We just launched Paxel!
Paxel is a newly launched tool that analyzes Claude and Cursor coding sessions locally to generate a personalized 'builder profile' across five dimensions. It runs in Docker, keeps code private, and is free to use. Y Combinator is also integrating Paxel tokens into their Startup School application process.
Summary
The transcript introduces Paxel, a tool designed to help developers understand how they build software using AI coding agents. The speaker opens by noting that while everyone is now writing software with AI, the practice is largely uncharted — people are figuring out best practices in isolation without visibility into their own patterns or those of others.
Paxel addresses this by reading a user's Claude and Cursor sessions to surface behavioral insights: whether someone is an architect who plans before building, a late-night shipper, how many agents they run in parallel, and what their go-to prompts are. The tool generates a 'builder profile' across five dimensions — steering, execution, engineering, product instinct, and planning — along with a 'growth edge' that suggests specific next steps based on actual session data.
A key feature highlighted is privacy: Paxel runs locally inside Docker via a single command, meaning code never leaves the user's machine. The profile is delivered to the user's inbox within 15–30 minutes and is free.
The speaker then reveals an integration with Y Combinator's Startup School: applicants can paste their Paxel token into their application to show how they build, not just what they've built. The speaker emphasizes this can only help, not hurt, an application, and encourages those who already applied to go back and add it.
The transcript closes with a broader philosophical point: historically, software development was an exclusive 'priesthood,' but AI has opened the doors. Paxel is framed as a discovery mechanism for identifying talented builders — 'cracked builders no resume would ever surface' — and as a collective experiment to define what great AI-assisted building looks like.
Key Insights
- The speaker argues that despite widespread AI-assisted coding, no one has yet defined what 'building well' with coding agents looks like — everyone is figuring it out independently and in the dark.
- Paxel generates a builder profile across five specific dimensions — steering, execution, engineering, product instinct, and planning — framing it explicitly as 'a mirror, not a grade.'
- The speaker claims Paxel runs entirely locally inside Docker, so the user's code never leaves their machine, positioning privacy as a core product feature rather than an afterthought.
- Y Combinator is accepting Paxel tokens as part of Startup School applications, with the speaker asserting it can only help — not hurt — an applicant's chances, and encouraging those who already applied to retroactively add it.
- The speaker frames Paxel as a talent discovery mechanism, arguing that traditional resumes cannot surface the best AI-era builders and that the tool is an experiment to collectively define what great AI-assisted building looks like.
Topics
Transcript
[0:00] Something strange is happening right now. Every one of us is writing software with AI, but we're doing it alone. No one really knows what it means to build well with coding agents just yet. We're all figuring it out in the dark. So, we built Paxel to turn the lights on. Paxel reads your clawed codecs and cursor sessions and shows you how you actually build. Are you the architect planning first? building scaffolding that compounds, or are you the night owl [0:31] shipping at 1:00 a.m.? Maybe both. It surfaces your go-to prompt, how many agents you run in parallel, and the moves that are uniquely yours. You get a builder profile across five dimensions: steering, execution,…
Full transcript available for MurmurCast members
Sign Up to AccessMore from Y Combinator
Susan Kare: How I Designed the Original Apple Mac Icons
Susan Kare discusses her pioneering work designing icons and fonts for the original Apple Macintosh, sharing design principles focused on simplicity and metaphor, along with advice from influential figures like Paul Rand that shaped her career in digital design.
Chelsea Finn: This is the State of the Art in Robotics
Chelsea Finn discusses advancements in physical intelligence, highlighting the development of general-purpose robots capable of performing various tasks autonomously. Key techniques include reinforcement learning, efficient data utilization, and the importance of memory in complex task execution.
Circleback CEO Ali Haghani: Recording Company Meetings Will Become The Norm
Ali Haghani discusses CircleBack, an AI note-taking tool designed to capture, organize, and automate meeting content. He shares insights on his hardware setup, unexpected uses of CircleBack, and the evolving landscape of software engineering as AI capabilities grow.
Why Robotics Still Isn't Solved - But Could Be Soon | YC Paper Club
YC Paper Club discusses why robotics remains unsolved despite repeated predictions of breakthrough years, presenting four fundamental challenges (physical modeling, deformable objects, sensorimotor feedback, embodiment drift) and showcasing recent advances in memory-augmented policies, embodied reasoning, sim-to-real learning, and world action models.
Max Hodak: What Really Kills Deep Tech Startups?
Max Hodak, CEO of Science (a retinal prosthesis company), explains that deep tech startup success is determined by infrastructure and iteration speed rather than technical brilliance. He emphasizes that proper systems for purchasing, recruiting, and performance management are as critical as the core technology, and shares specific processes Science uses to scale efficiently.