Description
Set up a shared delivery system for a product owner and engineer working with AI coding agents: a working agreement, a weekly cycle, two approval gates in GitHub, and evidence-based reviews.
Price$800Per person
Time8 course hoursOn-demand video and labs, plus 1 hour of coaching
DeliveryOn-demand asynchronous trainingWith online support and 1 hour of coaching
CredentialCertificate of completionFrom We Can Code IT
Your capstone, reviewed by a coach
You finish by running one real feature through a full delivery cycle with your partner (or your coach in the other role), and your coach reviews it with you, including both approval gates. That review is part of earning your certificate.
Group coaching for teams
Each learner gets 1 hour of coaching. Teams pool their hours into group sessions, so a team of 6 shares 6 hours of group coaching.
About this course
Spec-driven development works when the product owner and the engineer run it together. This course sets up the shared system: one definition of done where shipped means verified on the main branch, a written working agreement, a weekly cycle from specification handoff to review, and two approval gates configured in GitHub (engineer review on each pull request, product owner approval to promote to production). You also learn to raise delivery problems with board data rather than blame. It is designed for a product owner and engineer taking it together.
Who it is for
This course is for product owners and engineers who work together on software built with AI coding agents, founding teams, and the team leads who set up their process.
Prerequisites
Spec-Driven Development for Product Owners, or Spec-Driven Software Development with Claude Code or with OpenAI Codex
Requirements
Any computer with a modern browser
A free GitHub account
Labs use a public practice repository, since branch protection requires a paid plan for private repositories; do not put employer code in it. Teams on a paid GitHub plan can use a private repository.
A partner from the other role is recommended (product owner with engineer); learners without one work through the labs with their coach in the other role
What you will be able to do
- You will be able to write a definition of done and a working agreement that state what the product owner, the engineer and both own.
- You will be able to set up a weekly delivery cycle on a GitHub Projects board, from specification handoff through pull requests to review.
- You will be able to configure two approval gates in GitHub: engineer review on each pull request and product owner approval to promote to production.
- You will be able to report delivery health from board data such as ready-queue depth, time in review and unowned work.
- You will be able to run a process-only retrospective that results in a specific change to the working agreement.
Syllabus
1
Two roles, one definition of done 1 hour
What each role owns, Shipped means verified on main, Evidence for every status.
Lab: You will write your team's definition of done with a check for each line.
2
The working agreement 1.5 hours
Ready queue depth, Acceptance within one working day, Named owners, Work-in-progress limits, Demos per pull request, Automated review.
Lab: You will draft a working agreement for your team and mark who owns each item.
3
The weekly delivery cycle 1 hour
Specification handoff, not status meetings, End-of-week pull requests, Review and planning, Written daily check-ins.
Lab: You will plan one full delivery week on a GitHub Projects board with dates on every card.
4
Approval gates in GitHub 1 hour
Story pull requests and promotion pull requests, Rulesets and required reviewers, Earning direct pushes through automated review.
Lab: You will configure both gates on a shared repository and promote one change through them.
5
Delivery health from board data 1 hour
Ready-queue depth, Time in review, Unowned work, Words that turn process into blame.
Lab: You will build a board view that shows queue depth and time in review, and rewrite three blaming messages as data-backed observations.
6
Retrospectives that change the system 1 hour
Process-only retrospectives, Asking for pushback, Following up on parked concerns, Versioning the agreement.
Lab: You will run a short retrospective with your partner, or with your coach in the other role, and change one line of your working agreement.
7
Capstone 1.5 hours
Agreement, Weekly cycle, Approval gates, Retrospective.
Lab: You will run one real feature through a full cycle with your partner, or with your coach in the other role, and review it with your coach.
+
Coaching sessions 1 hour
Your coach reviews your capstone with you and answers questions as you work. Teams pool their hours into group sessions, so a team of 6 shares 6 hours of group coaching.
How it is delivered
How you learn
On-demand asynchronous training with online support, plus 1 hour of coaching.
Live or in person
Live online or in-person sessions are available for an additional fee. Email admissions@wecancodeit.org for details.
Frequently asked questions
How do product owners and engineers work with AI coding agents?
The product owner keeps specified, checkable work ready and accepts results against evidence; the engineer directs the agents, reviews their pull requests and keeps the checks passing. This course sets up that system.
Spec-driven development vs agile?
Spec-driven development runs inside an agile cycle. It raises the bar for what counts as ready and what counts as done.
What should a product owner do when the code is written by AI?
Keep the ready queue full of well-specified work, define how each item will be checked, and accept or reject delivered work quickly against those checks.
Should we take this course as a team?
Yes. It is designed for a product owner and an engineer taking it together, so the capstone runs a real cycle between you.
What does the coaching include?
Each learner gets 1 hour of coaching. Your coach reviews your capstone with you and answers questions as you work through the labs. Teams pool their hours into group sessions, so a team of 6 shares 6 hours of group coaching.
How long does it take and what does it cost?
8 course hours of on-demand video and labs plus 1 hour of coaching, for $800 per person.
Related courses
Write specifications and executable acceptance criteria that AI coding agents can build from, configure GitHub issue forms and Projects to manage them, and verify delivered work in deploy previews.
10 course hours, $1,000
Build software with Claude Code from written plans: configure CLAUDE.md and agent settings, write verify-first acceptance checks, build in small tested pull requests, review with a second AI model and add security checks to CI.
10 course hours, $1,000
Build software with OpenAI Codex from written plans: configure AGENTS.md and agent settings, write verify-first acceptance checks, build in small tested pull requests, review with a second AI model and add security checks to CI.
10 course hours, $1,000
Enroll your team
One or a few learners
Choose the number of seats, add the course to your cart and check out.
A group, or a written quote
Send the form below for group enrollment or a written quote. We reply within one business day. You can also email admissions@wecancodeit.org.
We Can Code IT, LLC, 26300 Cedar Rd, Suite 1105, Beachwood, OH 44122. Registered with the Ohio State Board of Career Colleges and Schools, Registration No. 15-03-2064T.
