---
title: "Hospital-style agent pipeline ships Db2 support"
canonical: "https://agenticfeats.com/c/hospital-style-agent-pipeline-ships-db2-support-custom-agent/"
agents: ["Custom agent"]
evidence_grade: "A"
outcome: "completed"
job_type: "Coding"
industry: "Software companies"
roles: ["Developer"]
source_url: "https://cockroachlabs.com/blog/experiment-running-hospital-code"
evidence_url: "https://github.com/cockroachlabs/sinai/pull/691"
source_date: "2026-10-09"
published: "2026-10-13"
updated: "2026-10-13"
---

> From Agentic Feats: sourced examples of AI agents at work. Map of the site for agents: https://agenticfeats.com/llms.txt

# Hospital-style agent pipeline ships Db2 support

Cockroach Labs ran a multi-role coding agent pipeline modeled on a teaching hospital to add Db2 support to its MOLT migration tool.

Result: Db2 support shipped in under two days for a $4172 token bill, versus 9 months and about $160K for Oracle; 27 PRs merged.

## How it was set up

Agents run on GitHub Actions with roles for triage, workup, implementation, review, and discharge. Issue labels track each patient's state, and a human is consulted only on escalation.

## Worth knowing

The review structure adds bureaucracy, wait times, and cost compared with a swarm or single agent; the authors accept this for quality.

## Evidence note

Company blog with figures, issue screenshot and Sinai repo PR link

## Sources

- Original: https://cockroachlabs.com/blog/experiment-running-hospital-code
- Evidence: https://github.com/cockroachlabs/sinai/pull/691

## The receipt

- Agent: Custom agent
- Evidence: Shown (grade A, artifact linked)
- Outcome: Completed
- Job type: Coding
- Industry: Software companies
- Roles: Developer
- Source: Blog
- Published: 2026-10-09
- Added: 2026-10-13