Claude

ChatGPT

LangChain

CrewAI

Microsoft

Sol Farahmand

AI Engineer | 2X Entrepreneur | AI Hackathon Winner

Learn About AI Agent Design Patterns: Choose The Right One

MindStudio

Lovable

AI Hackathon Winner | 2X Entrepreneur | AI Workflow Builder

Learn to break a task that is too big for one prompt into ordered steps that pass results forward.

How prompt chaining works and when it fits

Learn to recognize when a central router should hand a request to a different prompt, model, or agent.

What a routing pattern actually does

Learn to tell which tasks are truly independent and safe to run at once, and which must stay in order.

Where parallelization helps and where it fails

Learn to follow how one agent decomposes a task and coordinates workers that handle discrete sub tasks.

Orchestrator and worker roles, explained plainly

Learn to match a real task to chaining, routing, parallelization, or an orchestrator with workers.

Choose the right pattern for a given problem

You'll learn how to design AI features that people understand, use and trust — with practical UX guidelines and tons of real-life examples.

Sr. UX Lead • LinkedIn Top Voice in UX

European Parliament

Lexware

Otto Group

Axel Springer SE

SmashingConf

Vitaly Friedman

20 years of experience • Senior UX Lead @ EU Parliament • Speaker • SmashingMag

A practical guide on how to design AI features that people actually understand, use and trust.

Summer 2026

September 2026

🍰 20% off – code "CHEESECAKE" (2 spots left)AI features are painfully verbose and unreliable. AI responses are too generic, insights are untrustworthy, hallucinations are hard to spot — and users have to ping-pong between prompts, over and over again. Well, let's fix that!In this course, you’ll learn:<ul><li>State of AI, from limitations to capabilities</li><li>Design patterns for AI products</li><li>Context engineering and how to design for it</li><li>Agentic AI, and how to design guardrails</li><li>How to design for trust and confidence for AI</li><li>How to prioritize impactful AI features</li><li>Launching AI features, where teams fail/succeed</li><li>AI-friendly design systems, and how to set them up</li><li>100s of real-life examples and UX guidelines</li></ul>No fluff, no theory — just what actually works in real products. Practical live sessions and guidelines that you can apply on day 1.<h2>The course includes:</h2>🪴 Real case studies from real products 🔬 All video recordings, slides, resources, templates 🎯 Hands-on tasks and actionable insights 👋 Live interactive sessions and feedback 👫 Dedicated time to answer all your questions 🏅 Well-deserved certificate for your hard work

How to design AI products that people actually use and trust. 

The State of AI UX

Design Patterns For AI Products

Boosting AI UX In Complex Products

Designing For Trust and Confidence

Real-World Case Studies

AI Design Workflow, From Start to Finish

We’ll be spending a lot of time, sketching, designing and thinking. 

Be ready to challenge your general view of the AI design proces.

☕️ Bring your preferred coffee mug!

Product&nbsp;designers who want to understand the constraints of AI and how to design effective AI experiences that people trust and use.

UX Leads who want to learn how to design feasible and effective AI features that don't frustrate people but help them get their work done.

Interface designers&nbsp;who want to boost their AI design skills and understand what makes a truly incredible AI experience.

Learn how to define task autonomy, decision thresholds, guardrails, and human override in agent-enabled systems.

Modernizing Business Analysis

Angela Wick

25+ years practicing, shaping, and teaching analysis, product, and requirements.

Agentic AI Skills for Business Analysts

Agentic AI changes the game because AI can autonomously act. It can initiate actions, make decisions, and operate across workflows with increasing autonomy. Risk escalates, and so does opportunity! Without deliberate, disciplined, and structured analysis, agents act on incomplete logic, unclear boundaries, and undefined escalation paths. That is where exposure multiplies. This course matters because Business Analysts are uniquely positioned to define autonomy limits, decision thresholds, guardrails, and monitoring structures before agents scale. It equips you to design control into autonomy, so AI-driven systems remain accountable, coherent, and aligned with business intent rather than becoming fragile at scale.AI is moving beyond assistance. Agents can:<ul><li>Initiate actions on their own</li><li>Make decisions</li><li>Trigger workflows</li><li>Operate continuously</li></ul>This changes the role of Business Analysis.When agents act without clearly defined:<ul><li>Goals</li><li>Boundaries</li><li>Escalation rules</li><li>Monitoring thresholds</li></ul>Organizations lose control.This course teaches how to design and govern agent behavior responsibly.

Prioritize, Define, Design, and Govern AI Agents and Agentic Systems

Distinguish Between Automation, Copilots, and True Agents

Decompose Tasks for Autonomous or Semi-autonomous Execution

Define Agent Goals, Success Criteria, and Measurements

Define/Design Multi-Agent Orchestration

Design Human Override and Intervention Paths

Participate in Ongoing Evaluation of Agent Performance

Business Analysts, Product Owners, Business Systems Analysts, Systems Analysts, Business Process Analysts, and similar roles.

BA Leaders redefining roles for AI-enabled teams

Business Leaders, Project and Product Professionals pulled into AI initiatives without clear accountability

Build, don't just prompt: ship AI assistants & a multi-agent system in 1 day.

