Artificial Intelligence (AI) · Advanced level

Advanced level · Module 6 of 6 · 30 guided hours

AI Capstone Project

Design, build, test and govern an AI assistant system for a realistic organisational need, and recommend whether to adopt it.

Learning objectives

  • Deliver a working, evaluated AI system
  • Secure and govern it to a professional standard
  • Make an evidence-based adoption recommendation

Topics

  • requirements and design
  • build with retrieval and tools
  • evaluation and red-teaming
  • governance pack
  • adoption recommendation
  • presentation

Lessons

  1. Lesson 1 Capstone Design

    Finalise requirements, architecture, model choice and safeguards for the capstone system.

    requirementsarchitecturesafeguardsdesign review

  2. Lesson 2 Building the System

    Build the system with retrieval, tools, permissions, logging and offline fallbacks.

    retrievaltools and permissionsloggingfallbacks

  3. Lesson 3 Testing and Red-Teaming

    Evaluate accuracy and safety, red-team the system and fix the findings.

    task evaluationred-team findingsfixesretesting

  4. Lesson 4 Governance Pack

    Prepare the governance documents leadership needs to decide on adoption.

    use policyimpact assessmentmonitoring planreview schedule

  5. Lesson 5 Recommendation and Presentation

    Present the system and a go, no-go or pilot recommendation to leadership.

    recommendationevidence summaryconditions for go-livepresentation

Practical activity

Deliver the capstone through five reviewed milestones: design, build, test and red-team, governance pack, presentation.

Expected outcomes

  • A portfolio-quality AI system and governance pack
  • Experience of leading an AI initiative end to end

Assessment

The level project assessed against its criteria with a presentation and live demonstration.

Taught live by an instructor — online or in person. Free course lessons are for self-study and do not lead to a certificate — see registration options.