Skip to content
Cohort BootcampEngineers & technical builders

Agentic AI Engineering Bootcamp

Five live sessions, capstone-as-spine. Pick one project you care about and add a layer each session - reliable reasoning, RAG, agents, TRACE evals, memory - then sprint to Demo Day with the Builders cohort. Coding-agent-first: Cursor and Claude Code write the code; cohort time goes to systems thinking, judgment, and what actually breaks in production.

5 sessions + build sprint
Coding-agent-first
Capstone-as-spine
Certificate on completion

Taught by Dr. Akshika Wijesundara, PhD · SnapDrum / The AI Internship

Programme at a glance

FormatLive sessions + async Deep Dives + office hours
Duration5 live sessions + 2-week build sprint + Demo Day
Assignments1 per session, building toward the capstone
CapstoneYour own agentic AI project - reasoning, RAG, agents, TRACE evals, memory, then deploy
Primary toolsCursor, Claude Code, FastAPI, LangGraph, MCP, TRACE evals, Hermes, GBrain
CertificateIssued on capstone completion and Demo Day showcase

Introduction

What is AI engineering?

AI engineering is building reliable products on top of frontier models you did not train - grounding them in your data, giving them tools, measuring whether they work, and shipping something that holds up when real users touch it. Coding agents write most of the code; your job is systems thinking and judgment.

Read the full introduction in pre-course

Start with a step-by-step guide to what AI engineering is, then install your coding agent and get ready for Session 1.

What you keep

A clear mental model of AI engineering - reliability around models you did not train - plus a working coding-agent workflow.

You ship

Cursor or Claude Code installed, GitHub + OpenAI key ready, and a capstone one-liner before the first live session.

Async

What is AI engineering? (start here)

A step-by-step guide: what AI engineering is, what we assume, what we teach, and what to do next before Session 1.

Read lesson
Async

Software components for beginners

APIs, REST, POST, FastAPI, Docker, scaling, and the other building blocks Session 1 assumes. Plain-English map for newcomers.

Read lesson
Async

Install Cursor or Claude Code (do this next)

Pick one AI coding agent, install it, open a project folder, and confirm you can chat with it. This is the highest-leverage pre-course step.

Read lesson
Async

Python, Git, and API keys

Let your coding agent check Python, create a venv, and scaffold FastAPI. Create a GitHub account, add your OpenAI API key, and keep secrets out of chat.

Read lesson
Async

Seed your capstone

Pick the one project you will build across five live sessions - your Session 1 `/ask` endpoint is its first capability.

Read lesson
Async

Building in public

Why we share builds openly, where to post (LinkedIn, Substack, share it), and how to talk about the skills you learn.

Read lesson
Async

Pre-session check-in

Share your setup status and capstone one-liner before Session 1.

Read lesson
Async

Session 1 checklist

What you must have ready before the first live session - and what is fine to finish during or after it.

Read lesson

What you keep

How to turn a model call into a dependable, observable piece of software - plus context engineering, token optimisation, and a free-resources bridge to mastery.

You ship

A working `/ask` endpoint that answers reliably, plus a Streamlit UI that demos it - the reasoning core of your capstone.

Live

From model call to reliable component

Production means the right shape, at a known cost, with a plan for when it fails - every time.

Read lesson
Live

The OpenAI API and the Playground

Experiment in the Playground first: system vs user messages, temperature, max tokens, and the token counter.

Read lesson
Async

Module 1.1 - Build your first LLM service

Stand up a real POST endpoint with typed models before any theory - the living thing everything else improves.

Read lesson
Async

Module 1.2 - Prompting that ships

Structured outputs, few-shot, and decomposition - three techniques to make output deterministic enough to build on.

Read lesson
Async

Module 1.3 - Output guardrails and validation

Schema, semantic, and safety validation - plus retry patterns - between the model and everything downstream.

Read lesson
Async

Module 1.4 - Token economics and context budgets

Tokens are money and latency. Treat the context window as a budget, not free space.

Read lesson
Async

Module 1.5 - Choosing the right model

Match capability, cost, and latency - and route different steps to different models in one system.

Read lesson
Async

Module 1.6 - Context engineering: the throughline

Prompting, cost, and model choice are all facets of one skill: engineering what the model sees.

Read lesson
Deep dive

Module 1.D1 - Advanced structured outputs and function-calling schemas

Nested schemas, enums, and function calling - when the shape must be airtight and feed code directly.

Read lesson
Deep dive

Module 1.D2 - The provider landscape beyond OpenAI

Anthropic, Gemini, open-weight models - per-task fit and portability across providers.

Read lesson
Async

Module T - Token Optimisation

Nine concrete techniques to cut cost and latency without trading away quality you need.

Read lesson
Async

Module B - Mastering AI Engineering: the free-resources bridge

A curated map from bootcamp graduate to self-directed mastery - almost everything is free.

