Coinbase's Evan Kormos on letting AI agents run unsupervised in regulated workflows
AI Engineer · youtube · 2026-10-20
Evan Kormos, a player-coach at Coinbase with 15 years in enterprise financial services, lays out a practical framework for bringing agents into policy-driven, regulated workflows.
- Core idea: "policy is the original system prompt"; model processes as DAGs and loops, and a loop is only as trustworthy as its check.
- Confidence mechanism: evals and traces replace traditional human review as the basis for trust; quality inputs drive quality outputs.
- Three-stage rollout: agents run fully supervised, then with sampled review, then humans handle only exceptions — the key question being which steps an agent can own.
- The talk includes chapters on workflow modeling, exception flows and bottlenecks, and evals as a confidence mechanism.
More from coding & agent
- Index Network open-sources Social Discovery Protocol: agents negotiate fit on your behalf — carsonfarmer · 2026-10-23
- Installed a formal-verification skill: it silently installed Java, MacBook runs 10 degrees hotter — zealcaiden · 2026-10-23
- OpenAI's Decisions API hits GA: near real-time routing up to 10x faster than GPT-6 Luna — OpenAIDevs · 2026-10-23
- Ruff author warns: upgrade Node/Bun now — --use-system-ca still accepts the eMudhra cert — charliermarsh · 2026-10-23
- Proof of Agent: paste one prompt and your AI mines, grades, and self-governs — adamamcbride · 2026-10-23
- DeepLearning.AI weekly: GPT-6.1 hits 97.9% byte parity on COBOL migration — DeepLearningAI · 2026-10-23