Seroter's Daily Reading: Levels of Agentic Engineering and Git's Future in the AI Era
rseroter · x · 2026-11-18
Google engineer Richard Seroter's reading list #911 rounds up notable posts on agent engineering and developer tooling:
- The levels of agentic engineering: a maturation framework from someone who's led the climb twice; Seroter thinks picking the right work should come earlier in the model
- Accelerating development for massive Git repos: built for Android's giant repo and open sourced
- Put MCP next to your API, not on top of it: sensible if it avoids duplicating code and governance like access controls
- 10 best AI agent frameworks in 2026: the list is stabilizing; he wonders whether people will still build custom agents versus throwing skills at managed ones
- "AI slop is A-OK": nobody becomes an expert overnight; let people work through the journey with AI without shame
- Gemini 4 Hydrogen: a faster model for general-purpose robotics, turning Google Antigravity into a full-featured robotics workbench
Also covers ephemeral disks on Cloud Run and Google's showing in the 2026 Gartner Magic Quadrant for cloud operational databases.
More from coding & agent
- Stitch launches AI agents natively in its banking OS, under bank permissions — CurieuxExplorer · 2026-11-18
- Microsoft Ignite LAB663: a hands-on loop for improving agents with Copilot traces and Model Router — lee_stott · 2026-11-18
- "The model has no idea what its own biases are": designers on AI slop — petergyang · 2026-11-18
- Agent tweak is 15% faster at nearly same cost — the model admitted it overweighted raw token counts — dosco · 2026-11-18
- Aware browser bets on feeds, not chat, as the right interface for AI agents — HaijunXia · 2026-11-18
- Ramen 1.0: open-source governed MCP platform with SSO, per-tool guardrails, and eval-gated deploys — Ok_Plum3595 · 2026-11-18