Workshop

AI Engineering Workshop

Aki Wijesundara, PhD

AI Advisor | Google AI Accelerator Alum

Manu Jayawardana

AI Founder | Co-Founder & CEO at Krybe |

Ship Real AI Features in a Day With Claude Code

The exact time and date will be discussed after payment. We will reach out to you to organize all logistics and have a setup call. If you have any questions about the program, you can email us at hello@theaiinternship.com before enrolling.

AI engineering has changed. The bottleneck is no longer writing every line yourself it's knowing what to delegate to AI, how to supervise it, and how to prove the output is safe to ship.

Most engineers still use Claude Code like autocomplete. This workshop turns it into a teammate. In one intense day you'll work in a real, unfamiliar codebase: ship a merged pull request, build an internal agent that completes a real task end to end, and stand up an evaluation harness with a path into CI.

You leave with working artefacts and a team operating model not notes. This is not a lecture. It's a hands-on build day where you ship.

You'll walk away with

- A merged change in a real codebase, shipped with Claude Code

- A working internal agent that completes a real task end to end

- An eval harness wired toward CI, so model behaviour is regression-tested not just "does the code run."

So 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

Aki Wijesundara, PhD

Aki Wijesundara, PhD

Contact

AI Advisor | Educator | Google AI Accelerator Alum

Google
Amazon Web Services
Meta
OpenAI
NVIDIA
Manu Jayawardana

Manu Jayawardana

Contact

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

See all products from TAI

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 Aki Wijesundara, PhD & 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.

Frequently asked questions

Maven for Teams

Reimbursement

Get your company to pay

Everything L&D needs: email template, receipts, and certificate of completion.

Get reimbursed

Private cohort

Run a cohort for your org

A dedicated cohort with a custom schedule and curriculum, tailored to your team.

Book a private cohort