Source: https://internal-agents.com/agents/ycombinator-agent-infra # Y Combinator — 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. > 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 - Deployment stage: Deployed - Autonomy: Human in loop - Evidence strength: Detailed primary - Status: Internal - First reported year: 2026 - Work: Coding, Ops - Invocation: Unknown - Entry reviewed: 2026-09-15 ## Where people stay involved - **internal request → agent-assisted organizational work** — Unknown · Level unknown ## Overview ### Summary 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. Fact · Reported · Low confidence · `ycombinator-agent-infra--summary` Confidence reason: Only limited public evidence supports this claim. Evidence: - Supports · [1] [Inside YC's AI Playbook (Lightcone podcast, with Pete Koomen)](https://www.ycombinator.com/library/Qh-inside-yc-s-ai-playbook) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/ycombinator-agent-infra-source-1/content.md) ## Supervision evidence ### Operating model assessment Unclassified for internal request → agent-assisted organizational work; human attention boundary: unknown. Inference · Catalog judgment · Unverified confidence · `ycombinator-agent-infra--operating-models-0` Confidence reason: The source describes internal agent infrastructure but not a sufficiently specific human attention boundary. Qualifications: - Observation date: 2026 Evidence: - Supports · [1] [Inside YC's AI Playbook (Lightcone podcast, with Pete Koomen)](https://www.ycombinator.com/library/Qh-inside-yc-s-ai-playbook) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/ycombinator-agent-infra-source-1/content.md) ## Implementation details ### Sandbox unknown Inference · Catalog judgment · Medium confidence · `ycombinator-agent-infra--architecture-sandbox` Confidence reason: The preserved sources do not document an execution sandbox; unknown does not mean absent. Evidence: - Supports · [1] [Inside YC's AI Playbook (Lightcone podcast, with Pete Koomen)](https://www.ycombinator.com/library/Qh-inside-yc-s-ai-playbook) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/ycombinator-agent-infra-source-1/content.md) ### Harness Own harnesses built from the ground up for internal AI use Fact · Reported · Low confidence · `ycombinator-agent-infra--architecture-harness` Confidence reason: Only limited public evidence supports this claim. Evidence: - Supports · [1] [Inside YC's AI Playbook (Lightcone podcast, with Pete Koomen)](https://www.ycombinator.com/library/Qh-inside-yc-s-ai-playbook) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/ycombinator-agent-infra-source-1/content.md) ## Lessons and interpretation ### Lesson Don't add AI as a feature; make it the operating system the whole organization runs on Inference · Catalog judgment · Low confidence · `ycombinator-agent-infra--lessons-learned-0` Confidence reason: Only limited public evidence supports this claim. Evidence: - Supports · [1] [Inside YC's AI Playbook (Lightcone podcast, with Pete Koomen)](https://www.ycombinator.com/library/Qh-inside-yc-s-ai-playbook) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/ycombinator-agent-infra-source-1/content.md) ### Lesson Build the harness and surrounding infra in-house rather than bolting onto a hosted agent Inference · Catalog judgment · Low confidence · `ycombinator-agent-infra--lessons-learned-1` Confidence reason: Only limited public evidence supports this claim. Evidence: - Supports · [1] [Inside YC's AI Playbook (Lightcone podcast, with Pete Koomen)](https://www.ycombinator.com/library/Qh-inside-yc-s-ai-playbook) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/ycombinator-agent-infra-source-1/content.md) ## Sources 1. [Inside YC's AI Playbook (Lightcone podcast, with Pete Koomen)](https://www.ycombinator.com/library/Qh-inside-yc-s-ai-playbook) - Podcast · First party · Evidence - Original URL: - Accessed: 2026-08-12 · Last verified: 2026-08-31 - Preserved copy in the repository: