How do you talk to AI Agents?
summary
Claims the main limiter for coding agents is requirements clarity bottleneck and argues for AI that turns vague specs into executable tasks for code-generating agents. Proposes concrete tooling for PMs and engineering managers to produce formalized task definitions, then delegates those tasks to coding agents, a workflow labeled AI-assisted task authoring. Suggests this reduces friction in early launches and enables smaller teams to coordinate multiple agents, though evidence and metrics remain preliminary.
AI-written summary · about
related talks
01h 02m10 Tips To Level Up Your AI-Assisted Coding
36mHow to Get AI to Stop Being Weird and Actually Be Useful
13mMeet the Speakers
30mUsing AI to Create Better Requirements and Designs
27mAgentic Engineering: Working With AI, Not Just Using It
27mEngineering in the Age of AI: Making AI Work for Us, Not Replace Us
26mAI Agents as Your Co-Developer
24mMixing AI Coding in IDEs, CLIs, and Cloud