Skip to main content

Structured LLM Brief

Learning goals​

Run structured AI analysis with explicit cost and secret requirements.

Quick reference: Level 4; intermediate; output type structured_brief; estimated cost: provider-dependent.

Architecture​

Text alternative: The graph contains FlowBeads/input, LLMBeads/LLMProcess, FlowBeads/output. It accepts public input and returns a public result.

Prerequisites​

None.

Connections​

None.

Secrets​

  • One supported LLM secret

Build and run​

  1. Select a model and secret.
  2. Run the analysis fixture.
  3. Inspect output and usage metadata.

Use this fixture in the Test panel:

Analysis prompt
Summarize the risks and next steps in launching an AI support workflow.

Expected result​

  • structured brief is returned
  • usage is visible when provided

Open the persisted run and verify the node timeline. Browser sinks appear in the Inspector; public output appears in the run result when enabled.

Side effects and cost​

This Braid has no external side effect.

Cost: provider-dependent. DataBraid stores summaries and structured errors, not secret values.

Extensions​

  • Change the fixture and compare the node-level timeline.
  • Add a Data Probe before the final output.
  • Save a known-good fixture for regression testing.