Module 0
✓
Foundations
Python-for-agents essentials, Git and env hygiene, and the one-page ML mental model every later lesson assumes.
AskAiml Academy · Intermediate to Advanced
Agentic AI Engineering
A ground-up course on building AI agents that ship: LLM APIs and prompting, RAG with hybrid search, single- and multi-agent orchestration in LangGraph, MCP servers and A2A, evaluation, guardrails, fine-tuning, serving, and deployment. Ends with a specialisation track and a capstone.
- 7 modules
- 33 lessons
- 4h of reading
- 5 projects
0%
complete
- Lessons done
- 0 / 33
- Badges earned
- 0 / 7
- Certificate
- Not yet earned
Curriculum
7 modules, from primitives to production
Every module ends in a quiz. Pass it to earn the badge. Pass the final exam to earn the certificate.
Module 1
✓
LLM APIs & prompting
Call the major LLM APIs, get structured JSON back, give the model tools, and keep tokens (and bills) under control.
Module 2
✓
Retrieval-augmented generation
Ground answers in your data: embeddings, vector databases, chunking, hybrid search, reranking, and honest evaluation.
Module 3
✓
Single-agent systems
The agent loop, LangGraph state machines, memory, tools, and the reliability and observability that make it shippable.
Module 4
✓
Multi-agent systems
When one agent is not enough: supervisor and swarm patterns, CrewAI, MCP servers, A2A, deep agents, n8n, and DSPy.
Module 5
✓
Production
Evals, guardrails and the OWASP LLM Top 10, observability and cost, fine-tuning, self-hosted serving, and CI/CD.
Module 6
✓
Specialisation & interview prep
Pick a specialisation track for your capstone, then use the interview workbook — system design, coding drills, and behavioural — to land the role.
- Specialisation tracks — pick one and ship the capstone
- Interview prep — system design templates
- Interview prep — coding drills
- Interview prep — behavioural stories and resume lines
4 lessons
Start
Reading only
Achievements
Collect a badge per module
Badges unlock as you pass each module quiz. The final exam issues a verifiable certificate you can share.
- Foundations specialist
- LLM APIs & prompting specialist
- Retrieval-augmented generation specialist
- Single-agent systems specialist
- Multi-agent systems specialist
- Production specialist
- Certified Agentic AI Engineer
Portfolio
5 projects that prove you can build it
Reading is not evidence. Each project is a deployable system you can put in front of an interviewer.
RAG-powered KB chatbot — "Ask Our Docs"
Ingest a real documentation set, ship a chat UI, and prove quality with a RAGAS evaluation.
Multi-tool LangGraph agent — "Personal Assistant Pro"
A single agent with calendar, email, search, and RAG tools, plus tracing and human-in-the-loop approvals.
Multi-agent crew with MCP and A2A — "Research Studio"
A supervisor plus specialists that share tools over MCP and coordinate through A2A messages.
Fine-tuned open model served via vLLM — "BYO LLM"
Fine-tune a small open model with QLoRA, serve it on vLLM, and benchmark against the closed baseline.
Specialisation capstone — your differentiator
A polished, end-to-end project in your chosen track with evals, cost dashboards, and a public write-up.