← back to examples
ai intermediate

Runic Adaptive Researcher

Dynamic two-phase Runic workflow that hot-swaps between full and slim writing DAGs based on deterministic research richness.

primary showcase ai l2 ai-tool-use runic adaptive

Related guides and notebooks

Tutorial
AI agent with tools
Build tool-aware workflows and orchestration loops.
Livebook
AI agent with tools
Run the companion notebook in Livebook
Source
adaptive demo source
Two-phase adaptive runner script.
Source
adaptive researcher module
Dynamic phase selection and runic.set_workflow usage.
Explanation

What this example teaches

Interactive Demo

Run the agent and inspect state

Source Code

Read the production implementation

Runic Adaptive Researcher
Real deterministic phase selection with `runic.set_workflow` swapping between full and slim writing DAGs
status: idle
Phase 2
pending
Workflow
phase_1_research
Summary Length
0
Threshold
180
Topic presets
Selected Topic
Incident Retrospective Narrative
Timeline of the customer-facing latency regression · Operational tradeoffs between rollback and mitigation · Signals that show whether the incident is stabilizing
Phase Selection
Run the selected topic to inspect the research summary length and chosen phase-2 workflow.
Phase 1 Research DAG
2 node(s)
plan_queries
AgentJido.Demos.RunicAdaptiveResearcher.Actions.PlanQueries
idle
simulate_search
AgentJido.Demos.RunicAdaptiveResearcher.Actions.SimulateSearch
idle
Phase 2 Writing DAG
awaiting selection
The adaptive phase-2 graph appears after the research results select the next workflow.
Article Output
Run the adaptive workflow to inspect the final article artifact.
Takeaway
The adaptive takeaway appears after the writing workflow completes.
Execution Log
0 entry(s)
Each executed node records its workflow, input payload, and result here.
Activity
0 note(s)