Course 4 · Advanced
Autonomous Agents & Vector RAG Systems
12 hours · 3 sessions × 4 hours · Max 6 participants
A vector-grounded autonomous pipeline with retrieval, tools, specialist agents, provenance, usage controls, and production acceptance tests.
Who should attend
Intermediate and advanced developers, software engineers, and technical product architects.
Where and how
- In person in Haiphong, Vietnam.
- English-language delivery.
- Bring your own laptop and build as you learn.
- Open groups and private B2B cohorts available.
What we cover
Session 1 — Tool Calling & Vector DB — Use native function calling, local embeddings, vector similarity, Qdrant or Chroma administration, and native RAG.
Session 2 — Multi-Agent State Graphs — Build agent loops with LangGraph or CrewAI patterns, supervisor/worker flows, and multi-step processing.
Session 3 — Deployment & Optimization — Add cycle aborts, specialist routing models, token thrift, telemetry, FastAPI health/run endpoints, and validation.
You will learn to
- Build native function-calling routers.
- Create embeddings and understand similarity and top-K behavior.
- Ingest and query a local vector database.
- Build RAG from first principles.
- Orchestrate supervisor/worker state graphs.
- Add abort rules, usage ledgers, health checks, and production validation.
Investment
- B2C
- 8,500,000 VND / person
- B2B private cohort
- 42,000,000–58,000,000 VND / private cohort
Cloud and API use can be included as a capped allowance or billed at cost.
Completion
Attend, complete the assessment, and finish the capstone. We will give you a course completion certificate.
For private cohorts, we can adapt the examples to a cleaned-up company use case after a short technical call.