Inside Google DeepMind's DevX team: benchmarks, agent harnesses and day-0 integrations
osanseviero · x · 2026-11-20
Osanseviero (ex-Hugging Face, now at Google DeepMind) describes how the DevX team there goes far beyond a traditional DevRel function:
- Works directly with research: building benchmarks, giving capability feedback (agentic behaviors, Gemma design), and teamfooding models early
- Leads collaborations across agentic harnesses (OpenCode, OpenClaw, Hermes, ...) and 3P SDKs for day-0 readiness
- Drives GTM for model and tool launches: day-0 integrations, dev guides, demos, and developer-grounded messaging
- Designs APIs, ships skills/docs, and builds automations
On top of hundreds of events, high-quality content, and educational initiatives. He calls it a cracked team of engineers with strong product taste and developer empathy.
More from coding & agent
- Claude Code wrote my affiliate app — a security audit found 4 real holes — ItsYashKapoor · 2026-11-20
- Microsoft Graph MCP Server lets agents manage M365 users, licenses, and groups — modelcontextprotocol · 2026-11-20
- Sbir MCP connector wraps the free, no-auth SBIR.gov public API — modelcontextprotocol · 2026-11-20
- Demo shows controlling AI coding agents hands-free from smart glasses via open protocol — Scobleizer · 2026-11-20
- 109 AI agent conversations build a 75.9M-voxel eclipse village in a single HTML file — CurieuxExplorer · 2026-11-20
- What 1.5 Years of Building Agents Taught Me: It's All a While Loop, Tools, and Specs — khant_dev · 2026-11-20