-08-18securityaimcp
Microsoft’s Copilot app is now available on iOS
The Microsoft Copilot app lets you ask questions, draft text, and generate images using AI.
weeklyfoo #14 / 2024-01-07aicopilotmicrosoft
Midjourney V6 is here with in-image text and completely overhauled prompting
Mistral AI, a Paris-based OpenAI rival, closed its $415 million funding round
My Current AI Dev Workflow
Ghostty + Claude Code + minimal tooling = maximum productivity.
weeklyfoo #100 / 2025-09-01aiproductivity
My experience creating software with LLM coding agents - Part 2 (Tips)
This post details my experiences creating software with LLM coding agents, emphasizing that what you do with AI agents is ‘creation’, not just ‘coding,’ and sharing what worked for me.
weeklyfoo #100 / 2025-09-01aitips
No, AI is not Making Engineers 10x as Productive
Nobody Knows How To Build With AI Yet
The future of software development might just be jazz. Everyone improvising. Nobody following the sheet music.
weeklyfoo #95 / 2025-07-28aiengineering
Ollama's new app
PDF Chat with Node.js, OpenAI and ModelFusion
Practical AI techniques for daily engineering work
I love these ones: the second opinion and the throwaway technique.
weeklyfoo #86 / 2025-05-26engineeringai
Principles for coding securely with LLMs
Writing code with LLMs is fundamentally different from other ways of programming. LLMs are often non-deterministic and always unpredictable. They have a capability that no other technology can match: the ability to interface with natural language. What does that mean for security?
weeklyfoo #81 / 2025-04-21aisecurity
Prompt Of The Year: 2023 🌟
In the evolving world of Large Language Models (LLMs), crafting effective prompts has become an essential skill. That’s why I’ve created this collection, showcasing the most impactful prompts of the year across various intriguing domains.
weeklyfoo #13 / 2023-12-31aiprompts
Senior Developer Skills in the AI Age
SEO Is Dead. Long Live GEO.
How to win in the era of LLMs, AI Overviews, and GEO — before your traffic disappears
weeklyfoo #93 / 2025-07-14seogeomarketingai
Software engineering with LLMs in 2025: reality check
How are devs at AI startups and in Big Tech using AI tools, and what do they think of them? A broad overview of the state of play in tooling, with Anthropic, Google, Amazon, and others
weeklyfoo #92 / 2025-07-07ai
Stuff we figured out about AI in 2023
Summarizing with Transformers.js
Switching to Claude Code + VSCode inside Docker
Last night I finished a transition from my old AI coding setup I’ve been using for a while to running Claude Code in Docker using VSCode’s “Dev Container” feature. In this post I lay out a few of my thoughts on why I wanted to switch to something in the first place, and also a short guide for those who want to do the same.
weeklyfoo #94 / 2025-07-21aiwork-setup
Tech's Dumbest Mistake
The Bitter Lesson
The Brute Squad
The End of Programming as We Know It
There’s a lot of chatter in the media that software developers will soon lose their jobs to AI. I don’t buy it.
weeklyfoo #71 / 2025-02-10aiengineering
The enshittification of tech jobs
The Fastest AI Code Editor
The Hidden Cost of AI Coding
The Intelligence Age
In the next couple of decades, we will be able to do things that would have seemed like magic to our grandparents.
weeklyfoo #52 / 2024-09-30ai
The Last Programmers
We’re witnessing the final generation of people who translate ideas into code by hand.
weeklyfoo #102 / 2025-09-15ai
The last six months in LLMs, illustrated by pelicans on bicycles
The LLM Curve of Impact on Software Engineers
There is so much debate online about the usefulness of LLMs. While some people see giant leaps in productivity, others don’t see what the fuss is about. Every relevant HackerNews post now comes with a long thread of folks arguing back and forth. I call it the new Great Divide.
weeklyfoo #72 / 2025-02-17engineeringai
The promise and challenges of crypto + AI applications
Not (that) web dev relevant, but anyways a good read how AI and Blockchain can benefit from each other
weeklyfoo #18 / 2024-02-05aiblockchain
The Prompt Engineering Playbook for Programmers
Turn AI coding assistants into more reliable development partners
weeklyfoo #88 / 2025-06-09promptsai
The Second Half
The web isn’t URL-shaped anymore
The Year in Computer Science
Artificial intelligence learned how to generate text and art better than ever before, while computer scientists developed algorithms that solved long-standing problems.
weeklyfoo #12 / 2023-12-24ai
Top ways to ensure your content performs well in Google's AI experiences on Search
As a site owner, publisher, or creator, you may be wondering how to best succeed in our AI search experiences, such as AI Overviews and our new AI Mode.
weeklyfoo #87 / 2025-06-02googleai
Using AI Without Leaving the Terminal
v0.dev -> v0.app
Vibe Coding as a software engineer
There’s a lot of talk about “vibe coding”, but is it just a vague term for prototyping, or could vibes change how we build software?
weeklyfoo #88 / 2025-06-09aivibe-coding
Vibe Coding Is Creating Braindead Coders
Confession: I’ve been using Claude Code to write all my code for me. And I think it’s making me worse at the thing I’ve loved doing for twelve years.
weeklyfoo #103 / 2025-09-22aivibe-coding
Vibe coding is rewriting the rules of technology
Vibe Coding Terminal Editor
I wrote a small tool for myself as my biannual routine check of where llms are currently at.
weeklyfoo #101 / 2025-09-08ai
Vibe Coding Tips and Tricks
Note This field is evolving quickly, and we will update this guide as new methods and recommendations arise.
weeklyfoo #99 / 2025-08-25aivibe-coding
Vibe Shift? Senior Developers Ship nearly 2.5x more AI Code than Junior Counterparts
Fastly’s July 2025 survey of 791 developers found a notable difference in how much AI-generated code is making it into production.
weeklyfoo #101 / 2025-09-08aisurvey
We Put a Coding Agent in a While Loop and It Shipped 6 Repos Overnight
This weekend at the YC Agents hackathon, we asked ourselves: what’s the weirdest way we could use a coding agent?
weeklyfoo #100 / 2025-09-01aihackathon
What does AI engineering look like in practice?
Hands-on examples and learnings from software engineers turned “AI engineers” at seven companies
weeklyfoo #78 / 2025-03-31aiengineering
What We’ve Learned From A Year of Building with LLMs
What Will Happen In 2024
Why I stopped using AI code editors
I chose to make using AI a manual action, because I felt the slow loss of competence over time when I relied on it, and I recommend everyone to be cautious with making AI a key part of their workflow.
weeklyfoo #79 / 2025-04-07ai
Why I'm Betting Against AI Agents in 2025 (Despite Building Them)
I’ve built 12+ production AI agent systems across development, DevOps, and data operations. Here’s why the current hype around autonomous agents is mathematically impossible and what actually works in production.
weeklyfoo #95 / 2025-07-28aiagent
Will AI Replace Human Thinking?
window.ai - running AI LOCALLY from DevTools!
You are using Cursor AI incorrectly...
I’m hesitant to give this advice away for free, but I’m gonna push past it and share it anyway. You’re using Cursor incorrectly.
weeklyfoo #72 / 2025-02-17cursorai