Skip to content
Module
Module 7 of 7Lesson 1 of 1~30 min

Assemble the agent dossier of a real case

The final workshop brings the whole course together in one concrete deliverable: the design dossier of an agent for your own product, from the initial decision to the evaluation. You self-assess it with a grid, then leave with a reusable kit and a plan to put it to work with your team.

Take this lesson: your first course is freeSee the full syllabus

Lesson objective

By the end of this lesson, you will be able to assemble the agent dossier of a real case in your product (decision, workflow, tool cards, loop, control matrix, injection mitigations, trace and evaluation), self-assess it and plan how to apply it over 7 and 30 days.

Topics covered

  • AI agents workshop
  • agent dossier
  • agent design
  • exit kit
  • action plan

Where it fits

Your agent dossier

How do I assemble the agent dossier of a real case in my product and apply it over the next 30 days?

Lessons in this module

  1. Assemble the agent dossier of a real case (this lesson)

What you will learn in this module

This lesson is part of the course Design reliable agents and tool calling

  • Decide, with explicit criteria, whether a use case calls for a single call, a workflow or an agent, and choose the right pattern.
  • Write tool cards the model uses well (name, description, parameters, return, errors, idempotency, risk level).
  • Specify an agent's loop (goal, context, stop conditions, budgets, error handling) and judge whether an orchestrator and subagents are warranted.
  • Place human approval points and an agent's permissions according to the blast radius of each action.
  • Identify prompt-injection paths through tool outputs and specify structural mitigations that do not rely on the prompt alone.
  • Specify the trace of a run and the evaluation of an agent (task success, trajectory, cost, latency, consistency over several trials).

Related courses