Officiating & Odds-Adjustment AI Agent

What this agent does

Two pipelines, and no join between them

Where the deployment is officiating, ingest venue tracking and the competition's own definition of the line or zone.

Where it is odds adjustment, ingest market state and the feeds the licensee has approved.

Reason

When an output is produced, carry the tolerance band its tier permits with it.

Where a market is new, it is filed and approved by the licensee, not the agent.

Where the rules give the official the final word, the output is advisory, not determinative.

Decide

When an automated decision affects one customer, they can contest it.

Where separation is claimed, it is a test case, not a promise.

Out

Retain the output, the band it carried, the version and who acted, inside its own deployment.

Execute write actions only inside the approval boundaries agreed during implementation.

→ Product statement

The agent measures or prices; a match official or a licensee's trader decides, and the competition's rules say which of them is bound.

Example workflow

One event, in one deployment

AgentHuman

1Event input receivedVenue tracking, or the licensee's approved market feed

2Rules assembledThe competition's line or zone definition, or the operator's filed house rules

3Output proposedA measurement or a price move, its band and confidence

4Controls appliedTolerance-band checks, separation checks, filed-rule checks and the confidence threshold

No human action required

Stages 1 to 4 run unaided inside one deployment, and nothing is decided at any of them — the official's or the trader's lane opens at the gate.

5DecisionBranches at the tolerance band

Outside the band

Goes to the official or the trader on duty.

Inside the band

Arrives marked unresolved, with no value.

Official or trader

The output arrives with its tolerance band, its version and the confidence.

Accept · Override · Suspend the feed

Accepted — acted on by a person▼

6Match or market record updatedOnly where write access and approval policy allow it

7Outcome evaluatedOverride rate, band breaches, suspensions and what the person found

Overrides

Every override is counted in the evaluation.

What should not run autonomously

Human approval stays in control

Outside the boundary — human approval required8 items

Making the call the competition's laws give a person.

Setting the line, the zone or what counts as out.

Bringing a new wager type to market.

Deciding whether a wager stands or is voided.

Automation boundaryAgent acts unaided

✓Produce the measurement or the price move, and the band it carries.

✓Run in one deployment, and test for a path to the other.

✓Apply the definitions or house rules already filed.

✓Hand it to the official or the trader on duty, and log who acted.

Any write happens inside the boundaries agreed at implementation, never ahead of a person.

Deciding one customer's limits, offers or restrictions.

Ruling that a match or a market was affected.

Reporting suspicion to a regulator or a governing body.

Changes to tolerance bands or approval boundaries.

Example output

One measurement, annotated

Everything the agent outputs carries the definition it was measured against.

Officiating output · single callIllustrative example

Competition

Measured event

Output type

Definition used

Confidence

Authority

Tennis, live line calling

Ball impact rebuilt from the calibrated camera set

Fitted path

Governing-body line

91%

Chair umpire, determinative

As receivedTaken from the officiating deployment — the trading deployment keeps its own, and a join is a tested case.

What was used Calibrated camera set The filed line definition Per-frame positions

Why it carries a bandIt is a trajectory fitted to camera data, not a photograph of the impact.

ActionAcceptOverrideSuspend the feed

What the score decidesInside the configured band the agent returns unresolved, and the person calls it unassisted.

Value

Where AI adds value

The same four claims, placed at the point in the workflow where each one applies.

Where the value landsValue 01 – 04

Every eventInside one deployment

03Assistance

Work to the filed definition

Work from the definitions the governing body set, or the house rules the operator filed.

01Approved path

Two deployments, never one pipe

The officiating agent and the trading agent are built, deployed and run apart.

02Human review

Send the close ones to a person

A call inside the band arrives unresolved rather than as a value, so attention goes where it is close.

04Build an evidence trail

The measurement, its tolerance and the official or trader who acted on it stay on the record.

Integrations

Typical integrations

Five system groups connect to the same agent. Which of them are in scope is decided in discovery.

