← All implementations

Y Combinator · Platform

Internal agent infrastructure

Y Combinator built its own agent harness and infrastructure, led by partner Pete Koomen. It is an agent loop over a shared tool registry, now over 350 tools, including one that runs read-only SQL against YC's single Postgres database. Agent conversations are broadcast to a Slack channel.

1

Supporting infrastructure

This entry describes supporting infrastructure that other work builds on. The catalog classifies it as a platform. The record reports no execution workflow.

Approach type
Platform
Work
Coding, Ops
Human involvement
Human in loop
Deployment stage
Deployed
Evidence strength
Detailed primary
Entry reviewed

Where people stay involved

The catalog records no execution workflow for this entry, so the scopes below describe access to the system rather than work it completes on its own.

  • internal request → agent-assisted organizational workUnknown · Level unknown

Unclassified for internal request → agent-assisted organizational work; human attention boundary: unknown.

1

Observation date
2026

Implementation details

Sandbox

unknown

1

Harness

Own harnesses built from the ground up for internal AI use

1

Reported results and limitations

The catalog records what the sources report, with the scope and the denominator of every figure. A qualification below limits the figure it sits under.

Lessons and interpretation

Don't add AI as a feature; make it the operating system the whole organization runs on

1

Build the harness and surrounding infra in-house rather than bolting onto a hosted agent

1

Sources and research details

Citations link to the original publisher. Each source also keeps a preserved copy in the repository, so a changed or removed page stays checkable.

  1. Inside YC's AI Playbook (Lightcone podcast, with Pete Koomen)https://www.ycombinator.com/library/Qh-inside-yc-s-ai-playbookPodcast · First party · Last source verification: 2026-08-31
Research details for every claim on this page
  1. Summary
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    Low
    Confidence reason
    Only limited public evidence supports this claim.
  2. Sandbox
    Statement type
    Inference
    Provenance
    Catalog judgment
    Confidence
    Medium
    Confidence reason
    The preserved sources do not document an execution sandbox; unknown does not mean absent.
  3. Harness
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    Low
    Confidence reason
    Only limited public evidence supports this claim.
  4. Lesson
    Statement type
    Inference
    Provenance
    Catalog judgment
    Confidence
    Low
    Confidence reason
    Only limited public evidence supports this claim.
  5. Lesson
    Statement type
    Inference
    Provenance
    Catalog judgment
    Confidence
    Low
    Confidence reason
    Only limited public evidence supports this claim.
  6. Operating model assessment
    Statement type
    Inference
    Provenance
    Catalog judgment
    Confidence
    Unverified
    Confidence reason
    The source describes internal agent infrastructure but not a sufficiently specific human attention boundary.
    Observation date
    2026

The catalog records no related implementation for this entry yet.