AI-Native Software Factory Buildcamp
Paramanantham Harrison
Head of Engineering at Jobbatical
Build the system that makes coding agents easier to trust.
You already work with a coding agent, but getting useful code from it still takes constant supervision. It writes a function in seconds, and then you spend the afternoon re-explaining your codebase, checking whether it broke something, and cleaning up the pull request.
The agent is not the problem. There is no system around it: nowhere safe for it to run, no reliable way to give it the right context, and nothing that checks its work before it reaches you.
In this buildcamp you build that system for your own team, one project a week: your workflow from triage to pull request, then your blueprint of rules, skills, commands, hooks and verification gates, then the Software Factory that runs it. By the final Saturday, a real issue from your backlog becomes a verified pull request waiting for your review.
I have been building software since 2011, and today I am Head of Engineering at Jobbatical and build production agentic engineering systems. The course is based on systems and workflows I build and use in practice, rather than isolated demos.
What you’ll learn
Build your workflow, your blueprint and your Software Factory, so real issues become verified pull requests on your own codebase.
Map how an issue moves from triage to a merged pull request on your team today.
Split that path into stages an agent can run: triage, plan, build, verify, review and deliver.
Give each stage an input, an output and an owner, agent or engineer.
Write the check that ends each stage before work moves on.
Decide which stages an agent may run alone and where an engineer approves.
Walk one real issue from your backlog through every stage of your workflow.
Set boundary rules for what an agent may never touch in your repositories.
Turn repeatable engineering know-how into skills and commands instead of rewriting prompts.
Load only the context each task needs, so agents stay accurate on a large codebase.
Run hooks before and after an agent acts to block unsafe steps early.
Add static analysis gates and holdout tests the implementing agent never sees.
Define what a pull request must carry before it reaches review.
Choose where each task runs, in a Git worktree, container or sandbox.
Limit the files, commands and network access each run can reach.
Break a plan into tasks small enough to verify one at a time.
Connect a Doer and a Tester so a failed check comes back with the reason.
Set retry limits so a run finishes, escalates or stops instead of spinning.
Open a pull request only when every gate passes, and leave the merge to an engineer.
Learn directly from Paramanantham
Paramanantham Harrison
Engineering leader, Agentic AI educator
Who this course is for
Senior and staff engineers who use coding agents daily and are tired of reviewing work they cannot trust
Tech leads who want agents on real backlog issues without risking the main branch or the team's standards
Prerequisites
You work in a real codebase
You are comfortable with Git, tests and pull requests in a project you are allowed to change.
You have used a coding agent
Any command-line coding agent works, and you do not need to be an expert with it.
You can build between sessions
The weekly projects are where your workflow, blueprint and Software Factory take shape on your own repositories.
What's included
Live sessions
Learn directly from Paramanantham Harrison in a real-time, interactive format.
Live build sessions
Every session is hands-on. You build the next piece of your workflow, blueprint or Software Factory on your own codebase while I build it alongside you.
Weekly office hours
A live hour each Saturday to get unblocked on your repository, your agent setup or that week's project.
Starter repo and sandbox
A reference Software Factory, ready to run from the first session, so your time goes into adapting it to your team rather than setting it up.
Capstone demo and live feedback
Your third project is a Software Factory that takes a real issue to a verified pull request on your own codebase, and you demo it on the final Saturday for feedback from me and the cohort.
Rejoin a future cohort
Keep lifetime access to the materials and join a later live cohort of this course at no extra cost.
Recordings you keep
Every live session is recorded, so a missed session or a second look is always there.
Cohort community
A space to share your workflow and blueprint, compare approaches and get help from engineers building the same thing.
Certificate of completion
Share what you built with your employer or on LinkedIn.
Maven Guarantee
Your purchase is backed by the Maven Guarantee.
Course syllabus
9 live sessions • 6 lessons • 3 projects
Week 1
Week 1: Design Your Workflow
Oct
19
Design Your Triage-to-PR Workflow
Oct
21
Define the Checks and Human Approvals at Each Stage
Oct
24
Office Hours
Week 2
Week 2: Write Your Blueprint
Oct
26
Write the Rules, Skills and Commands Your Agents Load
Oct
28
Add Hooks and Verification Gates
Oct
31
Office Hours
Free resources
Schedule
Live sessions
4-4 hrs / week
Two build sessions a week on Mondays and Wednesdays, recorded in case you miss one
Mon, Oct 19
4:00 PM—6:00 PM (UTC)
Wed, Oct 21
4:00 PM—6:00 PM (UTC)
Sat, Oct 24
4:00 PM—5:00 PM (UTC)
Office hours
1-1 hr / week
Saturdays, live Q&A on the problems you hit in your own codebase
Projects
3-5 hrs / week
Your workflow in week 1, your blueprint in week 2 and your Software Factory in week 3, built on your own repositories
Frequently asked questions
Maven for Teams
Reimbursement
Get your company to pay
Everything L&D needs: email template, receipts, and certificate of completion.
Get reimbursedPrivate cohort
Run a cohort for your org
A dedicated cohort with a custom schedule and curriculum, tailored to your team.
Book a private cohort$1,997
USD