@timoreilly: I'm really looking forward to my conversation with my old friend Jesse Vincent tomorrow. We'll talk about Superpowers a…
Summary
Tim O’Reilly will host a live conversation with Jesse Vincent to discuss the 'Superpowers' agentic development methodology, its evolution, and its impact on AI-assisted development.
View Cached Full Text
Cached at: 09/15/26, 11:48 PM
I’m really looking forward to my conversation with my old friend Jesse Vincent tomorrow. We’ll talk about Superpowers and where Jesse has gone since then, why he has written a therapist for AI agents, and why it’s better to treat agents as colleagues than as assistants.
Give Your Agents Superpowers: Jesse Vincent Live with Tim O’Reilly
Source: https://www.oreilly.com/live-events/give-your-agents-superpowers-jesse-vincent-live-with-tim-oreilly/0642572444747/ View all eventsPublished byO’Reilly Media, Inc.
Intermediate content levelIntermediate
Tools and workflows for a world where people think and agents do
ScheduleJesse Vincent has been building tools that help people do their best work for 30 years. You’ve probably heard of at least one of his projects, maybeRequest Tracker(still running bug trackers around the world since 1996),K-9 Mail(now Thunderbird for Android), or his and Kaia Dekker’sKeyboardioergonomic mechanical keyboards. Last year Jesse launched something a little different, drawn from his experience using AI coding assistants: an open source agentic development methodology he callsSuperpowers.
Built on top of a set of composable skills, along with some instructions that make sure your agent actually uses them, Superpowers plugs into the world’s most widely used coding agents and teaches them exactly how Jesse works. It’s just the kind of pattern Tim O’Reilly has argued will shape the future AI + human knowledge economy. As Tim explainedback in March, “If a Skill is like handing a colleague a detailed playbook for a particular job, a Superpower is more like the professional habits and instincts that make someone effective at everything they do. Superpowers are meta-skills. They don’t tell the agent what to do. They shape how it thinks about what to do.” No surprise that it’s become one of the most widely adopted open source projects in AI-assisted development, with more than half a million installs, and ranks among the 50 most-starred public repositories on GitHub. As Jesse pointed out in his announcement post, “Superpowers are for everybody.”
Tim invited Jesse to share Superpowers’ origin story and talk about how the project has evolved alongside the capabilities of frontier models. (It’s currently on version 6, which you can read about on Jesse’s blog,Massively Parallel Procrastination.) They’ll get into how a personal CLAUDE.md file and a handful of prompts turned into a full development methodology used by hundreds of thousands of engineers, what Jesse had to get right about brainstorming, planning, and test-driven development before an agent could follow the process without him in the room, and why “writing skills” became one of the first skills Superpowers ever taught itself. They’ll also chat about the next rung in the hierarchy of skills, the work Jesse’s doing with Simon Willison, Drew Ritter, and Eden Kettleson over at his AI research labPrime Radiant, and what it means for the software industry when a Superpowered novice can independently tap into Jesse’s 30 years of experience rather than slowly gleaning that knowledge by putting in the time alongside someone like Jesse.
Save your spot to join in the conversation and share your questions and comments.
Schedule
The time frames are only estimates and may vary according to how the class is progressing.
Wednesday, September 16, 2026, at 9:00am PT / 12:00pm ET
- Interactive discussion and Q&A (60 minutes)
Tim O’Reillyis the founder and CEO of O’Reilly Media, Inc. His original business plan was simply “interesting work for interesting people,” and that’s worked out pretty well. He publishes books, runs online conferences, invests in early-stage startups, urges companies to create more value than they capture, and tries to change the world by spreading and amplifying the knowledge of innovators. He’s perhaps best known for his role in shaping big ideas like open source software, unconferences (Foo Camp), Web 2.0, and government as a platform. His 2017 bookWTF? What’s the Future and Why It’s Up to Usexplored the role of human agency in shaping the future in the face of the coming AI wave. These days, he’s focused on mechanism design for the human-AI economy. Mechanism design is sometimes described as “reverse game theory”, whereby you start with the outcome you want and then figure out what rules of the game will produce that outcome. He explores these ideas at the non-profit AI Disclosures Project, which he co-founded with Ilan Strauss. He writes frequently on Substack at theO’Reilly Radar, the AI Disclosures Project’sAsimov’s Addendum, and his own Conversations with AI.
Jesse Vincent is the founder of Prime Radiant, an AI research lab, and the creator of Superpowers, a popular open source agentic software development framework. He hasn’t written a line of code since October 2025. In past lives, Jesse cofounded Keyboardio, where he designed award-winning ergonomic mechanical keyboards. He led VaccinateCA during the height of the COVID-19 pandemic, created the open source issue tracking system Request Tracker, created K-9 Mail for Android, and served as the project leader for the Perl programming language.
Skill covered
Innovation
Similar Articles
@timoreilly: About to go live with @mlpowered to talk about the "neuroscience of AI." https://learning.oreilly.com/live-events/crack…
Tim O’Reilly and Emmanuel Ameisen discuss AI interpretability, focusing on world models in LLMs like Claude and Anthropic's tools for steering model behavior.
@timoreilly: I've really been impressed with the framework for enterprise AI adoption and compounding value that Dan Guido talked ab…
Tim O'Reilly praises Dan Guido's framework for enterprise AI adoption from Trail of Bits, and announces a free live Q&A event on the O'Reilly platform.
@mattpocockuk: In just over an hour, I'll be live with @unclebobmartin We'll be figuring out if software fundamentals still matter in …
Robert C. Martin discusses his career, the impact of 'Clean Code', and his approach to using AI agents with constraint tools like static analysis and mutation testing to enhance software development.
@kentcdodds: This is happening tomorrow! https://luma.com/mega-its-time?tk=z80Od9… This is so packed with value you'll wonder why it…
This article announces a live event titled 'It's Time: The Work Changed' by MEGA.dev, featuring discussions on AI agents in software development with expert speakers and a Q&A session.
@timoreilly: Takeaways from last week's Live with Tim conversation with Anthropic interpretability researcher Emmanuel Ameisen. http…
This article summarizes a live conversation with Anthropic interpretability researcher Emmanuel Ameisen, discussing how large language models develop complex world models through next-token prediction and the implications for understanding human cognition.