Explore

Every resource founders actually use, in one library.

The essays, videos, podcasts, books and tools behind every answer across eChai's hubs, from starting up to go-to-market, D2C, founder money and AI, each with a note on why it is here.

What founders use most, ranked by how many answers lean on it.

  1. The thread version of the argument, with the mistakes he keeps seeing. x.com Thread · How Founders Use AI Walden Yan: principles for building agents Walden Yan
  2. The honest update: some multi-agent setups now work, most sexy ideas still don't. x.com Thread · How Founders Use AI Walden Yan: a year later, what changed Walden Yan
  3. The follow-up naming the specific multi-agent patterns that survived production. cognition.com Article · How Founders Use AI Multi-Agents: What's Actually Working Cognition
  4. The other side of the debate: a 90% performance gain, at 15x the tokens. anthropic.com Article · How Founders Use AI How we built our multi-agent research system Anthropic
  5. Anthropic's own decision rules for graduating beyond a single agent. claude.com Article · How Founders Use AI When to use multi-agent systems (and when not to) Anthropic
  6. Shows why Cognition and Anthropic are both right about different problems. philschmid.de Article · How Founders Use AI Single vs Multi-Agent System? Philipp Schmid (Google DeepMind)
  7. The architecture broken down with diagrams a non-researcher can follow. blog.bytebytego.com Article · How Founders Use AI How Anthropic Built a Multi-Agent Research System ByteByteGo
  8. 200+ analyzed tasks and 14 failure modes, the evidence behind the caution. arxiv.org Article · How Founders Use AI Why Do Multi-Agent LLM Systems Fail? UC Berkeley (MAST)
  9. The open dataset and annotator to diagnose your own multi-agent failures. github.com Tool · How Founders Use AI MAST: Multi-Agent System Failure Taxonomy UC Berkeley Sky Computing Lab
  10. The digestible summary of where multi-agent systems break. sky.cs.berkeley.edu Article · How Founders Use AI MAST project page UC Berkeley Sky Computing Lab
  11. A neutral recap of the whole debate if you want it in ten minutes. ctol.digital Article · How Founders Use AI AI Leaders Clash Over Agent Architecture CTOL Digital
  12. Frames the choice as a coordination-cost calculation, which is the right lens. cognilium.ai Article · How Founders Use AI Multi-Agent vs Single Agent: When It's Worth the Cost Cognilium
  13. Extracts the engineering lessons hiding inside Anthropic's post. llmmultiagents.com Article · How Founders Use AI The Art of Multi-Agent Collaboration: Reflections on Anthropic's Research System LLM Multi Agents
  14. Maps each MAST failure mode to a practical fix. futureagi.substack.com Article · How Founders Use AI Why do multi-agent LLM systems fail (and how to fix) Future AGI
  15. The paper's findings retold for people who won't read a paper. thegrigorian.medium.com Article · How Founders Use AI Why Do Multi-Agent LLM Systems Fail? (explainer) Anna Alexandra Grigoryan
  16. The case study written for someone deciding whether to copy the pattern. zenml.io Article · How Founders Use AI Anthropic's multi-agent research system (LLMOps case study) ZenML
  17. Where coding agents go next, from the person who built the category leader. lennysnewsletter.com Podcast · How Founders Use AI Head of Claude Code: What happens after coding is solved | Boris Cherny Lenny's Podcast (Boris Cherny)
  18. The engineering story, including the 80-90% self-written stat. open.spotify.com Podcast · How Founders Use AI Building Claude Code with Boris Cherny The Pragmatic Engineer (Gergely Orosz)
  19. YC's founder-angle interview: what agentic coding means for startups. ycombinator.com Video · How Founders Use AI Inside Claude Code with its creator Boris Cherny Y Combinator
  20. A CEO describing non-technical teammates shipping via the terminal. x.com Thread · How Founders Use AI Dan Shipper: Claude Code cracked something open for us Dan Shipper
  21. The clearest head-to-head, including advice for non-technical founders. builder.io Article · How Founders Use AI Claude Code vs Cursor: What to Choose Builder.io
  22. Covers the other big coding agent so you compare all three. builder.io Article · How Founders Use AI Codex vs Claude Code: which is the better AI coding agent? Builder.io
  23. A long-term usage report rather than a launch-week hot take. thenewstack.io Article · How Founders Use AI Claude Code vs. Cursor vs. Codex vs. Antigravity, six months in The New Stack
  24. The intermediate techniques that separate toy use from real product work. softcery.com Guide · How Founders Use AI Agentic Coding with Claude Code and Cursor: Skills, Subagents, Hooks, MCP Softcery

Show the next 24

The hubs

Starting Up Find an idea, validate it, build, and land your first customers. 1046 questions GTM Go-to-market, from breaking in to how the best teams do it. 352 questions D2C Building a direct-to-consumer brand, India-first. 482 questions Wealth Paying yourself, ESOPs, secondaries, and de-risking founder wealth. 154 questions How Founders Use AI How founders actually put AI to work, mapped topic by topic. 278 questions Glossary Plain-language definitions of the startup and VC terms you'll hit. 390 terms
eChai Partner Brands The partnership →