Seroter's daily reading list #848: AI code review and zero-trust agent practices
rseroter · x · 2026-08-19
Richard Seroter's daily reading list (#848) rounds up several AI engineering pieces:
- Data on AI usage patterns in software teams — which roles and levels use AI regularly, and what hasn't changed
- Best practices for AI code reviews from a team that's made them work
- Building zero-trust AI agents with Google's Agent Development Kit: if AI generates your agents, explicitly feed this guidance in
- A better approach to generative UI — don't just render HTML/JS from an LLM; the piece effectively argues for A2UI
- A complete code-example guide to Google ADK 2 Graph Workflows: deterministic steps with flexible patterns
- Plus: where personal context should live, planning a Italy trip with an agentic workflow, and what happens when the hard part stops being hard
More from coding & agent
- Help: Adding Video LoRAs to LTX 2.3 for fight scene animations — SayethTwat · 2026-08-19
- AI made writing code nearly free; knowing where to swing the hammer still takes experience — _jaydeepkarale · 2026-08-19
- Hands-on: Gemini 3.7 Flash is crazy fast in reasoning mode but loses track in engineering — haider1 · 2026-08-19
- Claude Code creator releases 28-min breakdown: persistent context and parallel session workflows — goyalshaliniuk · 2026-08-19
- Aithy local agent runtime tests show strong coding performance from Qwen 2.5 4B — dosco · 2026-08-19
- AI code reviewers have a blind spot: clean code can still break UX — _jaydeepkarale · 2026-08-19