During this bootcamp you will design, build and deploy two real enterprise AI agents that remember users, read documents, talk to external systems and run 24/7 on AWS. A production system live at a real public URL.
Barcelona Code School
Since 2015 / 500+ graduates
AI Agent Engineer Bootcamp in Barcelona Code School
Prepare for "AI agent engineer" roles
On campus or remote live
Course format
Full-time
- 4 weeks, 40 hours/week, 160 hours total
- Monday–Friday, 9:00–18:00
- Morning theory, afternoon you build
- On campus in Barcelona or remote live
Part-time
- 6 months, 6 hours/week, 160 hours total
- Monday, Wednesday, Thursday, 18:30–20:30
- On campus in Barcelona or remote live
- Taught in English
- Prerequisites: familiarity with Python or other programming language, using APIs, CLI.
- Industry-recognised certificate upon completion
- Career counseling and job support
Part of Barcelona Code School's AI engineering track — practical skills, real tools, production code from day one.
What makes this different
- Projects: one continuous project + capstone project of your choice
- You work with the tools professionals use. LangGraph, LangSmith, PostgreSQL, ChromaDB, Docker, AWS — the actual stack employers ask for, not simplified stand-ins.
- AI-powered development from day one. You work with Claude as your coding assistant. Learning to work effectively with AI-generated code: reading, testing, owning it — is a core skill of the course.
- Production is the target, not a bonus chapter. Security, cost optimisation, monitoring and deployment.
The tech stack
- LLMs: GPT, Claude, Gemini — you work with all three
- Frameworks: LangChain, LangGraph — state machines, graphs, multi-agent orchestration
- Monitoring: LangSmith — tracing, evaluation, hallucination detection
- Databases: PostgreSQL, Supabase, SQLite, ChromaDB (vector search)
- Integrations: HubSpot / amoCRM, Google Calendar, WhatsApp Business API, Telegram Bot API
- Auth: OAuth 2.0
- Protocols: MCP (Anthropic), A2A (Google)
- Deployment: Docker, AWS EC2 + ECR, nginx, CloudWatch
- Cost optimisation: GPTCache, model routing, token budgeting
- IDE: Claude for AI-powered development
Skills you will gain
- Design agent architectures from scratch — ReAct, Plan-and-Execute, multi-agent coordination
- Build multi-turn agents with persistent memory and database backends
- Implement RAG pipelines — ingestion, chunking, vector search, source citation, quality evaluation
- Orchestrate multi-agent systems with LangGraph, including human-in-the-loop checkpoints
- Connect agents to real enterprise systems: CRM, Calendar, WhatsApp, custom APIs
- Deploy to production on AWS with monitoring, alerting and cost controls
- Protect agents against prompt injection and scope creep
- Evaluate and debug agent behaviour with LangSmith
- Work efficiently with AI-assisted development in Claude — reading, verifying and owning AI-generated code
Who is this bootcamp for?
A typical student is a developer who wants to specialise in AI engineering to stay relevant for the "AI-first" and "AI-agent" engineer roles.
Or someone from a technical background who has been watching the AI agent space and decided it is time to get in properly.
After the bootcamp
You graduate with two working enterprise agents in production and a portfolio that shows real engineering decisions.
The AI agent engineering market is moving fast. Companies are hiring people who can build these systems right now, not in two years when university programmes catch up.
Become prepared for positions like AI agent engineer AI integration developer, Conversational AI engineer, Automation engineer.
You will also leave knowing how to cost and evaluate the agents you build — a practical skill that separates engineers who ship production systems from those who only demo them.
Enroll now.
Tuition
2900€
Paid at registration.
Instalment payments are available at the checkout by 
September 1, 2026
AI Agent Engineer Bootcamp
8 weeks, 40 hours/week, 320 hours total
Monday–Friday, 9:00–18:00
On campus in Barcelona or remote live
6 students per group max — spots fill fast
Get the full syllabus
FAQ
What Python level do I need?
Basic is enough — variables, functions, libraries, HTTP requests. You do not need to have built anything with AI before. The first module covers everything you need to start working with LLMs.
Is the online track the same as in-person?
Yes. Both tracks attend the same live sessions simultaneously, see the same instructor screen, and do the same hands-on builds in real time. Same sessions, same price.
What computer do I need?
Any Mac or Windows laptop made in the last five years. The heavy compute runs on cloud services — your machine just needs to run Cursor and a browser.
Are there costs for the tools and APIs?
Yes. During the course you will use paid APIs — OpenAI, Anthropic, Google — and AWS services. Expect to budget roughly 50–100€ over the 8 modules for API and cloud costs. We teach cost management as part of the curriculum so you keep this under control.
What happens to the agent I build?
It is yours. It runs on your own AWS account. There are no ongoing fees to Barcelona Code School.
What if I miss a day?
Recordings are available. That said, this is a hands-on bootcamp — the practical work done in sessions is where the real learning happens. We recommend attending live wherever possible.
What is the language of instruction?
English.
Do I need to prepare anything before the course starts?
Yes. Before the first session we will send you setup instructions (accounts to create, tools to install) and a short Python refresh to complete. It takes 2–3 hours and makes sure everyone starts day one at the same level.
Is there a certificate?
Yes. An industry-recognised Barcelona Code School certificate upon completion of the bootcamp and the final project.
Inquiry about the bootcamp
Some of the companies where our graduates work or have worked
