Step01
Establish a Structure for Learning
Schedule a recurring hands-on session and open a public channel for prompts, experiments, failures, and questions. Choose one approved tool and send account setup before the meeting.
BeginnerOperations
How to Run an Engaging Hands-On AI Workshop for Your Team
Teach a team to use AI by having everyone build the same small app, compare how the outputs differ, repair failures together, and then push the working result in a personal creative direction.
Source episode · 14:00
How I AI: Brian Greenbaum's 3-Step Playbook for Driving Company-Wide AI Adoptionwith Claire Vo
Brian combines biweekly Product AI sessions with a public Slack channel, has everyone build the same Bolt to-do app, uses failures as live debugging practice, and ends with playful creative iterations.
Before you start
What you need
- A recurring session and public sharing channel
- An approved browser-based builder tool
- A simple prompt and a finishable exercise
- Facilitators who can help with access and errors
- A place to save examples and lessons
What you’ll make
A working first prototype for each participant, shared evidence of model variability and repair strategies, and a repeatable habit of peer learning.
Step by step
The workflow
Follow the sequence once, then adapt the prompts, checks, and handoffs to your own setup.
5 steps
Step02
Design a Hands-On Kickoff Exercise
Give everyone the same small, finishable assignment, such as a to-do app in Bolt. State the minimum working behavior and let participants run the prompt at the same time.
Example prompt
Create a simple to-do application. Users can add a task, mark it complete, and delete it. Keep the first version small enough to run in this session. Explain how to launch the preview and report any error in plain language.
Pick a tool with a very low barrier to entry that produces a visual or tangible result quickly to maximize engagement.
Step03
Demonstrate AI's Variability
Compare the results as a group. Note visual and behavioral differences, then repair a few failures live using the error message and observed behavior rather than starting over.
Example prompt
The preview failed with this error: [error]. Inspect the current project, explain the likely cause, make the smallest repair, and confirm that adding, completing, and deleting a task still work.
Step04
Use Errors as a Teachable Moment
Give participants a menu of visual, interaction, media, and playful changes. Ask each person to choose one, improve the working app, and share the prompt plus result in the public channel.
Step05
Encourage Creative Exploration
Close by naming reusable prompting and debugging patterns, assigning owners to capture them, and announcing the next session topic based on participant questions.
Example prompt
Try modifiers like '...add a retro 8-bit pixel art theme' or '...make it look like MySpace from 2007.'
What good looks like
- Most participants reach a working result during the session.
- Failures become documented repair examples rather than private dead ends.
- Participants can explain why identical prompts produced different outputs.
- The public channel remains active between sessions with useful examples and questions.
Build your next product with ChatPRD
Turn an idea into a PRD, user stories, and a plan.
After the steps
Runbook notes
How to recover when the loop fails and where human judgment helps.
Recover
If it goes sideways
- Account creation or tool access consumes the exercise
- Send setup instructions early, verify access at kickoff, and provide a paired or demo path for blocked participants.
- Participants interpret an initial error as proof they cannot use the tool
- Debug one failure live, model a concise repair prompt, and let participants retry before changing tasks.
- The session turns into a presentation with little tool use
- Time-box the introduction and reserve most of the session for building, comparison, and iteration.
- Experiments disappear after the meeting
- Save prompts, outputs, fixes, and owners in the public channel and open the next session with one reused example.
Keep building
Related workflows
advancedEngineeringClaude
How to Implement AI Governance with Context-Aware Project Controls
Create context-aware guardrails for your enterprise AI agent using a 'Project' governance layer. As a project owner, define rules, scope tools, and require human-in-the-loop approval for sensitive actions, ensuring safe and effective AI use.
Open
intermediateOperationsKai (Stripe)
How to Turn a One-Off AI Chat Session into a Reusable Workflow for Your Team
Transform a successful AI chat session into a reusable skill that anyone in your company can use. Package prompts, tools, and code into a standardized workflow, making it easy to share and scale automation across your organization.
Open
beginnerDataKai (Stripe)
How to Create a Custom Data Dashboard On-the-Fly with a Natural Language AI Agent
Use a natural language AI agent to instantly generate and iterate on custom data dashboards. This workflow queries your company's data securely, allowing non-technical users to perform their own 'last mile' data analysis without filing tickets.
Open
Start shipping
better products.
Join 100,000+ product managers who use ChatPRD to write better docs, align teams faster, and build products users love.
Free to start
No credit card
SOC 2 certified
Enterprise ready