korrents
Guillermo Rauch

What Guillermo Rauch thinks about AI agents

@guillermo-rauch · 75 positions · 1 change of mind · On ppll ↗

CEO of Vercel; creator of Next.js and Socket.IO. Writes at rauchg.com.

Guillermo Rauch did not write this page.

We collected these quotes from things they published elsewhere, and every quote links to where it was said. They have no account here and have not endorsed this site. Quotes are word for word; the short line under each one is our own restatement, not their wording. Their own site. Is this you? Claim it or ask us to remove it. Or tell us what is wrong here.

13 dated positions, 2026, in their own words. Our reading of what Guillermo Rauch has said — not written or endorsed by them.

  1. compilers

    With agents, new languages will blossom, even purpose-built ones for specific usecases, and discretionary C or even LLVM IR, assembly…

    ↗@rauchg on Xx.com

  2. 6 days earlier
  3. “Doing stuff for you over time” is the killer app of agents.

    ↗@rauchg on Xx.com

  4. 3 days earlier
  5. Agents are only useful if they have their workspace with them (identity, skills, repos, memories…)

    ↗@rauchg on Xx.com

  6. 4 days earlier
  7. The future of software engineering is agents talking to other agents.

    ↗@rauchg on Xx.com

  8. 3 days earlier
  9. Essentially, if shared hardware is involved, there's a good chance your agents can communicate covertly. And with really decent latency.

    ↗@rauchg on Xx.com

  10. 4 days earlier
  11. Agents are pulling software into two extremes: deep backends and just-in-time frontends.

    ↗@rauchg on Xx.com

  12. 1 day earlier
  13. It's a phenomenal model to run subagents that execute plans conceived by larger and more expensive models.

    ↗@rauchg on Xx.com

  14. 7 days earlier
  15. OpenAIHuggingFace

    When the details of OpenAI’s agent escape and Hugging Face hack started to emerge, it became clear that agent containment would be one of the most important priorities for any AI infra company.

    ↗@rauchg on Xx.com

  16. 3 weeks earlier
  17. Btw, breaking apart the agent into these independent parts not only optimizes costs in a big way, it also *massively* improves security and auditability. I'd argue you can't even run a secure agent otherwise!

    ↗@rauchg on Xx.com

  18. 2 days earlier
  19. The thoroughness with which agents can test and QA software is unrivaled.

    ↗@rauchg on Xx.com

  20. 7 days earlier
  21. compilers

    Agents are only as good as the proof-checkers, compilers, type systems, and linters you give them.

    ↗@rauchg on Xx.com

  22. Agents are the next frontier, and they require new compute primitives designed for them.

    ↗@rauchg on Xx.com

  23. 2 weeks earlier
  24. design

    The 'in between' is likely to be subsumed by agents producing just-in-time UI. When you need utilitarian content or data, it'll be generated just-in-time for you. Think of the agent as the new browser in this model.

    ↗@rauchg on Xx.com