Skip to content
Dr. Ram KumarDiabetes & metabolic health

Medical AI · Track 7 of 10

Agentic AI

LLM agents that use tools and take steps: tool calling against FHIR data, multi-agent workflows, MCP, guardrails and human oversight.

RAG track recommended first.

By the end of this track you should be able to

  • Explain what makes a system agentic and what new risks that adds
  • Give an agent safe, read-only tools over FHIR data
  • Design multi-agent workflows with a human in the loop
  • Evaluate agents on task success and safety, not just answer quality

Lessons

  1. Agents and tool use

    Coming soon

  2. Tool calling against FHIR data

    Coming soon

  3. Multi-agent clinical workflows

    Coming soon

  4. MCP and tool servers

    Coming soon

  5. Guardrails and human-in-the-loop design

    Coming soon

  6. Evaluating agents

    Coming soon

Lessons in this track are being written and reviewed. In the meantime, start with the Foundations track.

Next track: Evaluation, safety & deployment

Educational content only. This material teaches methods; it is not clinical advice. Code, models and examples here are not validated medical devices and must not be used to make decisions about real patients without proper clinical validation, governance and any required regulatory approval. Examples use synthetic or openly licensed de-identified data only. Never paste identifiable patient information into public AI tools. Mentions of models, tools or vendors are for identification, not endorsement.