AI-First UX & Service Design 101 & Certification- Design for LLM & Agents
Frank Spillers
25-year UX and Service Design Leader
.jpg&w=768&q=75)
Design AI-first products without breaking trust, teams, or users
This course reframes product and service design for AI-enabled products, services and workflows.
First, we will learn how to stop treating AI as a feature. Instead, you will practice designing human–AI services.
I will teach you how to update User Centred Design for probabilistic systems.
This course defines real AI UX value, not hype. It's based on how I'm using it in enterprise and gov environments (I recently led an AI Frontiers Service Design effort at the UK Government Digital Service).
Next, you will research, prototype, and test with AI in the loop. How? Each week builds toward a complete AI-first service concept. Every session is hands-on. Every artifact is reusable at work.
What you’ll learn
1. Design AI-first services, not just AI features
You’ll leave with an AI Service Anatomy Map that shows users, systems, AI touchpoints, human roles, risks, and recovery moments.
Use the AI Service Anatomy Map to expose the full service system. Compare AI features, AI-supported journeys, and AI-first services.
Deconstruct real AI examples to spot what changes backstage.
You’ll be able to evaluate AI opportunities, so you can avoid vague ideas and focus on problems where AI creates real value.
You’ll leave with an AI Fit Brief that explains the user need, service need, AI role, risks, and success measures.
Use the AI Fit Canvas to test value, risk, and feasibility. Diagnose weak use cases using the AI Anti-Pattern Checklist.
You’ll be able to design how humans and AI work together, so you can reduce confusion, repeat effort, and failed handoffs.
You’ll leave with an AI Service Blueprint that shows responsibilities, escalation points, systems, and governance needs.
Map who does what across users, AI, humans, and systems. Design handoffs that preserve context and accountability.
You’ll be able to specify how an AI should behave, so teams can test, critique, and build from a shared design standard.
You’ll leave with an AI Behaviour Spec and Prompt Map that define inputs, outputs, tone, boundaries, refusal rules, and recovery scripts.
Define acceptable and unacceptable AI responses. Prototype conversations, agent flows, and service behaviors.
You’ll be able to user test non-deterministic AI behaviour, so you can catch service risks before launch.
You’ll leave with a Stress Case Test Grid, AI Test Plan, and Risk Register.
Test AI responses against real-world stress cases. Review edge cases involving confusion, vulnerability, anger, and misuse.
You’ll be able to explain AI design trade-offs, so stakeholders understand what is ready, what is risky, and what needs more work.
You’ll leave with a certification evidence pack and a five-minute stakeholder-ready AI service case.
Build a rollout recommendation using a readiness checklist. Connect design decisions to risk, governance, and service value.
Learn directly from Frank
.jpg&w=384&q=75)
Frank Spillers
I’ve led AI-first service design across government, enterprise, and start-ups.
Who this course is for
Product designers working on AI or automation
Service designers shaping cross-channel, AI-enabled services
UX researchers adapting methods for LLM-driven systems
Prerequisites
You should already understand core UX or service design.
This is not an intro to UX or AI. This is a shift in how experienced practitioners work.
You should be comfortable with journeys, flows, or research
This course assumes you are practising or working closely beside UX roles.
You do not need to code. You do not need ML expertise.
Experience of GenAI is implied. But you don't have to be a prompt master. This is not an intro to GenAI.
What's included
.jpg&w=1536&q=75)
Live sessions
Learn directly from Frank Spillers in a real-time, interactive format.
Lifetime access
Go back to course content and recordings whenever you need to.
Community of peers
Stay accountable and share insights with like-minded professionals.
Certificate of completion
Share your new skills with your employer or on LinkedIn.
Live weekly workshops
Applied labs every week
End-to-end AI service capstone
The chance to practice what you're learning against a realistic project with constraints and challenges.
AI UX sweet-spot framework
This includes how to identify emotional value for AI-assisted UX, guard-railing, how to scale LLM prototyping to production and more...
Maven Guarantee
Your purchase is backed by the Maven Guarantee.
Course syllabus
Week 1
Nov
18
Session 1: What changes in AI-first design
Week 2
Nov
25
Session 2: Finding the right AI use case
Schedule
Live sessions
3 hrs / week
Wed, Nov 18
4:00 PM—7:00 PM (UTC)
Wed, Nov 25
4:00 PM—7:00 PM (UTC)
Fri, Dec 4
4:00 PM—5:30 PM (UTC)
Projects
1 hr / week
Async content
1 hr / week
Testimonials
- Testimonials are a great way to add social proof to your landing page so that students feel more comfortable choosing your course.
Author name
Author title - You can add as many as you’d like! We typically recommend landing somewhere in the 2-6 range and adding photos so that they feel more “real”.
Author name
Author title
Frequently asked questions
Maven for Teams
Reimbursement
Get your company to pay
Everything L&D needs: email template, receipts, and certificate of completion.
Get reimbursedTeam discount
Learn with your teammates
Save 20%+ when 2 or more teammates enroll in the same cohort.
Save 20%+ with a teamPrivate cohort
Run a cohort for your org
A dedicated cohort with a custom schedule and curriculum, tailored to your team.
Book a private cohort$999
USD