Day 1 Recap: What Practitioners Learned
summary
Day 1 surfaces practical fixes: codified engineering standards that restore trust in AI review, dev boxes in VPCs for isolated agent environments, runtime/kernel controls for taming rogue agents, and a warning that overconstraining skills breaks agents. Concrete outcomes include 93% of PRs co‑authored with Ona and an auto-merge label that requires a human button press, plus rules like database changes or >1,000-line edits forcing human review. Expect living architecture files or knowledge graphs and agents that self‑document nightly to enable safe automation.
AI-written summary · about
chapters (6)
- 0:00Day one recap intro
- 1:11Agentic workflow optimizations
- 5:06Self-improving agents
- 7:54Agent dev environments
- 10:02Security in autonomous agents
- 13:53Day two preview
related talks
05mSponsored Keynote: When AI Agents Trash Your Golden Path... And How to Take Back Control! -Will McMullen, Ona
07h 57mAI Agents Conference 2026 - Day 4
30mArchitecting Integrity: Responsible Software Evolution in the AI Era
29mBuilding Trust in AI Agents
08mBuilding an AI Platform Your Engineers Actually Trust
50mPanel: Beyond The Vibe: Code Quality First
30mBuilding Tools with Tools: Modern AI-Driven Development
40mHow To Tame Your Agents?