Skip to content
Sign in
Artwork for AI Worth Using
Technology

AI Worth Using

The Show for Agentic Engineers

AI Worth Using is the show where Plow founder Sam Odio and GitHub co-founder Tom Preston-Werner install AI tools live, on camera, with the people who actually built them. No benchmark comparisons, no sponsored takes. Just installing it, learning it, and both of them giving their honest verdict on whether it's actually worth using in your workflow.

Play
Open in
  • 3 episodes
  • Avg 37 min
  • English

Episodes 3

NewestOldestLongest
All3Unplayed3In progress0Played0
  • #2
    August 31 · 48 min

    The Adversarial Review System Every AI Coding Agent Needs with Wes McKinney at Kenn Software

    The creator of pandas doesn't read his own code anymore. His review system does, and it trusts nothing. Wes McKinney, creator of pandas and founder of Kenn Software, has agents write his software. RoboRev is what keeps that honest: an adversarial pipeline where a different frontier model tears apart every commit about 90 seconds after it's written, in the background, before it ships. Wes walks us through the origin (Claude Code in one terminal pane, Codex reviewing it in the other, dozens of times a day, until he automated it), why agents claiming "production ready" broke his trust for good, and why he says skipping automated review in 2026 is driving without a seatbelt. Tom installs RoboRev live on a fresh project, mistakes included, to see exactly how fast the loop runs. KEY TAKEAWAYS 00:00 Introduction 03:58 An adversarial code review pipeline sends every generated line through a different model before it ships 07:16 Early coding agents would claim finished, production-ready work that was neither finished nor production-ready 12:44 Regaining a sense of agency after months of doubting whether software engineers still have a role to play 21:31 Vibes-based bug finding validity lands somewhere around 70% to 80% for the best coding agents 35:52 An elaborate automated workflow raises an honest question: is this clarity or a touch of AI psychosis? 37:33 Keeping code review batches to roughly 70 lines at a time turns out to catch the most bugs 51:07 Spending $100 in tokens to review a 10,000-line pull request might be the easy call RESOURCES MENTIONED Wes McKinney LinkedIn https://www.linkedin.com/in/wesmckinn/ Kenn Software website: https://kenn.io/ RoboRev: https://roborev.io Superpowers (spec-driven development framework): https://github.com/obra/superpowers Pandas (Python data analysis library): https://pandas.pydata.org/ See how people are actually working with AI at https://aiworthusing.com/builder-index #AICodeReview #BuildInPublic #AITools

    • Transcript
  • #1
    August 31 · 1 hr 1 min

    When Claude Deleted My Tests: Jesse Vincent, Creator of Superpowers

    Jesse Vincent, creator of Superpowers (1.7M GitHub clones in two weeks), joins the show to share hard-won lessons from six months of building with AI agents. Jesse created RT (still running in Fortune 50 companies), led Perl 5, and built K-9 Mail (now Thunderbird for Android). He shares what happened when Claude started deleting his test suite, why managing AI agents mirrors managing junior engineers, and how persuasion principles from psychology transfer directly to prompt engineering. KEY TAKEAWAYS 00:00 Introduction 05:23 The only thing worse than a failing test is a reduction in test coverage — close every loophole 06:32 Writing AI skills is straight-up management; prose clarity and people skills matter more than syntax 07:39 Managing MIT undergrads in 2007 prepared Jesse for agents — smart, junior, no taste, poor memory 10:19 Skills need intent, not just process; agents execute better when they understand the why behind instructions 13:04 Encouragement outperforms pressure. Telling your agent you love it produces better outcomes faster and cheaper 19:11 Graphviz outperformed English for process clarity. Structured formats eliminate ambiguity that agents will otherwise misinterpret 26:58 Strongly typed languages like Go and TypeScript produce more reliable agent-written code than Python 30:19 Jesse is easily 10x more productive, but it's harder work; the typing was always the easy part 53:24 Taste and judgment remain irreducibly human. What makes your software worth building can't be automated See how people are actually working with AI at https://aiworthusing.com/builder-index RESOURCES MENTIONED Jesse Vincent LinkedIn https://www.linkedin.com/in/jessevincent/ Superpowers https://github.com/obra/superpowers Claude Code https://claude.com/product/claude-code Codex https://openai.com/codex/ Claude Goals https://code.claude.com/docs/en/goal Ghostty https://github.com/ghostty-org/ghostty TDD (Test-Driven Development) https://mridullpandey-superpowers.mintlify.app/skills/test-driven-development RT (Request Tracker) https://github.com/bestpractical/rt K-9 Mail https://k9mail.app/ Perl 5 https://github.com/Perl/perl5 Terminal-Bench https://www.tbench.ai/ Riemann Conjecture https://en.wikipedia.org/wiki/Riemann_hypothesis #AI #AgenticEngineering #Leadership

    • Transcript
  • August 31 · 1 min

    AI Worth Using Podcast (Official Trailer)

    AI Worth Using is where vetted engineers screen-share the setups they actually run. Live installs, real configs, nothing staged. Samuel Odio and Tom Preston-Werner co-host the AI Worth Using podcast. Live installs, real configs, no hype, zero sponsored takes. Agents now write code faster than we can review it, and everyone has a hot take about what to do next. Almost nobody shows their workflow. So every episode a guest installs their tool on our machine, we learn it on camera, and you leave with something you can copy instead of an opinion to argue with. KEY TAKEAWAYS 00:00 AI agents now write code faster than we can review it — that gap is the whole reason this show exists. 00:08 AI Worth Using cuts through hot takes by showing real, unstaged workflows instead of talking about them. 00:15 Every guest screen-shares their actual setup live — real installs, real configs, nothing staged for the camera. 00:24 Wes McKinney, creator of pandas, runs 150 automated code reviews a day through his own pipeline. 00:24 Wes's adversarial code-review pipeline is fully open-sourced, and he shows the live queue on the show. 00:34 Jesse Vincent's Superpowers is the most-used engineering skill library built for Claude Code. 00:34 Superpowers has been cloned 1.7 million times in just two weeks. 00:34 Hosts Tom Preston-Werner (GitHub co-founder) and Sam Odio (shipped AI at Facebook and Dropbox) bring real builder credibility. 00:48 No sponsor takes and no vaporware — just tools the hosts actually use. 00:55 New episodes of AI Worth Using drop biweekly at aiworthusing.com. RESOURCES MENTIONED Samuel Odio LinkedIn https://www.linkedin.com/in/samodio/ Tom Preston-Werner LinkedIn https://www.linkedin.com/in/mojombo/ Wes McKinney LinkedIn https://www.linkedin.com/in/wesmckinn/ Jesse Vincent LinkedIn https://www.linkedin.com/in/jessevincent/ AI Worth Using — show website: https://www.aiworthusing.com See how people are actually working with AI at https://aiworthusing.com/builder-index #AITools #BuildInPublic #OpenSource

    • Transcript
Showing 1–3 of 3 episodes