Products
Collective Reasoning Foresight Knowledge Agent Collective IQ
Company
Trust & Governance Results Developers Science

Product — Collective Reasoning Foresight

See ahead together.

A structured session where people and AI agents contribute judgments, explain their reasoning, evaluate one another's ideas, and develop a measurable collective view.

The result is not only a report — it is a persistent evidence-and-reasoning record that shows what the group thinks, why, where it agrees and disagrees, which ideas are most relevant, which arguments carried influence, and how the collective view changed as participants interacted.

Elicitation and social evaluation. Evolving ideas. Thinking together.

Passive extraction is valuable but bounded by what is already written and by the assumptions baked into the source. A session adds active elicitation and structured peer review on top.

Passive extraction from text
Collective Reasoning Session
Retrieves what documents contain.
Elicits what people and agents currently believe.
Treats the corpus as the knowledge boundary.
Adds tacit knowledge, judgment, and new hypotheses.
Produces a model-generated answer to a query.
Builds a traceable network of the collective reasoning process — a model of the collective mind.
Often gives one answer; may flatten minority views.
Preserves competing perspectives and structurally important dissent. Identifies points of disagreement, where constructive friction drives creativity.
Usually a static snapshot.
Tracks change, convergence, and relevance over time. Provides a complete audit trail of reasoning.
Evaluates text through model similarity.
Combines semantics with human and agent peer review.

Agents augment the group; they never replace accountable human judgment

Teams can add Knowledge Agents grounded in private documents to bring vertical expertise to the table. The system is fully agentic, allowing integration of human reasoning with agent inputs — but the accountable decision stays with people.

A five-stage learning cycle

A session runs as a facilitated, analyzable process. Participants receive the same framing but contribute their own positions first, before seeing others — preserving informational diversity and reducing conformity.

1

Context & elicitation

Facilitator sets prompts, materials, and participants; each contributes an independent position.

2

Proposition formation

Each response becomes attributable propositions that can be cited, reviewed, and analyzed.

3

Peer review

Intelligent sampling routes a diverse subset to each reviewer, forming an interaction graph.

4

Collective analysis

Relevance recalculates as reviews arrive; ideas rise by connection, not volume.

5

Synthesis & action

Rankings, graphs, convergence, and Collective Voice support the decision.

Structured interaction, not a transcript. Reviewers don't just read — they agree, disagree, request more information, comment, rate quality or novelty, indicate whether they would cite an idea, and rank by priority. Important ideas rise because they connect strongly with the group's reasoning — not because they were submitted early, repeated often, or written confidently.

Quantitative, qualitative, or hybrid

Quantitative

Estimates, forecasts, likelihoods, scored judgments. Feeds the Bayesian Belief Network and shows the distribution of estimates.

"Probability we ship by Sep 30?"

Qualitative

Open-ended inquiry with no forced number. Emphasizes themes, diversity, semantic distribution, relevance, and bridge ideas.

"What risks are missing?"

Hybrid

A measurable judgment paired with the reasoning to interpret it — estimate, explain, challenge, recommend.

Score + rationale

Six new capabilities that an Large Language Model cannot provide

Captures tacit knowledge in the context of a specific decision

The useful knowledge in experience, expectations, and local context — the kind that never made it into a file.

Capture multiple perspectives on a decision

Peer review, priority, citation, and graph position give signals beyond writing style.

Preserves disagreement

Distinct propositions and estimates keep dissent visible instead of editing it into a smooth narrative.

Creates new knowledge (capture serendipity)

Bridge propositions and cross-source synthesis emerge only through interaction — co-created, not merely extracted.

Makes reasoning auditable

The chain from participant → proposition → review → ranking → result is preserved; agent citations trace to source documents.

Capture and remember the reasoning process

The interaction pattern itself reveals fragmentation, convergence, influence concentration, and unresolved uncertainty.

Many lenses on one reasoning process

No single metric is treated as the collective truth. Each analytic answers a different question, and updates as participation continues.

What resonates & idea rankings

Relevance scores rank propositions by how they connect to the evolving review network, with rising / stable / falling trend.

Collective Voice

A conversational interface over the session's reasoning: "where do humans and agents disagree?" Answers trace to their propositions.

Bayesian Belief Network

Collective probability, weighted causal nodes, sensitivity analysis, outcome recording. A decision-support model, not proof of causality.

Relevance & influence

Which ideas shape the conversation and which participants supply reasoning others use. Influence is network position, not authority.

Convergence, free energy & entropy

Whether the group is stabilizing or still exploring, and whether uncertainty is organizing or diversity collapsing too fast.

Knowledge graph & spectral

Clusters, bridge propositions, centrality, isolated nodes, and the spectral shape of the network — similarity, citation, causal modes.

Analytics support judgment; they don't replace it.

Three ways to build one

Session Builder

Guided, conversational design: describe the decision, provide materials, refine framing with the Builder agent, generate a draft.

New · complex questions

From Scratch

Configure directly — title, mode, prompt sequence, seeds, agents, participants, privacy — then save and launch.

Experienced · well-defined

From Template

Start from a private, system, or community template with pre-built prompts, then customize context and agents.

Recurring · standardized

Chat-to-Session and API

Curate threads from Slack, Teams, WhatsApp, or Notion into seed propositions — turning an informal discussion into a structured evaluation without losing the ideas that started it. Developers can create and launch sessions through the REST API, embedding them in workflows, community apps, and decision-support systems. See the developer docs →

A short checklist

1

Define the decision, not just a topic

What it informs, who uses the result, what uncertainty needs reducing.

2

Design neutral, specific prompts in sequence

A strong hybrid pattern is estimate → explain → challenge → recommend.

3

Select for diversity, not headcount

Different information, roles, and experience. Choose agents for a defined contribution.

4

Add context and seeds carefully

Enough to start, not so much that the group anchors. Distinguish evidence from hypotheses.

5

Review in the green room, then launch

Activating agents and sending participant invitations.

Typical use cases

Strategic planning · risk management · research synthesis · product and innovation discovery · policy and community consultation · forecasting and calibration · post-incident learning.

Search finds what is already known. A session helps a group determine what it should believe and do next.

Run your first session.

Build a session, invite your team, add a Knowledge Agent. Tell us what you need.

Contact us