Officiating deploymentOptical ball tracking
Video review · replay desk

Competition rulesLaws, playing conditions
Match and event records

Odds deploymentTrading platform
Approved market feeds

Agent

Two agents, deployed apart

Reads its own side
Proposes with a band
Hands to a person

Compliance and integrityRegulator filings
Integrity reporting

Observability & evaluationOpenTelemetry · Langfuse
Supported monitoring/evaluation sources

Integration availability depends on the client's existing systems and API access.

Agent controls

Six layers between the model and the call

The layers nest, and the two deployments do not share one. What escapes is named below.

L6 · Outermost — last line of defenceInward → L1 · closest to the model

L6Rollback / safe modeRevert to unassisted operation, and say so to the person, when signals degrade.Roll back

L5Version monitoringTrack model, prompt, tolerance-band and definition changes.Track

L4TraceabilityRecord the output, the band it carried, the version and who acted.Record

L3Official or traderHold the output for the official or the trader; it governs who acts, not whether the act was right.Gate

L2Separation guardrailsTest each deployment against its filed rules and for a path to the other; a failure stops the output.Restrict

L1Tolerance thresholdsReturn unresolved rather than a value when the call sits inside the band.Require review

Model coreOutput produced — a measurement or a price move, its band and confidence

L1 – L2Test whether an output may stand

L3Puts the act in a person's hands

L4 – L5Hold the measurement and the tolerance it carried

L6Reverts to unassisted operation when signals degrade

How Nestack evaluates it

Evaluate the whole assist — not only the number at the end.

Coverage runs the whole depth of the workflow, and every layer is cut by slice.

Surface — the call or the price that goes out

Depth of coverage ▼

E1Final-output evaluationDid the output sit inside the band its tier permits?

E2Step-level evaluationDid the agent use the right definition, version and filed rules?

E3Tool evaluationDid it read and write only its own deployment's systems?

E4Confidence calibrationDo low-confidence outputs actually attract more overrides?

E5Slice evaluationHow does performance change across competitions and market types?

E6Business outcomeHow many outputs were overridden, and how many were suspended?

Floor — what the league or the licensee answers for

Failure modes

Where each failure originates in the agent

Seven failure modes, each at the stage it starts.

Agent lifecycleDirection of processing →

01 · Retrieval1 mode

OD-03

Superseded definition

The zone or line definition is read from a stale version.

Stage gathersTracking or market state, and the definitions on file

02 · Reasoning2 modes

OD-04

Certainty overstated

A fitted trajectory is reported as though it were observed.

OD-06

Unfiled rule applied

A price moves on a rule the operator never filed.

Stage proposesA measurement or a price, its band and confidence

03 · Tool / write2 modes

OD-02

Acted without a person

Agent completes an act a person owed the decision on.

OD-05

Cross-deployment path

Venue knowledge reaches the trading side.

Stage writesOnly where write access and approval policy allow it

04 · Output1 mode

OD-01

Undetected system state

Nobody is told the assist is off, degraded or unreset.

Stage returnsThe call the official makes or the price that posts

05 · Change / Version1 mode

OD-07

Silent band regression

A model or rule change widens what the agent will assert.

Stage tracksModel, prompt, tolerance bands and filed definitions

Sev-1 · a path opens between deployments Sev-2 · a wrong value reaches the decision Sev-3 · input degrades, the assist stands down

See the complete Sports & Fitness failure-mode catalogue →

Affected slices

One cohort carries most of the overrides

Take an aggregate override rate apart before trusting it: split it by cohort, and by deployment, because a small number of hard cohorts carry most of the overrides in both.

Slice performance — reported separately, not only in aggregateIllustrative example

Slice	Failure rate	Lift	Status
Occluded and crowded incidents	9.1%	3.7×	Review
Single-action micro-markets	5.4%	2.2×	Review
Restarts after an interruption	3.7%	1.5×	Watch
Clear, settled cases	1.5%	0.6×	Normal

Bar: override-rate lift vs. clear-case baseline · scale 0–4.0× · tick marks the 2.0× review threshold 2 of 4 slices over threshold

Evidence-linked improvement

A cycle ends in a test, not a meeting

Nothing closes on a review meeting. It closes on a case the next release has to pass, and that suite is what the next output either side is measured against.

