Step 1 · AI
Prompt Engineering Foundations
A friendly, practical start: clear prompts, thinking modes, files and images, and a personal library of 50+ prompt patterns
Learning path · Free
Build, evaluate and ship production AI: APIs, RAG, agents, MCP, evals, security and open models
Step 1 · AI
A friendly, practical start: clear prompts, thinking modes, files and images, and a personal library of 50+ prompt patterns
Step 2 · AI
Context engineering, structured outputs, thinking controls, tool and agent prompts, caching, evals and optimisation for production
Step 3 · AI
Production-grade integration of Claude, OpenAI, Gemini, cloud platforms and open models: formats, tools, cost, reliability, security
Step 4 · AI
From expert prompting to Projects, Artifacts, agentic tasks, Skills, connectors, Claude Code and API integrations, safely
Step 5 · AI
Embeddings, RAG, context engineering, tool calling, agents, MCP and the open agent standards, with hands-on code
Step 6 · AI
Design, build, secure and ship MCP servers and clients that connect Claude, ChatGPT, IDEs and agents to real business systems
Step 7 · AI
Design, build, secure, evaluate and ship AI agents that work reliably with real tools, data and people
Step 8 · AI
Ship reviewed, tested code with Claude Code, Codex, Copilot and Cursor: context engineering, guardrails, CI and governance
Step 9 · AI
Evals, LLM-as-judge, RAG and agent evaluation, CI regression suites and OpenTelemetry-based observability in production
Step 10 · AI
Threat-model, attack and harden LLM apps and agents using OWASP, MITRE ATLAS and NIST guidance, garak, PyRIT and promptfoo
Step 11 · AI
Licenses, model families, quantization, VRAM sizing, Ollama, llama.cpp, vLLM, edge AI, privacy and hybrid routing
Step 12 · AI
When not to fine-tune, data curation, SFT, LoRA/QLoRA, DPO, GRPO, distillation, embeddings, evaluation, cost and deployment
Step 13 · AI
Design, build, test and launch voice agents with ElevenLabs, OpenAI Realtime and telephony, in English, Arabic and Urdu
Step 14 · AI
Build, secure and govern AI agents that see screens, click, type and audit websites, with humans in control
Nothing is locked: take the courses in order or jump to the ones you need. More courses are added to this path as they are published.