A hands-on day with AI coding agents — Claude Code, Codex and Cursor. Learn to scope, prompt, review and ship real work with an agent, on your own repo.
The tools change weekly. The skill of working with them doesn’t.
This hands-on day teaches the durable skill, not this month’s buttons: how to scope work for an agent, prompt it, review what it produces, and keep it safe — demonstrated across Claude Code, Codex and Cursor.
Bring your own repository and leave having shipped something real.
Built for working developers; also the foundation for our team programs.
Agents fail most often because the task was too big or the constraints were never stated. That is a skill, and it is teachable.
These tools produce plausible code quickly. Reading it critically and quickly is what separates useful from dangerous.
We teach the mechanism underneath Claude Code, Codex and Cursor, so next quarter's release doesn't reset your skill.
Movement I · Blocks 01–02Understand the loopWhat an agent is actually doing, and how to scope work it can finish.
Movement II · Blocks 03–04Review and containReading generated code critically, and keeping an agent safe in a real repository.
Movement III · Block 05ShipA real change from your own codebase, taken all the way to commit.
What an agent is actually doingContext windows, tool use and the loop underneath Claude Code, Codex and Cursor. Enough of the mechanism that the failures stop being mysterious.
A mental model of the loop, so the failures stop being mysterious.
Scoping work an agent can finishThe single biggest determinant of success. How to size a task, state the constraints, and give an agent the context it needs without drowning it.
A repeatable way to scope and brief work for a coding agent.
Review, the skill that decides everythingReading generated code critically and quickly: what to check first, which mistakes these models repeat, and when to throw the output away rather than patch it.
A review habit that catches the mistakes these tools actually make.
Keeping an agent safe in a real repositoryBranches, scopes, secrets and tests. How to let an agent work in a codebase that matters without risking it.
Branch, scope and secret hygiene you can apply in your own repo on Monday.
Ship somethingThe last block is yours. You take a real change through scoping, generation, review and commit, on your own repository, with help at your shoulder.
One real change shipped from your own repository during the day.
The final block is yours. You take a real change through scoping, generation, review and commit — on your own repository, with a practitioner at your shoulder.
What you leave with is not a certificate but a merged change and a written account of where the agent helped, where it was wrong, and what you would brief differently next time.
For working developers. You should be comfortable in your own codebase and with Git — we do not teach programming here.
Bring a laptop with Git installed and a repository you are allowed to share, plus accounts for at least one of Claude Code, Codex or Cursor. We send setup instructions a week before.
Frameworks are great. But understanding what they abstract — the loop, the parsing, the failure modes — is what lets you actually debug and design them under pressure.
Amir founded, funds and directs AI Tech Institute, and still teaches. He holds a PhD and has spent more than twenty years building and leading AI, machine learning and data teams in Australian industry — the kind of work the programs here are drawn from rather than adapted to.
He currently leads asset performance and analytics at Synergy, Western Australia's state-owned electricity generator and retailer. Before that he led GenAI and MLOps program delivery at EY, working on platform modernisation for tier-one Australian banks; served as Chief AI Engineer at Hancock Prospecting, where he built enterprise GenAI platforms for executive decision support, led a Snowflake migration, stood up on-premises NVIDIA H100 infrastructure and Kubernetes clusters for production AI, and built a team of twelve engineers; and spent nearly five years as Tech Lead for ML and Data Science at Woodside Energy.
He has been teaching for twenty-one years. He is an Adjunct Associate Professor at the University of Western Australia, teaching quantitative analysis and decision-making at master's level, and holds Databricks University Alliance Faculty status and the AWS Certified AI Practitioner certification. He has published peer-reviewed research in Exploration Geophysics on machine learning for reservoir characterisation, and writes and records openly about the parts of AI engineering most courses skip — agent loops, termination logic and failure modes.
Cohorts are deliberately small so every piece of work gets reviewed properly and every presentation gets heard in the room. If an intake is full we’ll say so and hold your place for the next one — we won’t quietly oversell a cohort.
See all upcoming dates →The prerequisites for this program are in “Who it’s for” above. Our foundation-level programs and workshops assume none. If you’re unsure, ask on a qualification call — we would rather redirect you than take your money for the wrong cohort.
The commitment for this program is shown in the hero and in “Who it’s for”. Cohort programs run live sessions plus practice between them; workshops are a single block with no homework.
The work you shipped — defended in front of the cohort — and an honest recommendation on your next step. Sometimes that is another cohort with us, sometimes it isn’t; we will tell you which.
No. AI Tech Institute is not a Registered Training Organisation and this is not a nationally accredited qualification. It is professional education, assessed on the work you ship, with a certificate of completion from us. We won’t claim accreditation we don’t have.
Yes — we invoice organisations directly and can supply a scope and outcomes summary for your L&D or capability budget. If three or more people from one team want in, talk to us about a private cohort instead.
Full refund any time before the program starts. Once it has started we can’t refund the place, but we will carry you into a later intake where the circumstances warrant it. Ask us — we’re reasonable.
Thirty minutes with us and you’ll know whether this is your right next step — or which of our programs is. No pitch, no payment, and we will say so if the answer is “not this one”.