Read lesson
Async

Session 1 assignment support: Ship Your First AI Endpoint

A grouped guide with copy-paste prompts for the basic Session 1 submission (including Streamlit UI), plus optional add-ons.

Read lesson

Make your /ask endpoint answer from your documents, not training data. Running example: Northwind Robotics policy corpus throughout.

What you keep

How to make a model answer from your data instead of its training, and why naive RAG fails - plus Claude Code skills, MCP, and eval habits that make the build repeatable.

You ship

Week 1 /ask extended with a vector store, POST /ingest for new docs, RAG query with citations + refusal, a Streamlit UI for ingest + ask, and a golden-set eval on your live Render URL.

Live

Embeddings intuition

Similar meanings sit close together in vector space - retrieval quality depends on this mental picture.

Read lesson
Live

Build naive RAG, and watch it fail

Embed, store, retrieve, stuff into prompt - then break it instructively on the Northwind corpus.

Read lesson
Live

Chunking

How you split documents decides what retrieval can find - most bad RAG is bad chunking.

Read lesson
Live

Reranking and hybrid search

Reranking reorders candidates by relevance; hybrid search catches exact terms embeddings miss.

Read lesson
Live

RAG evals

Measure retrieval and generation separately - wrong chunks vs right chunks ignored.

Read lesson
Deep dive

Graph RAG

When knowledge has structure and relationships, plain vector RAG leaves value on the table.

Read lesson
Deep dive

Multimodal RAG

Retrieve over images, tables, and diagrams - not just prose.

Read lesson
Deep dive

Chunking video for multimodal RAG

Video chunking is two independent decisions - where to cut, and what to put in each chunk - and getting either wrong is the one RAG mistake no reranker fixes.

Read lesson
Async

Claude Code layers - skills, MCP, subagents, and plugins

One reference for which layer does which job: CLAUDE.md, skills, MCP, subagents, hooks, plugins.

Read lesson
Async

Session 2 assignment support: RAG on your Session 1 endpoint

A grouped guide with copy-paste prompts for the basic RAG submission (including Streamlit UI), plus optional retrieval add-ons.

Read lesson
Assignment

Session 2 homework: RAG on your Session 1 endpoint

Extend POST /ask with basic RAG: ingest text, retrieve before generation, cite sources, refuse when docs are missing, and ship a Streamlit UI.

Read lesson

What you keep

What an agent really is, how to build the loop by hand, and how to ship one on Google ADK (with LangGraph as an accepted alternative for explicit graph control).

You ship

Your assistant turned into an agent that plans and uses tools, plus a Streamlit UI that demos the loop.

Live

The agent loop, by hand with the raw SDK

Think, pick a tool, call it, observe, decide again - no framework mystification.

Read lesson
Live

Orchestration with LangGraph

Nodes, edges, shared state - durable execution and human-in-the-loop checkpoints.

Read lesson
Live

Tools and MCP

MCP is how modern agents get tools - connect to servers instead of hand-wiring every integration.

Read lesson
Live

Multi-agent and A2A

Several specialists when roles are genuinely separable - most problems do not need multiple agents.

Read lesson
Live

Prompt injection, where guardrails get dangerous

Malicious instructions in retrieved content can hijack tool-using agents.

Read lesson
Deep dive

Build your own MCP server

Tools, resources, and prompts, then a real Python FastMCP server you can wire into Claude Code today.

Read lesson
Deep dive

Build your own A2A integration

Agent Card, skills, and tasks - a minimal A2A server and the client call that reaches it.

Read lesson
Deep dive

LangGraph in depth

Reducers, Command routing, subgraphs, checkpointers, time travel - what the live session does not have time for.

Read lesson
Deep dive

Agent security mitigations

Least privilege, human-in-the-loop, structural separation of instructions from content, sandboxing, and an audit trail.

Read lesson
Async

Session 3 assignment support: Turn your capstone into an agent

Step-by-step: pick the job, build a Google ADK agent with one real tool and a Streamlit UI, prove Think → Act → Observe, then optional stretch (LangGraph accepted as alt).

Read lesson
Assignment

Turn your capstone into an agent

Google ADK agent with at least one real tool and a Streamlit UI - trace each step of the decision loop. LangGraph accepted as alternative. Stretch: HITL, MCP, A2A.

Read lesson

What you keep

The full TRACE loop as a system you build - Trace, Read, Analyze, Codify, Enforce. Code assertions first; validate every LLM judge with TPR/TNR.

You ship

An eval suite your capstone runs against, visible from a Streamlit UI.

Live

The vibe-check trap

"It works on the examples I tried" is not evaluation - and for non-deterministic systems it is dangerous.

Read lesson
Live

Trace and Read: error analysis

Capture full records, then read traces by hand - qualitative research on real failures.

