Topics
Each topic is a sequenced set of lessons built around one real agent. Read top to bottom, or jump to whichever piece of the reliability problem you're stuck on.
| Title | Lessons | Minutes | Status |
|---|---|---|---|
| Guided determinism for agents using AgentScript Combining LLM flexibility with deterministic gates in Agentforce. Built around one real refund agent. | 14 | 73 | available |
| Demystifying Agent Harnesses What's actually inside an agent harness, how the planner-tools-executor loop runs, and where each design knob lives. Coding agents are the running example; the patterns generalize. | 14 | 74 | available |
| Vibe Coding Reliable Agents Coding fluently with an agent in the loop while keeping the system reliable. The instincts and the guardrails. | – | – | upcoming |
| Testing Agents Writing test specs, asserting on tool calls, and reading run results. What stays deterministic and what doesn't. | – | – | upcoming |
| Observing Agents Pulling session traces, parsing them, and turning behavior signals into actionable diagnostics. | – | – | upcoming |
| Autotuning and Optimizing Agents Closing the loop: using observations to autotune prompts, gates, and tool choice without sacrificing correctness. | – | – | upcoming |