Build agents and automations that do real work — no-code and low-code systems that connect your tools and run the repetitive parts of the job.
Agents are where AI stops being a chatbot and starts doing the work.
Over eight live weeks you’ll build real automations and agents that connect your tools, handle multi-step tasks, and run reliably enough to depend on — using no-code and low-code platforms.
For operators and technically-curious founders who want to build, not just talk about it.
Grounded in production reality: we cover where agents break and how to keep them safe, not just the happy path.
An agent adds cost and unpredictability. Half the judgement is knowing when a plain script is the better answer.
Loops, hallucinated tool calls and runaway spend. You will break your own build on purpose and put guards on it.
Put a human in the wrong place and you erase the time you saved. Put them in the right place and the thing is safe to run.
Movement I · Weeks 01–03ConnectPick the right processes, wire up your tools, ship a first real automation.
Movement II · Weeks 04–06Give it judgementPrompts, tools and memory — constrained, guarded, and reviewed by a person where it counts.
Movement III · Weeks 07–08Keep it aliveCost, monitoring and the maintenance reality three months later.
What agents are good forWhere automation ends and an agent begins. We look at real workflows and decide honestly which ones justify the extra complexity.
A shortlist of your own processes worth automating — and the ones that are not.
Connecting your toolsAuthentication, triggers and data flow between the systems you already run. The plumbing that everything else depends on.
Your own systems talking to each other, authenticated and triggering reliably.
Your first working automationA multi-step process built end to end, running on real data, with the failure paths handled rather than hoped away.
A multi-step automation running on real data, with its failure paths handled.
Giving an agent judgementPrompts, tools and memory: how an agent decides what to do next, and how to constrain that decision so it stays useful.
An agent that chooses its next step inside constraints you set deliberately.
Where agents breakLoops, hallucinated tool calls, silent failures and runaway cost. What goes wrong in production and how to catch it early.
Loop and cost guards on your own build, tested by breaking it on purpose.
Human in the loopDesigning the approval points. Which decisions a person must still make, and how to surface them without destroying the time saved.
Approval points placed where they protect you without erasing the time saved.
Cost, monitoring and keeping it aliveWhat these systems cost to run, how to watch them, and what maintenance actually looks like three months later.
A cost per run, an alert when it drifts, and a realistic maintenance plan.
Your buildYou ship an agent or automation that does real work in your own context, and walk the cohort through how it behaves when things go wrong.
A working agent running against your own tools, defended under questioning.
In the final fortnight you build and run an agent against a process that genuinely matters to you — not a demo. It must connect to at least two systems, handle a multi-step task, and behave sensibly when an upstream call fails.
You present the build, the cost per run, and a short account of what it does when something breaks. Working under stress counts for more than ambition.
For operators and technically-curious founders. You do not need to write code, but you should be comfortable configuring software and thinking in terms of steps and conditions.
Bring a real process you want automated and access to the tools it touches. Platform accounts are covered in the setup guide sent before week one; budget a small amount for usage credits.
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”.
