Healthcare AI Learning
All visual guides

Guide 05From Prompt to Agent

A practical ladder from one-shot generation to bounded agentic workflows.

Six levels of AI system design, what chooses the next step at each level, and the controls each level requires.

A4 sheet — scroll sideways or pinch to zoom

Visual Guide 05 · GenAI / Agentic / Builder

From Prompt to Agent

A practical ladder from one-shot generation to bounded agentic workflows.

Healthcare AI Learning

LevelWhat it isWho chooses the next stepTypical useHealthcare exampleMain control need
1PromptOne request, one model response.User or system defines the task.One-off generation or rewriting.Rewrite a patient-facing explanation from supplied text.Input and output review.
2LLM applicationPrompt plus UI, bounded context and output formatting.Software defines the task shape.Repeatable single-step tasks.Structured summarisation assistant.Output validation and formatting rules.
3Context / RAG-enabled applicationRuntime retrieval supplies relevant information to the model.Retrieval logic is defined by software.Answers that need current, private or approved sources.Retrieve approved guideline sections before drafting an answer.Source allowlist, grounding checks, provenance.
4Tool-enabled AIThe model or app can call defined external functions and services.Model may select from a defined tool set.Tasks needing data lookup, calculation or actions.Retrieve a FHIR Observation, calculate a score, create a draft task.Tool allowlist, permissions, argument validation.
5Fixed workflowSteps and branching are primarily predefined by software, with model or tool calls inside.Software chooses the sequence.Known, repeatable multi-step processes.Intake → retrieve → summarise → validate → human review.Deterministic sequence, checkpoints, audit trail.
6Bounded agentic workflowThe system can choose and sequence at least some steps or tool use toward a goal, within explicit boundaries.System chooses within permissions and stopping rules.Tasks that genuinely benefit from iteration and feedback.Gather approved context, choose allowed tools, check quality rules, escalate when required.Permissions, stopping conditions, logging, escalation, monitoring.

More agentic ≠ better. Use the simplest architecture that safely meets the task.

Common misconceptions

  • “Tool use means it is an agent.” Not necessarily — fixed workflows use tools too.
  • “A workflow is an agent.” Not necessarily — predefined steps are not self-directed.
  • “An agent is fully autonomous.” Not in this learning platform’s bounded definition.
  • “Multi-agent is more advanced, so better.” Not inherently; it adds failure modes.
  • “Agentic systems remove human oversight.” No. Oversight and escalation stay required.
Healthcare AI Learning · Visual Guide 05Updated Sep 2026

Summarises the sources cited in the related Healthcare AI Learning courses: Building GenAI Applications in Healthcare, Agentic AI in Healthcare. Updated Sep 2026; regulatory content checked between 25 August and 10 September 2026. Educational summary only — not legal or clinical advice.

Related learning

Building GenAI Applications in HealthcareOpen
Agentic AI in HealthcareOpen

Guides summarise the same primary sources cited in the related courses — official EU legal texts, standards bodies and peer-reviewed literature. Educational summaries only, not legal or clinical advice; regulatory dates were checked between 25 August and 10 September 2026.

Updated Sep 2026