At a glance
WHAT IT’S REALLY ABOUT
Conductor orchestrates multiple coding agents, reshaping how engineers ship code
- Conductor is a Mac app that spins up isolated codebase copies so multiple AI coding agents can work in parallel, with humans reviewing and merging results.
- The company has grown ~10× since January, attracting users from indie hackers to engineers at large public companies, and just raised a $22M Series A co-led by Spark and Matrix.
- Conductor Cloud extends the product from local-only execution to persistent cloud workspaces so agents keep running even when the laptop is closed.
- The founders describe a YC journey of rapid prototyping and multiple pivots until focusing on dev tools they personally needed, discovering that orchestration and UX were the real bottlenecks.
- They predict engineering will move toward “CEO-like” management of many long-running AI workers, demanding new abstractions for agent oversight, review, and slop containment beyond today’s PR workflow.
IDEAS WORTH REMEMBERING
5 ideasParallel agents are productive, but human cognition becomes the constraint.
They find most people can effectively track only ~3–5 agents at once; scaling beyond that is primarily an interface/abstraction problem, not just a compute problem.
Persistence changes the usefulness of agent workflows.
Conductor Cloud keeps agents running in cloud workspaces even when the laptop is closed, removing a practical stop/start limitation of local-only agents and enabling longer tasks.
The winning product emerged from building internal tooling, not brainstorming.
After many YC experiments, they narrowed to dev tools and built what they personally needed; Conductor was discovered while building Chorus and the tooling to build it faster.
“Skills files” are becoming a competitive advantage for AI-assisted teams.
Top engineers encode codebase- and framework-specific best practices (e.g., React conventions) into markdown so agents repeatedly apply consistent standards instead of relearning or drifting.
Great AI builders borrow practices from managing great humans.
They argue the best pre-AI engineers tend to remain best in the AI era because success relies on clear constraints, proactive design thinking, and effective delegation/oversight.
WORDS WORTH SAVING
5 quotesSo Conductor is a Mac app that lets you run a bunch of coding agents all at the same time.
— Charlie
Um, but as of today, you can create a workspace that is backed by a cloud environment. So you can shut your laptop and the agent will keep working for you.
— Charlie
I remember, uh, like reading Hacker News at my first job out of college and reading, uh, You Weren't Meant to Have a Boss. And b- and being like, "Yeah, I wasn't meant to have a boss."
— Charlie
I think we have a, a nice dynamic where there's, like, two archetypes of engineers. I, I think of myself as a hacker, where I can make something really... Like, I, I like moving really fast, and I can make something that's sort of, like, duct-taped together and, like, leaves a trail of dust behind it. Uh, and then Jackson I've, is, I, I, I think of as, like, a gardener, where he will kind of, like, pick up the broken pieces behind me and then, like, build it into something, um, like some- something robust.
— Charlie
Put up a poster on your wall of your guys' faces, and then just say across it at the top, "Make something these guys want." And just build something that you guys want.
— Charlie
High quality AI-generated summary created from speaker-labeled transcript.
Get more out of YouTube videos.
High quality summaries for YouTube videos. Accurate transcripts to search & find moments. Powered by ChatGPT & Claude AI.
Add to Chrome