Claude Architect Bootcamp: Build Production AI Agent Systems

Dr. Aki Wijesundara

PhD in ML | Google AI Accelerator Alum

Manu Jayawardana

Exited AI Founder | Founder, TAI Labs

Early Bird Discount ends in 24 hours, then the price jumps back to $1599!

Build production Claude agents with MCP, Claude Code, SDK & orchestration.

Claude is becoming a leading platform for production AI agents. This 4-week bootcamp teaches engineers and technical PMs to architect Claude systems end to end using the API, MCP, Claude Code, Agent SDK, and reliable orchestration patterns.

You’ll build a working agent system through weekly graded assignments and a capstone demo.

The curriculum follows Anthropic’s official Claude Architect certification blueprint (CCAR-F), including a full timed mock exam, while teaching the same production skills companies seek in Claude practitioners.

Taught by TAI Labs, an official Anthropic partner building Claude systems for clients.

Note: Exam access is currently limited to Claude Partner Network organizations; this course prepares you but does not provide exam access.

A limited number of need-based scholarships are available for applicants facing real financial hardship. See if you qualify.

What you’ll learn

Learn to design, ship, and scale LLM products users trust, turning you into the AI product mind teams actually rely on.

Use tool calling, structured JSON outputs, streaming, stop reasons, and prompt caching.
Design for cost, context management, retries, fallbacks, and reliable error handling.

Build MCP servers with tools, resources, prompts, authentication, and remote deployment.
Understand MCP architecture, tool design tradeoffs, and when to use MCP vs native tools.

Build reliable skills, subagents, hooks, headless workflows, and CLAUDE.md configurations.
Apply session continuity, Agent SDK patterns, and hub-and-spoke multi-agent coordination.

Distinguish agents, workflows, and conversational systems and choose the right architecture.
Design retries, fallbacks, programmatic guardrails, error classification, and human escalation.

Evaluate context, orchestration, reliability, and tool-design tradeoffs in real-world scenarios.
Build and defend an end-to-end agent architecture through graded assignments and a capstone.

Learn directly from Aki & Manu

Dr. Aki Wijesundara

AI Founder | Educator | Google AI Accelerator Alum

Manu Jayawardana

AI Advisor | Founder, TAI Labs

Previous Students from

See all products from TAI Labs

Who this course is for

Engineers & technical leads. Build production Claude apps and design reliable agentic systems
Technical PMs & solution architects. Scope, design, and defend Claude agent architectures.
Certification-ready practitioners. For Claude Partner Network candidates and Claude Developer graduates moving to architecture level.

Prerequisites

Comfortable with Python or TypeScript
You should be able to work with at least one of these languages and have some basic coding experience.
Basic API experience + a Claude API key
You should have made API calls before and have a Claude API key. The free tier is sufficient for the course.
No prior MCP or Claude Code experience required
You can start without MCP or Claude Code experience — both are taught during the bootcamp.

What's included

Live sessions

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

8 live sessions

Eight recorded live sessions across four weeks, combining hands-on build sessions with architecture-focused sessions.

4 graded build assignments + Capstone Demo Day

Complete four practical assignments with clear pass criteria, then bring everything together in an end-to-end capstone you demo and defend.

4 weekly scenario quizzes

Test your understanding every week with scenario-based quizzes designed in the same style as the architect exam.

Full 60-question timed mock exam

Sit a complete timed, closed-book mock exam, followed by a domain-by-domain review and a personal gap plan.

Starter repos + reference architectures

Get access to project starter repositories and production reference architectures drawn from TAI Labs’ client stack.

Certificate of completion

Receive a TAI Labs certificate of completion after successfully completing the bootcamp.

Private community + instructor access

Get access to a private community channel where you can ask questions and interact with the instructors throughout the course.

Lifetime access to course materials

Keep lifetime access to the course materials, recordings, and future updates after the cohort ends.

Maven Guarantee

Your purchase is backed by the Maven Guarantee.

Course syllabus

Week 1

Aug 28—Aug 30

Claude as a Platform + Prompt Engineering & Context Management

4 items

Week 2

Aug 31—Sep 6

Week 2 — Model Context Protocol

4 items

Schedule

Live sessions

12 hrs

Eight live sessions across four weeks, with one hands-on build session and one architecture session each week. Each session is 1.5 hours and focused on building and designing production Claude agent systems.

Testimonials

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
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
Not only are the instructors experts in their field, they are 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 is 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