Lesson 1: Toolkit Check - The Delegator's Toolkit¶
Your Track at a Glance¶
Impact Lab offers up to four tracks, each designed to meet you where you are and push you to the next level of working with AI. Depending on the event, not all tracks may be available.
You're on the Intermediate track. For your group, that means moving from Doer to Delegator: going from using AI step by step to get things done toward defining the work clearly and handing entire tasks off to AI.
Here's what each level on the journey looks like:
- Dabbler. You've tried AI tools out of curiosity. Maybe you've asked ChatGPT to draft an email or explain a concept, but AI isn't part of how you work day to day.
- Doer. You use AI regularly to get things done. You can write effective prompts, build with AI assistance, and troubleshoot when things go sideways. You're doing the work with AI, step by step.
- Delegator. You define the work and hand it off. You write clear specs, user stories, and acceptance criteria that tell AI what "done" looks like. Instead of doing every step yourself, you delegate whole tasks and review the output.
- Director. You orchestrate multiple AI workstreams in parallel. You design systems of delegation: quality gates, evaluation harnesses, and structured feedback loops that let you scale AI across your team without losing control.
- Disruptor. You're redesigning how teams and organizations operate around AI capabilities. You think beyond individual productivity, building adoption strategies, self-healing systems, and organizational patterns that change how work gets done.
| Track | From | To |
|---|---|---|
| Beginner | Dabbler | Doer |
| Intermediate | Doer | Delegator |
| Advanced | Delegator | Director |
| Expert | Director | Disruptor |
AI-assisted work is uncharted territory. You're here to explore it and bring back real skills that last beyond this event.
Why a Toolkit Check?¶
Before you start any serious work, you take stock of your tools. You make sure you have what you need, you know how to use it, and nothing critical is missing. You might already know most of it, but you check anyway, because starting on the same page matters more than starting fast.
That's what this lesson is. We're doing a quick recap of the foundational concepts from the Beginner track: how AI behaves, how to communicate with it clearly, how to write prompts that produce reliable results, and how to give AI persistent project knowledge. Some of this will be familiar. Some of it might be new. Either way, this toolkit check ensures your whole team is starting from the same baseline.
Here's why this matters more than it used to: the bottleneck has shifted. AI can write the code. The hard part is getting clear about what you want built and how it should work. That means anyone who can define what needs to be built can ship it: designers, PMs, engineers, managers. We've seen designers go from producing Figma mockups to building testable prototypes in days, work that previously took weeks and required an engineer. Every concept in this lesson (the Three Pillars, delegation contracts, standing instructions) exists to make your intent precise enough that AI can act on it reliably.
If some of this is new to you, that's completely fine. You're in the right place, and your teammates are your best resource. Lean on each other. The goal isn't to have all the answers walking in. It's to have them walking out.
If you already know this stuff, great. Use this as a chance to sharpen your mental models and help your teammates get up to speed. Teaching a concept is one of the fastest ways to deepen your own understanding of it.
By the end of this toolkit check, you'll have the shared vocabulary and toolkit your team needs to start delegating real work to AI, together.
Now set your baseline. You read what Doer and Delegator look like above. Where do you honestly feel you are on that spectrum right now? This is a starting point, not a grade.
When you submit this slider, your avatar moves to your starting position on the progress board. You will check in again after each lesson, so you can see your own growth over the course of your Impact Lab.
What You'll Learn¶
- How AI processes your requests, and the three behaviors that explain most of its surprises
- A framework for making requests that consistently produce what you need
- How to write delegation contracts (user stories with acceptance criteria) that define "done" before you start
- How to give AI standing instructions so it remembers your project across conversations
Sections¶
- How AI Thinks - The three behaviors that explain most AI surprises
- Making Clear Requests - A framework for specific, effective prompts
- Stories as Delegation Contracts - User stories and acceptance criteria as your delegation format
- Standing Instructions - Project context files that persist across conversations
By the End of This Lesson¶
- You can explain why the same prompt produces different results, and why that's fine
- You can write a prompt using the Three Pillars (Scope, Intent, Structure)
- You can write a user story with acceptance criteria that defines "done" for AI
- You understand how project context files solve the "re-explaining every time" problem
- You're ready to start Challenge 1 with a clear delegation strategy
Meet Your Team
Team Discussion | ~3 minutes total | Round robin, one person at a time
Go around your team and have each person share two things:
- Your AI building experience so far. Have you used an AI coding assistant to build something? A prototype? A feature? A full application? What's the most ambitious thing you've tried?
- What you're hoping to level up on. What do you want to walk away from this lab being able to do that you can't do now?
Listen to each other. You'll be building together for the duration of the event, and knowing where everyone's starting from makes the whole team stronger.