← MindForgeAI homeJanuary 2027 proposed cohort · Admissions not openConnected campus
LaunchpointBY MINDFORGEAI
← Course catalogue

LANGUAGE & GENERATIVE AI / SPECIALIST

AI350Agent engineering, tool use & evaluation

24 h productive allocation9 h 36 m learning + 14 h 24 m training4 units · 1 assessed practical brief

Detailed course plan and training brief. A complete taught course pack is in preparation. The linked foundation module, where shown, is a smaller available resource.

BEFORE YOU BEGIN

A clear starting point.

Prerequisites: AI320 · MLO401

Specialist studio; environment and faculty must be confirmed before scheduling

WHAT YOU SHOULD BE ABLE TO DEMONSTRATE

  1. Explain the assumptions and failure modes in workflow architecture.
  2. Complete the practical: implement a bounded engineering-assistant workflow with a simulated external-action tool and a required approval step.
  3. Defend the resulting workflow graph with reproducible evidence.

THE SUBJECTS / FOUR CONNECTED UNITS

What you will study.

UNIT 016 h allocated

Workflow architecture

  • State machines
  • agent loops
  • planning
  • deterministic alternatives
UNIT 026 h allocated

Tools and memory

  • Typed tool inputs
  • scoped access
  • retention
  • failure responses
UNIT 036 h allocated

Control and safety

  • Approval checkpoints
  • budgets
  • injection resistance
  • idempotency
UNIT 046 h allocated

Evaluation

  • Task completion
  • traces
  • adversarial cases
  • human review

THE TRAINING STUDIO

Make the subject
visible in your work.

Implement a bounded engineering-assistant workflow with a simulated external-action tool and a required approval step.

Evidence to produce

  • Workflow graph
  • tool contracts
  • replayable traces
  • red-team cases

Training brief for supervised delivery. Code, datasets, answer keys and environment acceptance must be completed in the full course pack before delivery is confirmed.

ASSESS THE REASONING

A question you
should be able to answer.

Why is a successful demo not proof that an autonomous workflow is reliable?

Review dimensions

Technical correctness · reproducibility · interpretation of results · failure analysis · individual explanation. Course-level rubric and faculty moderation form part of the final adopted teaching pack.

External reference access, hardware, cloud accounts and paid services are separate. No third-party certification is included by implication.

Search by topic or purpose. Press Escape to close.