Patterns for Productive Agent-Assisted Programming
summary
Claims a repeatable four-step workflow—plan your changes, write tests first, let the agent build, document what you created—and shows it on a real repo using Cursor, Olama on Modal, FastAPI and HTTPX. Demonstrates a router that maps exact model names to GPUs (H100 vs A10G), a shared model volume, automated linting and a prewritten test harness; the agent scaffolds code and runs tests but hits container startup/logging issues during the live demo, illustrating what worked and what still needs human debugging.
AI-written summary · about
chapters (5)
- 0:00Agent-assisted programming patterns
- 4:23Live coding setup
- 12:57Iterating with agent
- 22:40GPU routing router
- 34:16Final patterns & Q&A
related talks
39mAgents for the Sake of Happiness
41mGoing beyond copilot with AI Agents
40mHow To Tame Your Agents?
01h 24mBuilding your own software factory
25mThe Ai-Assisted Developer Workflow: Build Faster and Smarter Today
48mAI Coding Agents and how to code them
27mAgentic Coding with Discipline & Skill: Practical Techniques and Tips
59mFrom Pair to Peer Programmer