16yrs AI, Founder, Startup Mentor

Zalando

Flipkart

IU International University of Applied Sciences

IQVIA

Baig Academy

Founder, Startup Mentor, 16 yrs AI & data, 3x Author

Cohort 1

Cohort 2

‼️ LIMITED SEATS ‼️⏳ Early Bird Special: Save 20% Today Get full access for 199 (instead of 249).Use code: EARLYBUILD ⚠️ Offer expires soonEveryone's experimenting with AI. Few leaders can actually build with it.Design an agent, give it real skills, and trust it to run a workflow without hand-holding every step.That gap is becoming a leadership skill gap, not just a technical one.This workshop closes it in a single day: you'll learn the same patterns production AI systems run on, skills.md, harness design, MCP, context management, progressive disclosure, and immediately use them to build assistants you'll actually use Monday morning, not throwaway demos.

Go from AI user to AI builder: design agents, skills, and multi-agent systems leaders can actually ship.

Master the skills.md paradigm and build agents in plain English

Build two working AI assistants you'll actually use Monday

Apply the technical depth behind reliable AI agents

Design and ship your own multi-agent system

The leader who wants to build, not just direct.You set AI strategy but want hands-on fluency, not just enough to ask questions.

The builder ready to go multi-agent. You use Claude Code daily and want to upgrade from single prompts to chained systems you can hand off.

Design patterns every AI product needs — and almost none of them have.

REWE

Alliander

20 years in UX  • Senior UX Lead & Advisor @ EU Parliament • Smashing

October 2026

Most AI features ship with an empty box and an empty promise.They pretend to be capable of everything, but break expectations before users even blink. They make users work harder and invite mistakes.Meet 50 AI Design Patterns That Actually Work — from B2B, enterprise and B2C products where reliability is non-negotiable. Used by doctors, lawyers, analysts and experts who can’t afford a plausible hallucination. It's the baseline every serious AI product needs, and almost none of them have.We’ll cover:<ul><li>Where AI lives, from co-pilots to dashboards to agents</li><li>How users prompt, modes of thinking, missing context</li><li>Input UX, to help users articulate their intent better</li><li>Output UX, to navigate and verify AI output</li><li>Refinement UX, to customize and finetune AI responses</li><li>Trust &amp; reliability, to prevent aversion and over-reliance</li><li>Guardrails, to set up limits in high-stakes scenarios</li><li>Agentic AI, gradual autonomy, verification layers</li><li>AI accessibility, keyboard navigation, UI states</li><li>Enterprise AI &amp; compliance, AI labels, GDPR, data</li></ul>You'll leave with a working reference of reliable AI UX patterns. You won't find them anywhere else. That's not a boast — it's just the reality of how long it took to find them.<pre><code class="language-markdown"></code></pre>

A focused 5h deep-dive into 50 practical AI design patterns — from B2B, Enterprise and B2C products, applicable to your work right away.

Where AI Lives and How Users Prompt

Input UX: Designing What Goes In

Output UX and Refinement

Trust, Confidence and Guardrails

Enterprise and Agentic AI

Product designers and product managers who ship AI features in complex, data-heavy or regulated products

Design and UX Leads who want to explore established and emerging practices and make more confident UX decisions for AI

UX researchers and practitioners who want to understand how users actually use AI products and AI features, and how to improve their UX.

Agentic AI

Coding with AI

AI Workflows

Claude Code

OpenClaw

Vibe Coding

AI Evals

AI Transformation

RAG & Search

AI for PMs

AI for Engineers

AI for Designers

AI for Marketers

AI for Founders

Product Sense

Product Discovery

User Research

Prototyping

Growth

Analytics

Tech Foundations

Strategy

Influence

Leadership

Career Growth

Machine Learning

LLM Ops

Context Eng

Security

System Design

Figma

Design Systems

Visual Design

Design Strategy

Automation

Content Marketing

Demand Gen

Go-to-Market

Product Marketing

Positioning

Social Media

Brand

B2B Marketing

SEO & AEO

AI for Leaders

AI Governance

Communication

Management

People Operations

Exec Presence

Storytelling

Goal-setting

Personal Brand

Fundraising

Everyone

Operators

Data Scientists

Business Analysts

User Researchers

Customer Success

Project Managers

HR Professionals

Sales People

Lawyers

Finance

Investors

Real Estate

Educators

Creators

Casual Chat and AI Tool Tips (Grok & Gemini Pro)

Introduction to AI Agent Design Patterns

The Importance of Design Patterns in AI

Foundations: Prompting and Programming

Design Pattern 1: Prompt Chaining

Design Pattern 2: Routing Pattern

Design Pattern 3: Parallelization Pattern

Design Pattern 4: Orchestrator-Worker Pattern

Design Pattern 5: Evaluator-Optimizer Pattern

Additional Patterns and Upcoming Hands-on Labs

Wrap-up, Upcoming Base44 Session, and Q&A

Product managers who drive strategy, development, and launch of products.

Engineers and engineering leaders who build, deploy, and scale software systems.

Data scientists who apply statistical and ML techniques to extract insights from data.

Applying AI tools and techniques to professional workflows — assign alongside more specific AI topics.

Building autonomous AI agent systems that take actions, use tools, and orchestrate multi-step workflows.

Designing scalable, reliable software systems — architecture patterns, distributed systems, and technical tradeoffs.

Learn About AI Agent Design Patterns: Choose The Right One

What you'll learn

Why this topic matters

You'll learn from

Sol Farahmand