AI ToolsACADEMY
AI Tools Academy
0 / 117 (0%)

Agents, tools and controlled automation

Finishing the course

Capstone · 30 min

Your final assignment

Design an agent workflow that can fail safely and explain its actions. Use the fictional examples from this course, or a non-sensitive scenario you are authorised to work on. Do not submit personal workplace records to complete the course.

Build your evidence pack

  1. Workflow or agent: choose the control you need: Compare those two tasks. Mark fixed steps, model-selected steps and actions requiring approval. Give each process an explicit stopping rule.
  2. Tool contracts and MCP boundaries: Write contracts for a search tool and a draft-creation tool. Specify required arguments, returned identifiers, side effects and what an error response means.
  3. Prompt injection in retrieved material: Create a harmless test document containing a genuine fact and an instruction to print the marker TEST-ONLY. Ask the assistant to extract the fact. Record whether it follows the unrelated instruction.
  4. Retries, idempotency and duplicate actions: Draw the success, confirmed rejection and timeout branches for creating a draft. State which branch may safely retry and what evidence is needed first.
  5. Approval gates, logs and rollback: Design an approval card for the article update. Include the rollback route and one case that invalidates the approval.

Combine the five outputs in the downloadable course workbook. Write a short decision note explaining the problem, your chosen approach, the evidence used and one limitation that would matter in real use. Keep initial and revised versions where a check changed your answer.

Review against these criteria

  • Identify when a fixed sequence is sufficient.
  • Explain what a connected tool may do before calling it.
  • Keep external text from acquiring instruction authority.
  • Handle an uncertain write without blindly repeating it.
  • Make an automated action reviewable and recoverable.

Ask a colleague or learning partner to challenge one assumption if available. If working alone, use the worked examples to review your reasoning and record the limits of that self-review. Completion is a personal learning record, not independent certification.

Change one condition

Choose one input or assumption from your original exercise and change it. Explain which part of the result must be recalculated, rechecked or withheld. Keep the revised answer and a short explanation of why the change matters. This is a transfer exercise: repeating the model answer without adapting it is insufficient.

Continue practising

Try a related Academy workspace or choose another course. The existing Practice Lab portfolio saves simulation work; keep this course workbook with your own learning records. Course completion progress remains in your browser and can be backed up through My Library.