AI Product Engineering
Block 3: Agents, Evaluation & Deployment
Responds to one message → waits
You direct every step
Pursues a goal across multiple steps
Decides what to do next based on results
The difference is autonomy: the agent sequences its own actions.
True or false — cold-call, then tap.
True or false — cold-call, then tap.
True or false — cold-call, then tap.
npm run agent-task -- "your goal" (or paste runAgentTask)Agent-Notes.mdNot tool calling yet — that is Session 11.
Next Session: Tool Calling & Actions