Course Objective & Scope
The most effective AI products do not try to sideline human beings; they pair human judgement and domain context with machine speed and scale. Poorly designed interactions, by contrast, turn experts into passive rubber-stampers whose attention drifts just when a critical edge case appears.
This course translates Human-AI Interaction (HAI) research—including updated Microsoft HAX and Google PAIR principles for the LLM/agent era—into mixed-initiative product workflows. Participants create a human–AI task allocation map and interaction design guide for their own product.
Who Should Attend?
- Product managers, UX researchers and interaction designers
- Digital workplace teams designing internal employee copilots and decision tools
- AI transformation and adoption leaders
- No technical prerequisites
Key Takeaways
- Map which cognitive sub-tasks belong to human judgement versus AI automation
- Design active engagement patterns that prevent automation complacency and skill atrophy
- Build adaptation loops that learn from a user's edits and preferences over time
- Design multiplayer human–AI workflows where teams collaborate alongside shared agents
- Balance speed metrics with decision quality and long-term human expertise retention
Curriculum
Automation vs Augmentation: Cognitive Task Allocation
- Navigating the jagged frontier of AI capabilities across sub-tasks
- Generator–verifier, co-creator and Socratic thought-partner interaction modes
Mixed-Initiative Interaction Principles
- Applying Microsoft HAX and Google PAIR guidelines to LLMs and agents
- Deciding when AI should proactively suggest versus wait to be invoked
Cognitive Ergonomics and Preventing Skill Atrophy
- Addressing review fatigue when work shifts from authoring to auditing
- Cognitive forcing functions that elicit human judgement before revealing AI suggestions
Longitudinal Adaptation and Multiplayer AI
- Adapting to user style and domain preferences from implicit edits
- Designing shared AI interactions inside team channels, docs and meetings
Workshop: Redesigning a Human–AI Workflow
- Re-architecting an organisational workflow around human–AI complementarity
- Task allocation matrix, failure/escalation rules and evaluation plan
Other Courses in This Category
-
End-to-end metric architecture for AI products: North Star and task completion, acceptance rate and edit distance, offline/online eval correlation, retention and cost per successful task.
- Live Course
- 5 modules
-
Experimentation design for probabilistic AI products: moving from offline evals to online A/B tests, shadow deployments, interleaving, controlling for novelty effects and multi-metric ship criteria.
- Live Course
- 5 modules
-
Model behaviour and quality management for product teams: behaviour specifications (tone, boundaries, refusal style), systematic error analysis, domain-expert rubrics and continuous quality loops.
- Live Course
- 5 modules
-
Managing the quality, latency and cost triangle in AI products: model routing and cascading, prompt/semantic caching, token budgeting, perceived-speed UX and gross margin protection.
- Live Course
- 5 modules
-
Managing AI-native products where AI is the core engine rather than a bolted-on feature: compound AI systems, eval-driven development lifecycles, data flywheels and modern PM–AI engineer collaboration.
- Live Course
- 5 modules
-
Agent Experience (AX) and delegation UX for products where users hand off multi-step jobs to autonomous agents: task briefing, plan sign-off, async progress tracking, blocker escalation and deliverable review.
- Live Course
- 5 modules
Get in touch
