Agentic AI
Exercises
- Day 1 Exercise — Deciding What AI Should Not Do Place FitPath's proposed features on the AI Capability Ladder, decline at least three on architectural grounds, and pressure-test your reasoning against an LLM arguing the other side.
- Day 2 Exercises — Prompt Engineering Turn Day 1's workout-plan sketch into a structured prompt that actually behaves, measure it, and then try to break it.
- Day 3 Exercises — Knowledge Systems, Vector Databases, and RAG Ground the Day 2 prompt in FitPath's real documents with RAG, then check whether that grounding made it trustworthy or just made it look that way.
- Day 3 Extra Content — Building the RAG Pipeline in Flowise Assemble the RAG pipeline yourself node by node in Flowise — chunking, embeddings, vector store, retriever — instead of letting NotebookLM decide it for you.
- Day 4 Exercises — Agentic AI Foundations and Agent Design Give FitPath's Weekly Check-In feature real tool access, watch an ungoverned agent make a judgment call on a genuinely risky case, then add an approval gate and confirm it actually changes what the agent does.
- Day 5 Exercise — Build a Supervisor Agent with Specialized Sub-Agents Split a single check-in agent into a supervisor and three specialized sub-agents, wire delegation and a human checkpoint in Fleet, then prove it behaves differently for a clean user than a flagged one.
- Day 6 Exercises — Enterprise Agent Adoption and Business Value Score FitPath's AI portfolio on value and feasibility, build a TCO and value case for the Day 4 agent, and defend the recommendation against incomplete or conflicting stakeholder requirements.
- Day 7 Exercise — Breaking the Agent Network Stand up a five-agent A2A network locally (Main, a Proxy broker, three topic researchers) and deliberately try to break it across eight scenarios, then add your own researcher and give the Proxy a new intent.
- Day 8 — Exercises: Red-Team the Agent & Build the Audit Record Play the attacker: try to manipulate an agent in Google AI Studio using content it retrieves rather than anything you type to it, then build the structured 8-field audit record that proves exactly what happened across every run.
- Day 9 Exercise: The Full Autonomy Ask Elicit what you need from a VP who wants member support fully automated in two quarters, then decompose the ask into discrete actions, assign each one an autonomy level with reasoning, and write a recommendation that states what will not be automated and why.