Read lesson
Live

Analyze: cluster, count, prioritize

Binary pass/fail judgments, ranked by frequency and impact - the spec for your eval tooling.

Read lesson
Live

Codify: build the eval suite

Code-based assertions plus validated LLM-as-judge - an unvalidated judge is just another vibe check.

Read lesson
Live

Enforce: evals in the loop

Wire evals into the development loop so every change gets measured automatically.

Read lesson
Live

Evaluating agents: trajectories, not just final answers

A polite final message can hide a wrong tool call, a silent retry loop, or an action that never actually happened.

Read lesson
Deep dive

Aligning an LLM-as-judge to human labels

The actual calibration workflow: blind labels, held-out validation, TPR/TNR, and re-validating after every model change.

Read lesson
Deep dive

Agent trajectory and world-state grading

Score the path the agent took and what actually changed in the environment, not just what it said.

Read lesson
Async

Session 4 assignment support: Build and run TRACE on your capstone

Path A: traces, taxonomy, code assertions, one fix, Streamlit. Path B: validated judge, goldens, CI sketch.

Read lesson
Assignment

Build and run TRACE on your capstone

Trace, read, analyze, codify, and wire evals to run on demand - show a metric moving after a fix.

Read lesson

What you keep

How to give an agent memory that lasts and improves, and how to run it persistently.

You ship

Your agent remembering across sessions and deployed to run for real, with a Streamlit UI that demos memory.

Live

The memory spectrum

Working, semantic, episodic, and procedural memory. Match the store to the job.

Read lesson
Live

Graph plus vector hybrid memory (and gbrain)

Vector recalls by similarity; graph recalls by relationship. Hybrid earns its cost when both matter.

Read lesson
Live

Compaction, write gates, and durable execution

Context fills up. Compaction loses rules. Writes need gates. Checkpoints are not full durability.

Read lesson
Live

Persistent runtime deployment

From "I built an agent" to "I deployed an agent": stays up, holds memory, ready for Demo Day.

Read lesson
Live

Skills and the compounding loop

Procedural memory you can write down: capture a process once, and the agent gets better at it every time after.

Read lesson
Live

Course wrap and your capstone from here

Reasoning, RAG, agents, evals, memory - the full arc, what carries forward, and where the capstone goes after Demo Day.

Read lesson
Deep dive

Rolling your own memory store

A real, minimal memory store: Postgres + pgvector, a write gate, hybrid retrieval, and an actual forgetting policy.

Read lesson
Deep dive

Skills authoring patterns

A skill is only as good as its trigger. Structure, scope, and how to actually test one before you trust it.

Read lesson
Async

Session 5 assignment support: Give your capstone memory and deploy it

Path A: durable store, cross-session recall, public URL, UI proof. Path B: graph, consolidation, provenance, crash drill, LLM wiki.

Read lesson

No new teaching. Two weeks to finish so your system ships instead of stalling.

What you keep

A demo-ready brief, a rehearsal habit (including a recorded backup), and a production checklist.

You ship

A publishable capstone URL, a 5 to 10 minute Demo Day walkthrough plan, and proof that memory, evals, and the core task still work for a stranger.

Live

Build-support office hours

Bring a concrete blocker: a failing eval, a flaky tool, a deployment error, or a memory write bug.

Read lesson
Async

Final system brief and production-readiness checklist

From working to demo-ready: one-page brief, 5 to 10 minute walkthrough, recorded backup, ship checklist.

Read lesson
Async

Final portfolio brief and ship checklist

The production-readiness checklist gets your system demo-ready. This gets your capstone interview-ready.

Read lesson

Mandatory live system + URL. Optional presentation. 5 to 10 minutes if you present.

What you keep

A public trail of your capstone and a story you can reuse in interviews.

You ship

Submitted live URL (mandatory). Optional 5 to 10 minute presentation with problem, architecture, stack, and live or recorded demo.

Live

Demo Day

Submit live system + URL (mandatory). Present the grounded, agentic, evaluated, memory-holding stack (opt-in).

Read lesson

Course resources

Week 1 live session
Week 2 live session
Foundations
Week 3 live session

Agents: raw loop, Google ADK (default assignment), MCP, multi-agent / A2A, prompt injection. ADK and LangGraph docs plus the Week 3 session deck.

Evals (TRACE)
Week 5 live session
Capstone build sprint and Demo Day

AI Engineering learning resources

A curated reference for students. Every link is a primary source or a practitioner-written guide, favouring free material where possible.

AI Engineering - Roadmaps
AI Engineering - Foundations (transformers from scratch)
AI Engineering - Free structured courses
AI Engineering - Evals for engineers

Start with pre-course

Install your coding agent, set up Python and GitHub, seed your capstone, and read the session modules below when you are ready to go deeper.

Pre-course lessons