Set the working context
Choose the business, project goal, relevant knowledge, and the people responsible for reviewing the result.
AI Council
Use multiple specialist perspectives when one answer is not enough.
Assemble distinct roles around a complex question, compare their analysis, surface disagreement, and produce a decision-ready synthesis.
No code · review gates · work organized by business
druidx — ai-council
druidx run ai-council. loading business context. distinct-specialist-roles, assign different lenses, evidence responsibilities, or review duties to the council. shared-objective, keep every contribution focused on the same decision and deliverable. model-choice, use the models available to each configured specialist. evidence-gathering, bring web sources and workspace knowledge into the analysis when required. disagreement-visibility, preserve meaningful differences instead of flattening them into false consensus. 5 steps complete · output saved to Library.
review gates on, outputs keptSee plans →
Make multiple-agent collaboration useful by giving each perspective a clear role and one shared decision.
Asking several models the same vague question creates repeated text, not better judgment. An effective council divides perspectives, preserves evidence, and synthesizes disagreement around a defined business decision.
Everything the run needs, built in.
6 capabilitiesDistinct specialist roles
Assign different lenses, evidence responsibilities, or review duties to the council.
Shared objective
Keep every contribution focused on the same decision and deliverable.
Model choice
Use the models available to each configured specialist.
Evidence gathering
Bring web sources and workspace knowledge into the analysis when required.
Disagreement visibility
Preserve meaningful differences instead of flattening them into false consensus.
Final synthesis
Produce one structured recommendation with findings, uncertainty, and next steps.
From business context to finished work.
The objective, the execution, and the outputs stay connected, so nothing gets rebuilt in the next tool.
Configure the capability
Select the appropriate agents, models, tools, connectors, and boundaries for the work.
Run, review, and retain
Inspect progress and outputs, answer questions or approvals, and keep the useful result in the workspace.
What you walk away with.
Useful outputs your team can open, share, and build on — not another stream of chat.
- Multiple relevant perspectives on one business question.
- Clear division of evidence and review responsibilities.
- Disagreement preserved for human judgment.
- A structured synthesis instead of repeated model answers.
- The final decision brief retained as a reusable deliverable.
Where teams point it first.
Focused project work
Apply the capability to a concrete business outcome with visible context and a defined deliverable.
Reusable team workflow
Configure the approach once, then bring it into future projects without rebuilding every instruction.
Governed automation
Use the capability inside a larger workflow with explicit logic, timing, and human review where required.
Your next move
Give your next business goal a place to get done.
Set up a workspace, add the context that matters, and let your AI team turn the goal into reviewed, reusable work.