AI Engineering
Practical ideas and tools for building with AI.
About this list
This reading list brings together items from the sources selected for AI Engineering. Open each item at its original source for the complete article, episode or video. This is a selection of current coverage, not a complete archive.
Latest podcasts
Newest first
Your AI-built app looks done until you use it. Reverse Engineer Anything (REA), the tool past 200,000 GitHub stars, shows how software you own handles the job
REA stands for Reverse Engineer Anything. It’s an open-source tool that gives AI coding assistants such as Codex and Claude Code a way to investigate existing software, including programs whose original source code you don’t have. You point your agent at an application or a supported browser session and ask how a particular feature works. REA supplies tools to inspect the code and behavior. Your agent uses those findings to explain the mechanism and help you build something of your own.
Uber’s AI infra, from the inside
Uber Distinguished Engineer Uday Kiran Medisetty shares how Uber builds internal developer tools, integrates AI agents into engineering workflows, and measures their impact on productivity.
Why could the same AI rebuild a 16,000-line program without seeing its code, yet fail to customize a library for METR? The answer shapes what you hand it
Watch now (21 mins) | Are we developing a more general intelligence, or getting much better at producing extraordinary abilities that transfer unevenly?
The Science and Engineering of Agent Work
Hilary Mason, Eric Ma, Bryan Bischof, and Tomasz Tunguz on experimentation, creative evals, agentic data science, and local agent
Executive Briefing: The 5 Skills That Help One Person on Your Team Carry More of the Work
Going beyond the video: how taste, agency, focus, resourcefulness, and follow-through develop together, through work that changes your understanding of what you can take on.
Google bid $10 million for an airline’s old work emails to train AI. Much of what made that work matter never showed up in an email
Google wants to learn from the record of our working lives. We should take a closer look ourselves, because understanding what our work accomplishes could change what we attempt next.
Building resilient systems with Sam Newman
Sam Newman joins me to discuss when to use microservices, how to build resilient distributed systems, and how AI is changing software development.
Your customers won’t ask for Gemini 4 Argon. Their best AI product idea probably isn’t in their feature requests either. Four questions surface the work they gave up on
Google’s new Gemini 4 Argon model has impressive benchmark results. Google says it leads the Vals Index, which evaluates professional work across several fields. The initial rollout is limited to trusted cybersecurity defenders, with broader access planned. Google has described internal uses and early customer work, but most of us still can’t use it ourselves.
ComplexMCP Finds Tool-State Gaps
ComplexMCP is a useful benchmark because it tests the part of tool use that simple function-calling tasks avoid: one action changes the state that the
The State of Agentic Data Science
What to Delegate, How to Verify
Executive Briefing: Before You Renew Software, Ask Your AI Power Users 4 Questions
The people using AI on your team are already making decisions about the future of your software. They are choosing which data matters, which application steps they can skip, which workflows they still trust, and which agent does the work. A surprising amount of your software strategy may already exist in those choices. Your leadership team has to go and learn it.
Android Bench Tests Long Coding Work
Android Bench turns mobile coding evaluation from small patch repair into long-horizon Android work. Google says the updated benchmark adds multi-day
Can Memory Systems Track a Group?
GroupMemBench reframes agent memory as a group problem, not a private chat log. The paper argues that assistants used inside teams need to remember who
Hitting your ChatGPT limit? Try Sol before paying $300 more
Used together, Dots, Space, and Sol turn the context you've built with AI into a shared workspace. The questions to ask are what can it take on and what does that work cost?
Only Allowed Copilot? 5 Habits I’d Build That Carry to the Next Model
Your company may have already decided where you can put its information. You might have a strong opinion about which model is smartest. I see it in company after company: Microsoft is what the employer trusts.
Academia is for Ambition — Alex Zhang, MIT
We catch up with RLM first author Alex Zhang, MIT PhD, on Jev, PhD masxing, and the future of harnesses.
Why Dwarkesh is Wrong about Computer Use + How OpenAI shipped its Jev competitor in 1 Week
Our DevDay coverage - the first pod on the DevDay lineup - dives in with the leaders of OpenAI’s CUA team and API platform.
Distributed databases with Peter Mattis
Cockroach Labs co-founder Peter Mattis discusses building reliable distributed systems and how AI helps him write more code without sacrificing quality.
Does your work cost less on Opus 5.5 now that its tokens are 20% cheaper? My 3-prompt guide shows which jobs do before you move them
With Opus 5.5, I can give the model direction, make a correction, and keep developing the thing I wanted. That sounds ordinary until you’ve spent a session explaining the same requirement repeatedly and wondering why a system this capable is so difficult to work with.
KNOWS Tests Browser Work After Search
The KNOWS paper turns web-agent evaluation from finding information into producing a usable document, spreadsheet or slide deck
Showing 20 of 48 podcasts
Know a source we’re missing? Tell us about it