Skip to content
Cadre
Agent packs

Markets · Agent pack

New pack

Market-surveillance adjudication

Cadre pack · Tribunal

Weighs the strongest manipulation and legitimate-trading cases before returning a disposition or referral.

Demonstrated on representative cases. Source coverage, thresholds, policy interpretation, escalation design, and performance require institution-specific validation.

Operating dossier

The job, permitted decisions, and owner

Mandate

Reviews flagged trading episodes by developing and testing manipulation and legitimate-trading hypotheses before issuing a disposition.

Case arrives with
Case ID
Allowed outcomes
Substantiated · Unsubstantiated · Refer
Where it fits
Trade Surveillance
Decision logic
  1. 01Reviews a flagged trading episode by developing both a manipulation hypothesis and a legitimate-trading hypothesis before forming a view.
  2. 02Tests the strongest case each way, then checks both sets of claims against the supplied orders, executions, and timestamps.
  3. 03Confidence on either side carries no weight without support in the episode record.
  4. 04The error costs cut both ways — a wrong substantiation falsely accuses a trader, a wrong clearance lets manipulation through — so genuinely contestable episodes are referred for senior review rather than forced to a verdict.
  5. 05Where the evidence is clear, the pack is designed to issue a disposition rather than refer by default; every disposition cites the specific orders, executions, or timestamps it rests on.
Must not
Invent missing evidence or act outside the permitted outcomes.
Human owner
Contestable evidence and senior review
Evidence retained
Structured outcome, observed path, and the source evidence used.

Case and record

One case, from supplied evidence to recorded decision

Supplied case

Representative case dataSynthetic or simulated data
Case ID
EP-SPOOF
View the case data

Case key spoofing-substantiated

{
  "caseId": "EP-SPOOF"
}

Recorded path and outcome

Cadre reference capture

One frozen, sanitized path through representative data. It is an inspection aid, not a performance claim.

Observed path

  1. Get episode

  2. Recorded the structured decision

  3. Argue prosecution

  4. Recorded the structured decision

  5. Argue defence

The full record continues on the capture page.

Recorded outcome

Substantiated

Verdict

Open decision record

Evaluation and limits

Evaluation coverage and stopping points

Published evaluation map

Expected decisions, boundaries, and costly failure modes.

These cases show what the pack is asked to decide, when it should stop, and which plausible errors the evaluation is meant to expose. They are not a reliability score or independent validation.

Expected and borderline behavior

Routine judgments, close calls, and named stopping points.

  • Large layered orders near the touch cancelled as price moves, extreme order-to-trade ratio

    substantiated.

    Case key

    spoofing-substantiated
  • Genuine large parent order worked over time; fills track the prevailing price, no self-matching. Superficially resembles layering

    unsubstantiated.

    Case key

    legit-parent-order-unsubstantiated

Boundary and misuse cases

Plausible inputs that could produce a costly or overconfident decision.

  • Genuinely contestable

    sell quotes cancelled near the touch before buys filled (a layering signature), but a modest order-to-trade ratio, cancels coinciding with a real upward tick, and genuine two-sided risk support a legitimate-trading interpretation. Neither interpretation clearly carries the evidence, so the disciplined disposition is refer; a confident substantiation here is the costly error.

    Case key

    ambiguous-refer

Operating fit

Workflow placement and validation

Operating pattern

Test both sides before deciding

Build the strongest evidence-based case on both sides before making a consequential judgment.

Decision sequence and workflow placement
  1. 01Build the case for
  2. 02Build the case against
  3. 03Verify citations
  4. 04Weigh error costs
  5. 05Rule or refer

Wider workflows

Trade Surveillance·Episode adjudication
Pattern guide

Institution-specific validation

These questions remain open until the pack is fitted to an institution.

Validation questions
  • Policy and legal interpretation
  • Source coverage, quality, and freshness
  • Thresholds and exception calibration
  • Integration and degraded-mode behavior
  • Human approval and escalation design
  • Performance on the institution’s own case mix
Inputs, actions, and outcomes
Give it
  • Case ID
It does
  • Get episodeget_episode
  • Argue prosecutionargue_prosecution
  • Argue defenceargue_defence
  • Rulecommitrule
It returns · Verdict
  • Substantiated
  • Unsubstantiated
  • Refer
Related packs

Related packs

Trade surveillance monitoring

Also in Trade Surveillance · Lookout