Internal operations agent

YC’s internal agent helps employees answer questions and carry out operational work using shared company tools.

Company: Y Combinator
Approach type: Agent
Work: Ops, Finance ops
Human involvement: Unknown
Invocation: Interactive
Deployment stage: Deployed
Evidence strength: Detailed primary
Entry reviewed: 2026-09-17

Copy as MD Ask ChatGPT

How it works

employee request → answer or operational tool action.

Read company context

The agent can read model files and run read-only SQL over YC’s database.^{[Source 1]}

Use operational tools

The shared registry supports finance journal entries, office-hour management and events.^{[Source 1]}

Where people stay involved

People review, approve, or guide the agent’s work here.

Not reported: The source does not establish the required human review boundary.

Supervision level
Not classified
- employee request → answer or operational tool action^{[Source 1]}

How supervision levels work

Implementation details

Model: Not reported
Harness: YC’s internal agent loop and shared tool registry.^{[Source 1]}
Sandbox: Not reported
Tool access: Read-only SQL and separate operational tools; SQL access does not imply every tool is read-only.^{[Source 1]}
Knowledge: Company database and application model files.^{[Source 1]}
Context management: Not reported
Credentials: Not reported
Interfaces: Not reported

Validation and failure handling

Not reported: The available sources do not describe how the team checks the output.

Reported observations

Not reported

Lessons

Not reported: The available sources do not report lessons from this work.

Back to agents

Improve this record

Give your coding agent the context and instructions to prepare a source-backed update.

Suggest on GitHub

Paste the prompt into your coding agent, then describe the correction or add a public source.

Preview prompt

Help me update the Internal Agents Map record for Internal operations agent at Y Combinator.

Repository: https://github.com/steel-experiments/internal-agents-map
Record: data/agents/ycombinator-operations.yaml
Published record: https://internal-agents.com/agents/ycombinator-operations
Readable context: https://internal-agents.com/agents/ycombinator-operations.md

Use the correction or public source I provide in this conversation. If I have not supplied either, ask what I want changed before editing.

Use an existing checkout of this repository, or clone it if needed. Read the current record from the repository. Follow AGENTS.md, CONTRIBUTING.md, and the relevant instructions in data/schema.md.

Verify that the evidence supports the requested change. Preserve uncertainty and distinguish reported facts from catalog judgments. Follow the repository process for capturing new sources. If evidence is insufficient, explain the gap instead of inventing details.

Make a focused change on a branch. Regenerate derived files and run the required checks. Do not edit generated content by hand.

Show me the change, supporting evidence, and check results, including any checks you could not run. Ask whether to submit a pull request unless I already requested one. Do not merge the pull request. If you cannot edit the repository, prepare a source-backed issue draft.

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.

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
Preserved copy

Question coverage and scope

purpose: Reported
workflow: Reported
human involvement: Not reported: The source does not establish the required human review boundary.
implementation: Reported
validation: Not reported
observations: Not reported
lessons: Not reported

Research details for every claim on this page

Summary
Statement type
Fact
Provenance
Reported
Confidence
Not assessed
Confidence reason
No explicit confidence assessment is recorded for this claim.
- SupportsInside YC's AI Playbook (Lightcone podcast, with Pete Koomen)Transcript: finance origins; two database tools; shared registry and team operations
Harness
Statement type
Fact
Provenance
Reported
Confidence
Not assessed
Confidence reason
No explicit confidence assessment is recorded for this claim.
- SupportsInside YC's AI Playbook (Lightcone podcast, with Pete Koomen)Transcript: finance origins; two database tools; shared registry and team operations
Knowledge
Statement type
Fact
Provenance
Reported
Confidence
Not assessed
Confidence reason
No explicit confidence assessment is recorded for this claim.
- SupportsInside YC's AI Playbook (Lightcone podcast, with Pete Koomen)Transcript: finance origins; two database tools; shared registry and team operations
Tool access
Statement type
Fact
Provenance
Reported
Confidence
Not assessed
Confidence reason
No explicit confidence assessment is recorded for this claim.
- SupportsInside YC's AI Playbook (Lightcone podcast, with Pete Koomen)Transcript: finance origins; two database tools; shared registry and team operations
Read company context
Statement type
Fact
Provenance
Reported
Confidence
Not assessed
Confidence reason
No explicit confidence assessment is recorded for this claim.
- SupportsInside YC's AI Playbook (Lightcone podcast, with Pete Koomen)Transcript: finance origins; two database tools; shared registry and team operations
Use operational tools
Statement type
Fact
Provenance
Reported
Confidence
Not assessed
Confidence reason
No explicit confidence assessment is recorded for this claim.
- SupportsInside YC's AI Playbook (Lightcone podcast, with Pete Koomen)Transcript: finance origins; two database tools; shared registry and team operations
Operating model assessment
Statement type
Inference
Provenance
Catalog judgment
Confidence
Unverified
Confidence reason
The source describes Internal operations agent and its work, but does not establish whether a person must approve or inspect each successful output.
Observation date
2026
- SupportsInside YC's AI Playbook (Lightcone podcast, with Pete Koomen)Transcript: finance origins; two database tools; shared registry and team operations