Leverage AI · Founding pre-sale
Build a real product with AI agents, and get it to paying customers.
Most AI-built projects die for three reasons: too big, no buyer, no finish line. The Builder's Toolkit is the process our own agent team uses, written down: 7 modules, each with templates, checklists, copy-paste prompts for Claude Code, Codex or Cursor, and a real worked example from a product on the App Store.
Founding price for the first 20 buyers (20 left). Module 1 is ready now; the other 6 ship on the dates below. Full refund on request until Nov 11, 14 days after the last module ships.
The 7 modules
1. Decide · Ready now
Idea pressure test (12 scored questions), one-week scope cut, go / change / drop rule
2. Write the PRD · Ready now
One-page PRD template, acceptance checks your agent can run and prove, a gap review by a second agent
3. Set up the agents · Ships Oct 20
Instructions file, skill files, setup checklist
4. Run the loop · Ships Oct 22
Build agent + review agent, task splitting
5. Verify and ship · Ships Oct 24
Check-before-done list, ship list
6. Launch · Ships Oct 26
Launch checklist, landing page and signup, search and AI-search setup
7. Get the first customers · Ships Oct 28
Content engine, outreach scripts, weekly numbers table
Inside module 1, ready now
- A guide to deciding what to build, and how small to start (about 3,400 words).
- The idea pressure test: 12 questions, each scored 0 to 2, with a clear go / change / drop rule.
- Two copy-paste prompts: an agent interview that asks the questions you would not think to ask, and a second-agent review.
- The one-week scope cut: Must, Money, Later, Never, and 3 to 5 checks that define done.
- A worked example from a real iPad app, including where its first test said "change".
Read a page first
Checklist: Finish Module 1 (Decide)
Free sample from The Builder's Toolkit.
Checklist: Finish Module 1 (Decide)
The Builder's Toolkit, by Leverage AI (leverageai.io)
Tick every box before you start Module 2. If a box stays empty, go back to the step in brackets.
Set up (5 minutes)
- I made a project folder with a
decide/folder inside it. (Guide, Part 6) - My agent or AI chat is open in that folder.
- I told the agent: no code during this module.
Pressure test (about 2 hours; the interview alone takes about an hour, often more)
- I wrote my idea in three lines: what it is, who pays, the job. (02, Part 0)
- The agent researched competitors, prices and workarounds, with links, or it marked facts "NOT VERIFIED". (Prompt A, Step 1)
- I answered all 12 questions, one at a time. (Prompt A, Step 2)
- The agent asked me 3 to 5 questions I would not have thought to ask, and I answered them. (Prompt A, Step 3)
- Every score of 2 has evidence I can point to: a link, a price, a named place, or a person. (02, "How to score")
- I opened at least 2 of the agent's links myself and checked them.
- Optional: a second, fresh agent reviewed the scores with Prompt B, and I accepted its changes.
Decision (10 minutes)
- I applied the rule. GO = 16+ of 24 and all four key questions at 2. If a DROP row and a CHANGE row both match, it is DROP. (02, Part 6)
- The test number (FIRST or SECOND), the decision, the date, a one-sentence reason and the biggest risk are at the top of
decide/pressure-test.md. - If CHANGE: I changed one thing only (buyer, job, size, or the missing evidence for a key question) and ran the test again as test SECOND.
- If DROP: I wrote what would make me look at the idea again, and moved it to my ideas file. Module done. Start again with the next idea.
Scope cut (about 1 hour, GO only)
- I listed every feature and idea, plus the competitors' features. (03, Step 1)
- I wrote the one job in one sentence: When / wants to / so that / They pay. (03, Step 2)
- Every item is in Must, Money, Later or Never. (03, Step 3)
- Must has 7 items or fewer. Money has 1 to 2 items.
- Every Later item is in
decide/later.md. - I marked the Must items I can do by hand for the first users. (03, Step 4)
Done defined
- I wrote 3 to 5 acceptance checks in Given / When / Then form. (03, Step 5)
- Each check is about the user's job and I can run it myself on a real device.
- The last check is about money: a new user pays and gets access.
- I wrote a start date, an end date 7 days later, and the stop rule "cut, do not extend". (03, Step 6)
Locked
-
decide/scope.mdexists and has all sections. (03, "The finished file") - The scope rule is in my agent's project instructions file (
CLAUDE.md,AGENTS.md, or Cursor rules). (03, Step 7) - I can say the one job and the checks out loud without reading them.
Output of this module: decide/pressure-test.md (with a GO), decide/scope.md, decide/later.md.
Next: Module 2 turns these files into a full requirements document (PRD) for your agent.
The terms, plainly
- $49 once. The price rises when all 7 modules have shipped.
- The founding counter shows real sales from Stripe.
- You get a private page that shows each module as it ships. Bookmark it.
- Full refund on request until Nov 11, through the contact page.