Multi-Agent Systems and MCP
40 hoursAdvanced5 modules
1 of 5 modules with a published syllabus
0 of 5 modules recorded
Syllabus
Brings together the four level-300 modules of the Agentic AI area — multi-agent systems and orchestration, planning/reflection/self-correction, MCP and integration with real systems, and agent security — with the module on evaluating AI systems. It presupposes the agent-building programme or equivalent.
Modules of this programme
The same objects as the full curriculum. A module opened from any programme that contains it is the same module, with the same syllabus and the same status.
| Code | Module | Content | Hands-on | Status | Price |
|---|---|---|---|---|---|
| AG-301 | Multi-agent systems and orchestration | Detailed syllabus not written yet | — | Syllabus published | |
| AG-302 | Planning, reflection and self-correction | Detailed syllabus not written yet | — | Syllabus published | |
| AG-303 | MCP and integration with real systems | Detailed syllabus not written yet | — | Syllabus published | |
| AG-304 | Agent security (prompt injection, sandboxing) | Detailed syllabus not written yet | — | Syllabus published | |
| CORE-304 | Evaluating AI systems | Benchmarks, LLM evals, A/B testing, red teaming | Build an eval suite for an application | Syllabus published | R$ 240US$ 80MX$ 1,000estimated price0 of 1 module published |
- AG-301Syllabus published
Multi-agent systems and orchestration
Detailed syllabus not written yet
- AG-302Syllabus published
Planning, reflection and self-correction
Detailed syllabus not written yet
- AG-303Syllabus published
MCP and integration with real systems
Detailed syllabus not written yet
- AG-304Syllabus published
Agent security (prompt injection, sandboxing)
Detailed syllabus not written yet
- CORE-304Syllabus published
Evaluating AI systems
- Content
- Benchmarks, LLM evals, A/B testing, red teaming
- Hands-on
- Build an eval suite for an application
R$ 240US$ 80MX$ 1,000estimated price0 of 1 module published
Not everything fits into 40 hours. State of the art, distributed training, interpretability, edge deployment and the five integrative projects exist only inside the complete tracks: Tracks