Build on it · Class 07
Score where AI pays off in your organization, draft an update with zero invented numbers, and leave with a one-page AI policy your team can live with.
Scheduled once 10 people ask for it. The date and format are confirmed before anyone pays.
This class is for the people who run things: owners, executive directors, and the one person who handles marketing, operations, and the volunteer schedule. In two hours we list the work your organization repeats, score it so you know where AI is worth trying first, and do one real piece of that work: an update written from messy notes that never makes up a number. Then we write the one-page AI policy that lets your team use these tools without anyone guessing what's allowed. You can work on your own organization or on one of our two fictional ones, a bakery and a food pantry.
Before you start: Class 01 or 02, or comfortable writing a detailed request to ChatGPT or Claude and asking it to try again when the answer misses.
Good to know
Try it now · free
Paste this into ChatGPT, Claude, Gemini, or Copilot. The pantry is fictional. The test is whether the AI sticks to the facts you gave it.
You're helping a fictional food pantry, Red Oak Community Pantry, write a short update for its volunteers. Use ONLY the facts below. Do not add any number, percentage, or claim about impact that isn't listed. If something would help but isn't in the facts, write [NEED: what's missing] instead of guessing. Under 150 words, warm and plain. FACTS: - Saturday distributions in September: 4 - Households served in September: 286 - New volunteers who finished orientation in September: 9 - The walk-in cooler was repaired on September 12, paid for by a local church that asked not to be named - November drive, 'Fill the Shelves,' runs November 2 to 21 - Most needed: canned chicken or tuna, cereal, size 4 and 5 diapers - Volunteer orientation: second Tuesday of each month, 6 p.m. After the update, list every number you used and which fact it came from.
Before you trust the answer, check:
Build the full pipeline for a recurring newsletter — source gathering, drafting, review, and scheduling — with a human approval step before anything sends.
You leave with
A working newsletter workflow with approval.
Turn scattered documents, notes, and institutional knowledge into a searchable library your AI tools can reason over.
You leave with
A working knowledge library with a query workflow.
Enough to decide where AI is worth trying in your organization, to learn the one habit that keeps it honest (facts from an approved sheet, [NEED] for everything else), and to leave with a policy your team can read in three minutes. Marketing campaigns from one brief, replies to hard customer and donor messages, writing SOPs, and building a knowledge library from your documents are follow-on labs that start from the map and fact sheet you build here.
No. Every exercise has a bakery version and a food pantry version, and you can switch to your own organization at any point. The method is the same: pick the right work, give AI your facts, and never let it make up a number.
No. Everything in class works with free ChatGPT, Claude, Gemini, or Copilot. Have two signed in so a free message limit doesn't stop you.
Yes, as long as it's something you'd be comfortable posting publicly: your list of recurring tasks, a newsletter, a web page. Leave out customer, client, donor, and staff details. The policy you write in class will say exactly where that line is for your team.
Class 09
Map one tedious task, then build one small working automation with an AI step in the middle and your approval before anything reaches a person.
Class 08
Design your own AI Chief of Staff on paper, then build the manual versions of inbox triage and meeting prep, with you approving every draft.
This is the LifeQuest capstone. From here, learners move into ongoing build sessions and community projects.
Map one tedious task, then build one small working automation with an AI step in the middle and your approval before anything reaches a person.
Design one small AI agent with written limits, run it, try to trick it, and leave with a tested spec and a run where it stopped and asked you.
Turn messy meeting notes into checked action items and a sent follow-up, and boil a long report down to a one-page brief you've spot-checked.
Bring one task you want to make easier. We organize a class when 10 people with similar work needs are interested. See the class details before you decide to enroll.
