Systems, not demos
You do not learn isolated tools. You learn how AI systems behave under real constraints — cost, latency, hallucination and reliability.
Your mentor
One mentor. All 100 days.
This program is taught from production code, not from slides. The self-healing frameworks, MCP-based Playwright generation, RAG pipelines and evaluation harnesses you build are the same architectures running in real enterprise engagements today.
Background
Quality Engineering Director. AI platform architect.
More than 17 years in test automation and enterprise quality engineering, delivered across banking and healthcare — two domains where getting AI wrong is not an academic problem.
Creator of a multi-agent AI quality platform built on 30 specialised agents spanning generation, execution, intelligence, compliance and operations. Builder of self-healing test automation, NLP-to-Playwright generation via the Model Context Protocol, and AI evaluation frameworks used in live enterprise delivery.
An active public speaker at technology meetups, including BrowserStack events covering agentic QA pipelines, governance, guardrails and evaluation.
Why this matters for you. Most AI courses are assembled by curriculum teams from documentation. This one is assembled from failures — the locator strategies that broke, the retrieval designs that hallucinated, the agent loops that burned tokens without converging. You get the shortcut.
Mentorship model1 : 35
01Live weekend teachingSat & Sun
02Weeknight office hoursdoubts
03Guided project labsweekly
04Architecture reviews1:1
05Mock interviewspanel
06Job-search guidanceongoing
A single accountable mentor across all 100 days — not a rotating cast.
Teaching philosophy
Judgement first, tools second
Failure as material
Every module includes what breaks and why. Analysing a bad retrieval design teaches more than shipping a working one you do not understand.
Reasoning out loud
Interviews are treated as an engineering skill. You practise structuring answers, handling follow-ups and defending trade-offs under pressure.
Compounding feedback
One mentor across 100 days means the review in week 14 refers back to the mistake you made in week 4. That continuity is the product.
Questions
About the mentorship
A single lead mentor teaches the cohort across all 100 days — a Quality Engineering Director with more than 17 years in enterprise test automation and quality engineering across banking and healthcare, and the architect of a multi-agent AI quality platform built on 30 specialised agents.
No, and that is deliberate. The person who reviews your architecture in week 6 is the person who runs your mock interview in week 15. Feedback compounds instead of resetting every module.
Cohorts are capped at 35 so that project reviews, doubt-clearing and mock interviews can be personal. Weeknight office hours are open to everyone, and capstone reviews are one-to-one.
Yes. That is the point — the material comes from systems currently in production for enterprise clients, and it is refreshed as those systems evolve. Our mentor also speaks publicly at technology meetups, including BrowserStack events, on agentic QA pipelines, governance, guardrails and evaluation.
Next cohort
Learn it from someone shipping it.
There is no better way to learn AI engineering than from a practitioner building these systems in production right now.
Cohort snapshot35 seats
01100 days live + self-paced15 wks
02Mentor-led weekend classes10 hrs/wk
038 guided projects + capstoneportfolio
04Interview prep & career supportongoing
Weeknight office hours · lifetime access to recordings · one accountable mentor across all 100 days