Restoring Trust in AI-Native Development
summary
Claims a path from prompt-to-production that pairs agent generation with automated verification using Executable Intent, Executable Architecture, Executable Specifications and Continuous Governance plus Harness Engineering. Uses OpenAPI/AsyncAPI, Arazzo for orchestration, contract tests, mocks, CI gates, language servers and MCPs to run closed-loop tests and drift detection. Prototypes spin up mock architectures and auto-generate tests; goal is one human managing ~100 agents like looms, but the system is a work-in-progress not yet fully solved.
AI-written summary · about
chapters (15)
- 0:00Autonomous agents in development
- 2:28APIs as modular building blocks
- 4:53Compiler safety in microservices
- 6:23Toll booths in pipelines
- 9:10Textile power loom lessons
- 13:30Jidoka for autonomous systems
- 15:45Poka-Yoke in API design
- 17:48Andon for issue visibility
- 20:02Harness engineering for agents
- 25:26Harness limits in architecture
- 26:38Executable intent specifications
- 27:51Executable architecture patterns
- 29:53Continuous governance control
- 31:50Closed-loop trust for agents
- 33:01Q&A
related talks
14mThe 4 Patterns of AI Native Development
29mBuilding Trust in AI Agents
30mArchitecting Integrity: Responsible Software Evolution in the AI Era
26mBuilding Agentic Workflows: Patterns for Orchestrating Intelligent Systems.
29mPairing with the machine: How AI Agents are rewriting the rules of software development
41mGoing beyond copilot with AI Agents
16mCloud-Native Intent Orchestration for Enterprise AI Ecosystems
26mAI Agents as Your Co-Developer