Get one thing built that you’ve wanted automated, by your own technical person, with review every week.

You have a technical person, or you are one: comfortable in a terminal or a no-code automation tool, or able to read and modify code. You have a real problem from your business or a client’s business, access to the system or data it involves, and a specific thing you want automated or an agent you want running.

Not for: people who want a repeatable workflow inside a chat tool. That’s Zero to Hero, and we’ll say so in the application reply.

• One build, bounded and deployed. A single trigger, a single output, a single user, running somewhere other than your builder’s laptop, in your accounts. Week one exists to cut the project down to that, because the most common failure in builder programs is a project that’s three projects.
• A README someone else could run it from. It comes with a written list of the ways the build fails and what was done about each. Week three is about failure: bad input, tool errors, refusals, hallucinated fields, cost.
• A builder who has shipped once, with Dan reviewing. Every Wednesday at 11:00 Central, Dan builds the week’s step on a reference project from a blank state, on camera, including the decisions he abandons and the things that break. Every Friday at noon, your builder shows their build running or failing, and Dan reads the code or the flow with them and names the one change that matters most.

1. Week 1

   Scope and stand up

   Friday clinic: Scope review

   By Friday your builder has: A scope sentence, an environment, a first successful call

2. Week 2

   The core path

   Friday clinic: Debugging

   By Friday your builder has: The right output on three real inputs

3. Week 3

   Survive contact: evals, failures, guardrails, logging, review points, cost

   Friday clinic: Failure clinic

   By Friday your builder has: A failure list with fixes, ten real inputs run

4. Week 4

   Ship: deploy, README, handoff, what to monitor

   Friday clinic: Demo day

   By Friday your builder has: A deployed build and a certificate

Ten questions, about fifteen minutes. The button opens an email to admin@edgeteam.io with the questions already in it: answer them and send. You can fill it in for your builder or have them do it. Dan reads every application and replies within three business days with one of three answers: you’re in, not this run and here’s the specific thing to sort out first, or this isn’t the right program and here’s the one that is.

The ten questions

1. Name, email, company, role.
2. What do you want to build? One paragraph. Include the trigger (what starts it), the output (what it produces), and who uses it.
3. What problem does it solve, and how is that work done today?
4. Do you have access to the system or data it needs? (yes / partly / not yet)
5. Which describes you best: I write code / I build in no-code tools / I read code and can modify it / none of these.
6. What have you built with AI so far, if anything? Links welcome.
7. Which tools do you plan to use? (Claude Code, an agent SDK, Make or n8n, other)
8. Can you attend Wednesday 11:00 and Friday 12:00 Central for four weeks?
9. Are you an EdgeCore member, an EdgeCore Pro member, or attending through an EdgeCorporate program? (affects seat type, not acceptance)
10. Anything else Dan should know before reviewing?

Apply by email Opens your email app. Or write to admin@edgeteam.io