AI Engineering Workshop

Dr. Aki Wijesundara

AI Advisor | Google AI Accelerator Alum

Manu Jayawardana

AI Founder | Co-Founder & CEO at Krybe |

5.3× ROI when engineers use Claude Code as a teammate

Your engineers already have Claude Code - but they use it like autocomplete, not a teammate. It suggests snippets while the real engineering - shipping changes in unfamiliar codebases, building agents, wiring evals into CI - still happens by hand. Across two evenings, on your own real codebase, that changes.

The math: teams that adopt AI properly run 25.1% faster on AI-suitable tasks - about 2.5 hours back per person, every week - which compounds into a 5.3× annualized ROI (Harvard Business School × BCG; U.S. BLS labor data). Break-even is ~28 minutes saved per person per week.

Proven on real teams. The same shape of session we ran for Modern Health, where Product, Ops, Design and Engineering each shipped a working build on their own data in a single day; MPB, 5× faster listing throughput; and Type B Digital, operator output lifted 2.5×.

One date, your whole team. Bring two people or twenty, no cap on numbers. Nobody experiments alone - everyone walks out on one setup and one shared way of working. Go native across the full engineering loop - delegate, build, ship with evidence.

Exact date and time are confirmed after enrolling. Questions first? Email us or book a call here.

What you’ll learn

From "I've tried Claude Code" to shipping a real change, a working agent, and an eval harness in one focused day.

Decide what's genuinely safe to delegate vs. what stays human
Recognise the failure modes that matter and the review norms that catch them
Build a delegation map you can apply to your own backlog

Context engineering: give the agent what it needs to act well
Agentic patterns, tool use, and MCP for real workflows
Onboard Claude Code to a real repository

Navigate code you've never seen, unguided
Make the change and open a pull request
Get it reviewed and merged

Scope an internal task worth automating
Build the agent with tools + MCP
Run it reliably on a real task, with failure modes handled

Test behaviour with an eval harness (LLM-as-judge / trajectory eval)
Set acceptance criteria before engineering builds
Wire a path into CI as an eval quality gate

Ship one real feature or agent with a harness wrapped around it
Capture guardrails, review norms, and where people stay in the loop as your team's practices doc

Workshop agenda

What Changes for Engineering (45 min · Produces: a delegation map)
Safe to delegate vs. keep human · AI failure modes to watch · review norms that keep quality high
Claude Code in Earnest (60 min · Produces: a configured setup)
Context engineering · agentic patterns · tool use and MCP · onboarding Claude Code to a real repo
Ship a Real Change (75 min · Produces: a merged change)
Navigate an unfamiliar codebase · make the change unguided · open and merge a pull request
Build an Internal Agent (75 min · Produces: a working agent on a real task)
Scope a task worth automating · build the agent end to end (tools + MCP) · run it on a real task
Evals and Harnesses (60 min · Produces: an eval harness)
Test behaviour, not just code that runs · stand up a harness (LLM-as-judge / trajectory eval) · wire a path into CI
Ship with Evidence (90 min · Produces: a shipped feature + harness)
Ship one real feature or agent · wrap an evaluation harness around it · demo with evidence
Operating Practices (30 min · Produces: a practices doc)
Guardrails · review norms · where people stay in the loop · your team's practices doc

Learn directly from Aki & Manu

Dr. Aki Wijesundara

Contact

AI Advisor | Educator | Google AI Accelerator Alum

Manu Jayawardana

Contact

AI Founder | Co-Founder & CEO at Krybe | Co-Founder of Snapdrum

Previous Students from

See all products from TAI Labs

Who this workshop is for

Software engineers who want to use Claude Code as a real engineering teammate, not autocomplete
AI engineers shipping agents and AI features who need evals and guardrails
Tech leads & eng managers defining how their team works with AI delegation, review, quality

What's included

Live sessions

Learn directly from Dr. Aki Wijesundara & Manu Jayawardana in a real-time, interactive format.

Lifetime access

Revisit all lessons, recordings, templates, and code repositories whenever you need , your learning doesn’t expire.

Community of peers

Join a cohort of ambitious builders, stay accountable, and collaborate with engineers, PMs, and founders working on similar goals.

Certificate of completion

Show your new AI engineering skills to employers, add it to LinkedIn, and strengthen your portfolio.

Follow-up office hours

Open office hours for questions and personalized feedback.

Maven Guarantee

Your purchase is backed by Maven

Maven Guarantee

Your purchase is backed by the Maven Guarantee.

Testimonials

Engineers improved the real systems they ship every day, and left with production-ready Claude integrations and a reusable AI playbook.
WireApps
AI-first engineering agency, 50+ engineers. Six-week cohort.
In a single on-site day, Product, Ops, Design and Engineering each shipped a working build on their own real data, using Claude Code and MCP.
Modern Health
Global mental health platform (Lyft, EA, Ancestry). On-site workshop.
The AI training approach is outstanding. Our team learned to build practical AI solutions that we could implement immediately in our educational platform. The hands-on methodology made complex AI concepts accessible to our entire development team.
Kavi T.
CEO of Tilli Kids / Stanford PhD
Not only are the instructors experts in their field, they're incredibly skilled at breaking down complicated AI concepts so students can grasp them quickly. Anyone interested in building foundational AI knowledge should take this training - it's worth the investment.
Dr. Elizabeth Creighton
Founder & Principal at Brazen
The instructors help break down AI model development and clearly have plenty of experience to help others learn about complex concepts like infrastructure setup. The practical approach to NLP and LLM applications was exactly what our team needed.
Alissa Valentine
NLP & LLM Real World Data Scientist
I sent my team through this training for upskilling, and the results have been remarkable. Within weeks, they became much more efficient at building automations and deploying AI agents at work. This program bridges the gap between theory and practice and it’s had a real impact on our productivity.
Aamir Faaiz
CEO of Bayseian