12 missions. Zero hidden.
This is the exact curriculum of the AI-Native Software Development Programme - every project, every checkpoint, every tool. No “request the syllabus” form. Read it all, then try the first missions free on Sigmo, the learning portal our students use every day.
We revise it as the field moves. This November 2026 edition keeps one language, JavaScript, from your first line of code to production, then goes where AI-native teams work today: LLMs, prompt and context engineering, RAG, agent harnesses, MCP, tracing and evals with Langfuse.
Phase 1 · Missions 1–3
Programming Foundations
JavaScript, the DOM, Git and APIs from zero. Build, debug and explain real web apps, including one with the AI switched off.
Phase 2 · Missions 4–7
Full-Stack Engineering
React, Express and PostgreSQL with real auth, then tests, CI, AI code review and a live deployment. You grow one recruitment platform the whole way.
Phase 3 · Missions 8–10
Applied AI & Agents
LLMs, prompt and context engineering, RAG, a hand-built agent harness with MCP, and the tracing and evals that make AI reliable.
Phase 4 · Missions 11–12
AI-Native Capstone
Two weeks to build your own AI-native app, then ship it to production and defend it live, including an unseen task.
Phase 1 · Programming Foundations
- Mission 1
Build an Interactive Personal Website
I can build an interactive web page with HTML, CSS and JavaScript, and explain how the browser runs my code.
Read the mission
- Mission 2
Build an Interactive Task Manager
I can build a CRUD app with the DOM, validate user input, persist data, and manage my code with Git and GitHub.
Read the mission
+1 - Mission 3
Build an API-Powered Search App
I can fetch and display live API data with async JavaScript, handle failures gracefully, and debug with DevTools instead of guessing.
Read the mission
Phase 2 · Full-Stack Engineering
- Mission 4
Build a Job Board Frontend in React
I can build a component-based React app with state, forms and data fetched from an API.
Read the mission
- Mission 5
Build a Recruitment API with Express & PostgreSQL
I can design a database-backed REST API with SQL, validation, error handling and a clean structure.
Read the mission
- Mission 6
Build an Authenticated Full-Stack Recruitment Platform
I can build secure login, sessions and permissions across a full-stack React, Express and PostgreSQL app.
Read the mission
- Mission 7
Test, Review & Deploy the Recruitment Platform
I can independently modify, debug, test and deploy an authenticated React, Node.js and PostgreSQL app.
Read the mission
+3
Phase 3 · Applied AI & Agents
- Mission 8
Build an AI Recruitment Assistant with RAG
I can build a reliable LLM feature with prompt and context engineering, structured output, basic RAG and tracing.
Read the mission
+1 - Mission 9
Build an AI Recruitment Agent with Tools & MCP
I can build a bounded, controllable AI agent with tool calling, MCP and human approval, and explain exactly how the loop works.
Read the mission
+2 - Mission 10
Make the Agent Reliable: Tracing, Evals & Safety
I can find why an AI agent misbehaves, fix it, and prove the fix with repeatable evaluations.
Read the mission
Phase 4 · AI-Native Capstone
- Mission 11
Build Your AI-Native Capstone
I can scope and build a full-stack, AI-native application end to end, using coding agents responsibly.
Read the mission+5 - Mission 12Final
Ship, Document & Defend Your Capstone
I can build, understand, modify, debug and maintain conventional software and AI-powered features, and defend my decisions live.
Read the mission
+1
After Mission 12: optional self-study
The 12 missions teach each tool to the depth a job needs, and no deeper. Going further is your call: these self-paced tracks are being added one by one, and nobody is required to do them all.
Career Readiness · coming soon
- TypeScript - Types, interfaces, generics, TypeScript with React and Node
- Data Structures & Algorithms - Recursion, stacks, queues, searching, sorting, trees
- Computer Science Fundamentals - Memory, operating systems, networks, concurrency, database internals
- Advanced React - React Router in depth, Next.js, advanced hooks, performance
- System Architecture - Hetzner, Bash, Docker, virtual machines
- Software Architecture - SOLID, design patterns, system design, caching, queues
- Python - Python, FastAPI, Pydantic, asyncio
Specialisation · coming soon
- Advanced RAG & Context Engineering - pgvector, hybrid search, reranking, context compression
- Advanced Harness Engineering - OpenAI Agents SDK, LangGraph, agent orchestration
- MCP Server Development - Building MCP servers, transports and authorization
- Advanced Evals - LLM-as-judge, custom evaluators, benchmark design
- Cloud & DevOps - Docker, Linux, AWS, Kubernetes, Terraform
- ML & Deep Learning - PyTorch, transformers, fine-tuning
Mastery-based, not time-based.
Every mission has one required project and one clear standard to pass, and ends with a recorded walkthrough where you explain what you built. The rule is simple - if you can’t explain it, you can’t submit it. You move to the next mission when you’ve mastered this one, not when a week runs out.
Prefer to explore it as a game? The same 12 missions are playable as a tiny RPG at /missions. And the first projects are free to actually do - not just read - on the free trial.
And if you just want the lessons: the whole free beginner course is published in full at /learn, every lesson readable without an account.
Don't read the curriculum. Do it.
The free trial puts you inside Sigmo, the same learning portal our students use daily - starting with 6 Projects in 6 Days. No card needed.