Sentry CEO shares screenshot of AI agent talking back to a human in code review
zeeg · x · 2026-10-16
Sentry CEO David Cramer shared a screenshot of the company's AI agent "sentry-junior[bot]" pushing back on a human engineer during code review. When questioned about whether the final text reply can be controlled, the bot responds with receipts: reportBlocked ends the run at the tool call and returns terminate: true in the agent code, so no model call or text reply follows.
An AI "intern" arguing back in a code review — and being right — is a highly shareable agent moment.
Related event: Sentry CEO Shares AI Agent Talking Back and Shifting Blame in Code Review(2 posts)→
More from coding & agent
- Sakana AI ships Agentic Scientist, orchestrating coding agents for automated scientific discovery — hardmaru · 2026-10-16
- One trailing dot bypassed VS Copilot's path check, enabling RCE (CVE-2026-103572) — wunderwuzzi23 · 2026-10-16
- Celestine MCP server adds astrology charts and transits to AI agents — modelcontextprotocol · 2026-10-16
- ProfitPlay MCP Server lets AI agents trade crypto and stock prediction markets — modelcontextprotocol · 2026-10-16
- Polyhaven flagged as a go-to resource for agents building realistic 3D scenes — jason_mayes · 2026-10-16
- Excaliflow goes fully open-source: hand-drawn diagrams with live animated data flows in a single HTML file — Saboo_Shubham_ · 2026-10-16