Marcus Stiehler

Ex-Disney Solutions Consultant | Native German | AI & Digital Transformation

Write Specs an AI Can Actually Build From

The Walt Disney Company

Ambiguity used to cost you a rework cycle. Now it ships at speed — see where AI-assisted delivery goes wrong first.

Why AI Amplifies Vague Requirements

A three-question check that tells you whether a requirement is buildable, testable, and free of hidden assumptions.

The Precision Test for Any Requirement

Watch a real stakeholder request go from one vague sentence to a specification an AI coding tool can execute cleanly.

Turn a Fuzzy Ask Into a Spec, Live

AI Rapid Prototyping as a Requirements Discovery and Elicitation Technique

Modernizing Business Analysis

Angela Wick

AI/BA Expert - 25+ years practicing, shaping analysis, product and requirements.

Cohort 1 - Aug 11th (US/EMEA/SA)

You were trained to discover requirements by asking, listening, and writing it all down. That made sense when building software was slow and expensive.Building a working, clickable prototype is now nearly free. You can stand up a working prototype in minutes, and a working prototype pulls out what people actually need faster than any interview, user story, or spec. Put something real in front of stakeholders and the reactions pour out, and those reactions and feedback are critical!AI helps us write faster, but it doesn't mean that writing requirements is still the best way to collaborate.This workshop treats AI rapid prototyping as what it really is: a discovery and elicitation technique. You will build and use prototypes to surface hidden assumptions, expose disagreement, and align technical, business, and vendor teams fast.*This is a "bring your own tool workshop". Students can use any AI rapid prototyping tool. Common tools include: Loveable, Bolt, Replit, Claude Design, Claude Code, Gemini, and Gemini Canvas, ChatGPT, and Copilot. If you do not have access to any of these, we recommend purchasing a monthly access to Loaveable or Claude Pro for about $20 for the month of class.

Master AI prototyping as an elicitation skill, and shift from documenting requirements to discovering them in real time.

Reframe prototyping as the new front end of discovery

Use prototypes to elicit what people struggle to put into words

Know the difference between discovery and delivery prototyping

Prototype across UIs & Workflows, Reports, Data & APIs, features, and full apps 

Facilitate prototyping across business, tech, and vendor teams 

BAs, product owners, product and project managers, systems analysts, requirements engineers, and consultants who bridge business and tech

Use AI to catch what QC requirements, reports, and updates are hiding.

Enterprise HRIS & Quality Leader

Erie Insurance

National University

Sue Lhymn, Ph.D.

HRIS Manager with 25+ years in systems, data, and analytics

Data Quality & AI Risk Specialist

Pfizer

Emergent

University of Phoenix

Davenportu

Laura Harris, Ph.D.

CEO of an AI-driven, IP-generating, quality-focused company

August 2026

<h2>Most project documents look complete. Requirements feel thorough. Status reports read confidently. Updates sound reassuring, but the gaps that cause delivery failures rarely announce themselves. They hide inside vague acceptance criteria, missing edge cases, and assumptions no one questioned at sign-off. </h2><h2>This workshop focuses on that critical window between receiving a document and approving it. Instead of relying on instinct or a quick read-through, you will learn how to use AI as a structured verification partner; one that surfaces what's missing, flags what's ambiguous, and confirms what actually needs to be true before the work begins. </h2><h2>If you have ever approved something that later turned into a costly rework, a missed dependency, or a scope dispute, this session will give you a repeatable system to prevent it. You will leave with an AI-powered verification framework you can apply to requirements, status reports, and project updates starting the same day.</h2>

A practical system to verify project documentation before it gets signed off

Check requirements for completeness and gaps

Surface hidden assumptions and ambiguity before they become rework

Validate alignment to business constraints

Trace requirements back to the business decisions that drove them

Catch misleading or incomplete status reporting

Approve or reject with structured, defensible reasoning

PMs, BAs, and Product Owners who are the last line of defense before a document moves to execution and want to be confident in that role

Stakeholders who approve project documents regularly but lack a structured method for knowing what to look for

Delivery leads who have experienced late-stage surprises caused by gaps that were present at sign-off but never caught.

Your team adopted AI. Why hasn’t delivery improved?

Staff Software Engineer

Luis Vieira

Staff engineer

Agentic Engineering 1

<blockquote>AI coding tools make implementation faster. But typing code is only one part of getting software safely from idea to production.Teams still need to turn ambiguous requests into clear plans, understand how changes affect an existing system, verify that they are safe, and make sound decisions about what reaches production.When code becomes cheap to produce, context, judgment, and verification become the limiting factors.This is why faster coding does not automatically mean faster delivery. Improving one part of the workflow has limited impact when the rest of the system continues to create bottlenecks.This workshop gives you a practical method for improving delivery with agents. You’ll learn to find the constraints slowing down your SDLC, design agents that can safely take on bounded work, and improve them over time using proof of work, feedback, and evals.</blockquote>

Learn how to find delivery constraints, design trustworthy agent workflows, and improve them through evidence, feedback, and evals.

Understand the AI coding plateau

Find agent opportunities across the SDLC

Design a trustworthy agent harness

Improve agent workflows over time

Software engineers using AI coding tools looking to improve their team SDLC

Tech leads and engineering managers who want to understand how to increase engineering output using AI

Engineering leaders who adopted AI tools but aren't seeing it in delivery speed or business outcomes and want to understand why and fix it

Stop fixing symptoms. Go from overwhelmed builder to systems architect: map, diagnose, and design AI into your venture with precision.

Systems Architect · 9 Ventures · Author

THE WORLD BANK GROUP

Carnegie Mellon University

Han Kay

Systems Architect · Carnegie Mellon (MISM) · Triple Master's (MBA, MS) · 30+ yrs

Cohort 1

Most founders don't fail because of bad ideas, bad timing, or weak execution. They fail because they are operating without a coherent mental model for how complex systems actually work. They optimize one engine while starving another. They fix symptoms while the root cause compounds. They apply AI to broken processes and get faster broken processes. They hire smart people who all work in opposite directions.This is not a talent problem. It's an architecture problem.Karpathy calls the missing layer "agentic engineering." Hassabis calls it a "world model." Both point to the same gap. The Systems Intelligence Model (SIM) is what fills it—a complete design architecture for your venture, built to work coherently when everything moves fast and complexity compounds.In 6 weeks, you'll see your venture as a designed system for the first time. Week 5 is the Apple Masterclass: a full deconstruction of Apple from 1976 to 2025—the mini-MBA case study that no MBA program teaches.E.O. Wilson put it plainly: "We have stone-age emotions, medieval institutions, and god-like technology." The SIM is the bridge that closes the gap—not as a philosophy, but as a working architecture for your venture.

AI amplifies everything. Including what’s broken.

Map any venture as a system using the SIM

Find the real leverage points in any complex situation

Design AI integration that amplifies your system, not just your speed

Read any company through the SIM lens — starting with Apple

Founders building a venture who feel complexity outpacing their mental model. You have pieces but no unified operating system.

Founders who hit their first real bottleneck and realized working harder isn't solving the structural problem underneath.

Founders deploying AI tools who keep getting disappointing results — because the system underneath was never designed to work coherently.

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

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

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

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

Using AI coding assistants and tools to write, review, and ship code faster.

Automating professional workflows with AI tools — productivity, operations, and task automation.