Mode Canvas Click a block to jump to the setting that controls it · click an i for detail

Name Q:MODE

What is this mode for?

Defaults below mirror Quorum's own Balanced mode. Change what you need in Panel and Deliberation, then come back here for the name.

Mandate

Panel — who deliberates

Curate a specific engine pool, or let Quorum's live scoring pick the best available engines within your filters each run.

Pool strategy

Minimum access tier

Which tier can use this mode. If you pick a fixed pool with a frontier-only engine, this is raised automatically to match.

Deliberation — how they argue

Depth is the biggest cost dial. Critique policy controls whether seats challenge each other before the answer is finalized.

Depth

Round budget and per-seat token ceiling.

LightStandardDeepExhaustive

Resolves to 2 rounds · 1.0× tokens

Critique policy

The real maestro.policy field qroute.js reads -- three real values, not a spectrum.

Panel routing

After the seats answer, one judge scores how far apart they are. This decides what happens next — writes follow_up_min_divergence and polish_min_divergence.

Seats stating contradictory facts always go another round, whichever you pick.

Staff — internal roles

Pick which real engine plays each internal role for this mode. Leave on Default to use Quorum's shared staff. Candidates are filtered to engines compatible with what your panel already handles.

Synthesizerwrites the final answer

Judgepicks best seat

Pre-scorerclassifies difficulty

Mandate — domain grounding

This is where a mode stops being a parameter tweak and becomes a real product. Not built yet -- shown so the lever set can be reviewed before that work starts.

Injected context

Attach documents, a style guide, or a rubric the panel can reference.

📎 Requires document ingestion -- not built.

Jurisdiction

Grounding sources and injected regulation for a specific region.

⚠️ Requires a real regional grounding source -- not built.

Review before publishing

Nothing here is a performance claim. Those come from a certification run — a held-out-question test against your published listing, launched from the Certified stage in the rail once this mode has one.

Holdings

Engine	Family

Disclosure

Status: Draft, unpublished -- usable by you personally once saved. Not visible or usable by anyone else until published and approved.

Testing

Testing lives in its own tab above, so a run and the diagram it exercises stay on one surface.

Save the mode to unlock the test rig.

Share this canvas

Not published yet — this canvas has no public link. Publish the mode to mint one, and the QR below the diagram becomes real.

Certification runs a held-out question set against this mode and writes the badge a stranger sees. It needs a listing first: publish the mode, then launch the run from the Certified stage in the rail, which says what the run is before you press it, shows the score while it runs, and shows what it wrote when it finished.

Routing key

Forward

Fast lane — skips ahead

Loop — repeats the round

Open web — leaves the frame

Panel readout

What's real here

Every block is traced from the live routing code, and clicking one jumps to the setting that controls it. The three seats show their real brand shape always — only who is seated changes. While a test is running, the moving dot replays your most recently completed question's actual path and timing — including a second, smaller dot for Grounding on questions that really used it. It only reflects test runs from this rig, not live production traffic yet.

Live preview

Q:MODE

Untitled mode

Not saved yet

Engine pool

Dynamic -- picked live per run

Real config, not an estimate

Depth

Standard

2 rounds

Concentration

—

pick a fixed pool to see this

Ask AI about this mode

AI-generated, grounded in a real but partial slice of the engine catalog — verify against the picker before finalizing.

No cost or latency estimate shown. Depth and Concentration above are real, computed from what you've actually configured -- cost/latency would need real historical averages this Builder doesn't compute yet, so rather than fabricate a number, it becomes real once the mode has actual usage.

Who can use this

Saving a draft makes it usable by you, immediately -- try it in Chat. Publishing to the Marketplace (so anyone else can find and run it) needs a real admin approval first. Certification -- the held-out-question test behind a public performance claim -- launches from the Certified stage in the rail once this mode has a listing. The API route (POST /v1/certify) runs this same certification and pins the same card, billed to your organization.

ROUTED

RESOLVED

Mode Genie

Injected context

Jurisdiction