Skip to content

Ship AI systems that hold up in production.

For developers. Build with model APIs, retrieval, agents and MCP, prove it works with evals, and deploy it with tests, tracing and cost controls.

Coding agents make bad engineering faster. This school teaches the engineering that makes AI systems correct, safe and cheap to run.

Who this school is for

A developer drawing a diagram on a whiteboard

Working developers

Backend, frontend and mobile engineers who want to build LLM applications properly, not as demos.

CS and engineering graduates

Graduates who can code and want a portfolio of deployed AI systems that employers can inspect.

Technical career changers

People with some Python or JavaScript who want to move into AI engineering. If you are not ready yet, we will point you to Python for AI first.

What you build here

Projects use African data and problems by default: mobile money, central-bank circulars, local languages, patchy connectivity.

An experienced engineer in his fifties and a younger colleague working through a problem side by side

A structured-output API

A service that turns messy WhatsApp order messages into validated JSON, with tests and token accounting.

A RAG system with evals

Retrieval over public central-bank circulars, with an eval suite of at least fifty cases and a score report.

A tool-using agent

A finance assistant that checks exchange rates, calculates budgets and drafts reports, with clear limits.

An MCP server

A Model Context Protocol server that exposes a business system safely, with permissions.

A voice or document app

Receipt-to-expense parsing, or a voice FAQ in Pidgin or Swahili, with latency measured.

A deployed capstone

A brief from Boltcliq, a hiring partner or your own idea: spec, build, eval, deploy and demo.

Start building today.

Free projects, roadmaps and challenges in Labs.

Your path through the school

A young man working through equations on a whiteboard
  1. 01Free

    Labs

    Free projects on the AI Engineer roadmap.

  2. 02Free

    Masterclass

    The Builders track: RAG and an agent in one weekend.

  3. 031 to 4 weeks

    Short Courses

    AI Coding for Developers, AI Agents in a Week, AI Security Essentials.

  4. 0412 weeks

    Certificate in AI Engineering Foundations

    Twelve weeks, 8 to 10 hours a week, six deployed applications.

  5. 056 months

    Fellowship in AI Engineering

    Six months, hybrid, with a production capstone for a real organisation.

  6. 069 to 12 months

    FDE Residency

    Full-time and paid, on live Boltcliq engagements.

How we teach engineering

Evals are acceptance tests

An AI feature is not done until you can show, with a test set, that it works and keeps working.

Coding agents with discipline

You will use Claude Code, Cursor and similar tools. You will also plan, review and test what they write.

Security from week one

Prompt injection, data leakage and PII handling under African data law are part of the course, not an appendix.

You must understand your system

AI help is allowed and expected. A short technical conversation, the viva, confirms you can explain what you built.

Questions

A tutor leaning over a student's notes at a library table
  • Basic Python or JavaScript, Git and the command line. The Certificate starts with a short readiness quiz. If you are not ready, we will recommend Python for AI first, and that is a good outcome.

Fundamentals first. Then build things people rely on.

Start with a free project in Labs, or build your first AI solutions in the free Masterclass.

  • Learn by building, from the first session
  • Free to start
Join the academy

Fundamentals first. Then build things people rely on.

For developers. Build with model APIs, retrieval, agents and MCP, prove it works with evals, and deploy it with tests, tracing and cost controls.