Skip to main content
Consilium is a hypothesis evaluation engine that assembles a panel of AI domain experts and runs a structured, multi-round debate around your research question. Instead of a single model answering in isolation, multiple specialized agents argue, cite literature, challenge each other, and converge toward a refined hypothesis — all grounded in real evidence from PubMed, ChEMBL, Reactome, UniProt, and other databases.

​
Why use Consilium

A single AI response can sound confident while missing critical angles. Consilium solves this by:
  • Multi-perspective analysis — Each agent evaluates your hypothesis through a different scientific lens (molecular biology, genetics, structural biology, drug discovery, bioinformatics).
  • Evidence grounding — Agents search real databases and cite papers, structures, and pathways. Every claim is backed by verifiable references.
  • Structured argumentation — Rounds follow a deliberate progression: literature grounding, position statements, cross-examination, synthesis pressure, and convergence.
  • Transparent disagreement — Unresolved tensions and minority dissent are surfaced explicitly rather than hidden behind a single answer.

​
Creating a new debate

Navigate to Consilium in the sidebar and click New Debate.

​
Step 1: Define your hypothesis

Enter the research question or hypothesis you want to evaluate. This is the central claim that agents will argue for or against. Be specific — a focused hypothesis produces sharper debate. Good examples:
  • “Loss-of-function variants in PCSK9 are protective against coronary artery disease through LDL receptor upregulation”
  • “The p.V600E BRAF mutation drives melanoma progression primarily through the MAPK/ERK signaling pathway”
  • “Combining CDK4/6 inhibitors with endocrine therapy improves progression-free survival in HR+/HER2- breast cancer”
You can optionally add a title. If you leave it blank, one is generated from your hypothesis.
Write your hypothesis as a testable claim, not an open-ended question. “Does BRCA1 matter?” is too vague. “Biallelic BRCA1 loss-of-function drives homologous recombination deficiency in triple-negative breast cancer” gives agents something concrete to evaluate.

​
Step 2: Experiment canvas (optional)

Provide additional context to help agents ground their analysis in your specific research setting: This canvas is shared with all agents to scope their arguments appropriately.

​
Step 3: Select your agent panel

Choose 2 to 8 domain experts from the available presets: Each agent comes with a predefined persona and evaluation lens. You can customize the name, color, and persona if needed. A Moderator agent is added automatically. It does not argue for or against the hypothesis — instead, it synthesizes each round, identifies tensions, and decides when the debate should fork or converge.
You need at least 2 agents to start a debate. For thorough evaluation, 3 to 5 agents with complementary perspectives work best.
Click Start Debate to begin. The debate transitions from configuration to active execution.

​
How the debate runs

Once started, the debate progresses through structured rounds. Each round has a specific purpose:

​
Round types

​
What you see during the debate

The debate page uses a three-panel layout:
  • Left panel — Debate graph: A visual map of the round progression. Click any round node to filter the feed to that round’s statements.
  • Center panel — Live feed: Real-time stream of agent statements as they are generated. Each statement shows the agent’s stance, key findings, agreements, conflicts, and cited evidence.
  • Right panel — Summary: Tabbed view with four sections (see below).

​
Summary panel tabs

Overview — Shows the original and refined hypothesis side by side, agent consensus breakdown (stacked bar chart of support/conditional/neutral/oppose), and round progress. Findings — Surfaces unresolved tensions (points where agents disagree and could not reconcile) and minority dissent (positions held by only one or two agents that the majority rejected). Literature — Aggregated, deduplicated list of all evidence cited across all rounds and agents. Searchable and sorted by quality score. Each citation shows the source database, star rating, validation status, and which agent cited it. Agents — Grid of all participating agents with their role, evaluation lens, color, and active/eliminated status.

​
Intervening during a debate

You are not a passive observer. While a debate is running, the intervention bar at the bottom of the feed lets you steer the discussion: You can also:
  • Advance to the next round manually if you want to skip ahead.
  • Pause the debate to review findings before continuing.
  • End the debate at any time.
Use the challenge intervention when you notice all agents converging too quickly — it forces them to reconsider assumptions and often surfaces overlooked evidence.

​
Understanding the output

When the debate completes (or converges), the summary panel contains the full output:

​
Refined hypothesis

The moderator produces a refined version of your original hypothesis that incorporates the strongest evidence and arguments from all agents. The Overview tab shows both the original and refined hypothesis in separate blocks so you can compare exactly what changed.

​
Agent consensus

A stacked bar chart shows how agents voted in the final round:
  • Support (green) — Agent believes the hypothesis is well-supported by evidence.
  • Conditional (yellow) — Agent supports the hypothesis with caveats or qualifications.
  • Neutral (gray) — Agent found insufficient evidence to take a position.
  • Oppose (red) — Agent believes the evidence contradicts the hypothesis.

​
Unresolved tensions

Key disagreements that the panel could not resolve. These are the most valuable output for planning follow-up experiments — they point to exactly where the evidence is insufficient or contradictory.

​
Minority dissent

Positions held by one or two agents that the majority rejected. These are worth reviewing carefully — minority positions in scientific debates sometimes turn out to be correct.

​
Literature evidence

Every citation from every agent, deduplicated and quality-scored. Each entry includes:
  • Source database (PubMed, PDB, ChEMBL, Reactome, UniProt)
  • Star rating (1-5) based on evidence quality
  • Validation status
  • Which agent cited it and in which round
  • Direct link to the original source

​
Filtering and navigation

  • Filter by agent: Click the colored agent dots in the header to show only that agent’s statements.
  • Filter by round: Click a round node in the left graph panel to jump to that round in the feed.
  • Search literature: Use the search bar in the Literature tab to find citations by title, source, journal, or type.

​
Managing debates

The Consilium page lists all your debates with:
  • Status badge (configuring, running, paused, converged, completed, etc.)
  • Participating agents (shown as colored dots)
  • Round progress
  • Token usage
  • Creation date
Use the search bar to find debates by title or hypothesis. Click the archive button to hide completed debates from the list without deleting them.
Archived debates are not deleted — they are hidden from the default view. You can still access them if needed.

​
Use cases

Set your hypothesis to a specific mechanism (e.g., “CFTR p.F508del causes cystic fibrosis through protein misfolding and ER retention, not channel gating defects”). Agents will debate the mechanism using structural data, functional studies, and clinical evidence, producing a nuanced view of the variant’s impact.
Before investing in a drug discovery program, use Consilium to debate whether a target is druggable, selective, and clinically relevant. Agents from drug discovery, structural biology, and bioinformatics will surface risks that single-perspective analysis might miss.
When published studies disagree, frame the conflict as a hypothesis and let agents argue both sides with citations. The literature tab aggregates all relevant papers in one place, and unresolved tensions highlight exactly where the evidence is ambiguous.
Before submitting a pre-registration, run your hypothesis through Consilium to identify weaknesses, missing controls, and alternative explanations. The refined hypothesis output can directly inform your pre-registration document.