Improvement cycle · five stagesSwitchback — the path turns at Improve and returns at Learn

01Detect

Override rate rises in one cohort.

02Diagnose

If the band held, the fault is in the definition, the version or the hand-off.

03Improve

Every change ships against a version with the incidents attached.

04Verify

The release is blocked while an affected case fails.

05Learn

The case becomes permanent, and the separation controls are re-tested.

Learn → DetectThe return edge. The next detection runs against a suite one case longer.

Typical build scope

Twelve workstreams across six weeks

The build scope read against the delivery timeline. Week structure follows the six-week plan — discovery, sources, output workflow, evaluation, integration, then production validation and handover.

Workstream Week 1Week 2Week 3Week 4Week 5Week 6

01Deployment separation and boundary definition.

02Venue and market-feed source assessment.

03Definition, tolerance band and house-rule mapping.

04Input ingestion and normalisation.

05Output logic and tolerance binding.

06Confidence scoring and unresolved routing.

07Official or trader workflow.

08Per-deployment system integration.

09Separation and tolerance cases.

10Guardrails and approval controls.

11Decision-trail instrumentation.

12Deployment, documentation and Agent Care handover.

12 workstreams · 6 weeks · bar shows the weeks a workstream is active — several run in parallel Final scope and sequence confirmed in discovery

Engagement tiers

What each tier includes

Rows are the capabilities named in each tier's scope. Higher tiers include everything below them.

Capability✓ in scope · — not at this tier PilotOne competition or book ProductionProduction deployment AdvancedMultiple competitions / books

Introduced at Pilot

Output to your filed definitions✓✓✓

Separation, and a human decision✓✓✓

Measurement-consistency baseline✓✓✓

Introduced at Production

Reporting by competition and market—✓✓

Decision workflow in your systems—✓✓

Approved write-back—✓✓

Trading-platform integration—✓✓

Introduced at Advanced

Multi-competition rule sets——✓

Multi-desk trading approvals——✓

High event volume——✓

Multi-jurisdiction filing controls——✓

Build price From $5,000 From $8,000 Custom quote

Final build priceConfirmed after discovery based on integrations, workflow complexity, transaction volume, approval controls and deployment requirements.

Separate from buildBuild pricing is separate from recurring Agent Care, which covers managed monitoring, evaluations, incidents and verified improvements after launch.

What we need from you

What you bring, and what we build with it

Each input maps to a piece of build scope and a week in the delivery timeline.

You bringWe build with it

01Your filed definitions or your house rules → Input ingestion and definition mappingWeek 1

02Representative events from one deployment → Output baseline, band binding and version stampingWeek 2

03Your tolerance bands and who signs them → Definition, tolerance band and house-rule mappingWeek 1

04Access to relevant APIs, feeds or exports → Venue and market-feed assessment, then integration setupWeek 2

05Calls and prices you would not want repeated → Separation cases and failure-mode testingWeek 4

06What a measurement is never allowed to decide → Confidence scoring, unresolved routing, guardrails and separation controlsWeek 3

07Named officials or traders to act on it → Decision workflow, then pilot and production validationWeeks 5–6

Nothing else is required Deployment, documentation and Agent Care handover are ours.

Delivery timeline

Four phases across six weeks

The bands sit on the weeks the work occupies, so the fifth carries evaluation and launch together.

Phase W1W2W3W4W5W6

Discovery W1

Build W2 – W3

Evaluate W4 – W5

Pilot & Launch W5 – W6

Week focus W1Deployment separation, definition mapping and the automation boundary W2Source integration and the output baseline W3Output workflow, tolerance logic and decision controls W4Evaluation suite, separation tests and failure-mode testing W5Per-deployment integration, pilot events and targeted corrections W6One competition round run under the officials or the trading desk, then handover

Reading the bandEach bar covers only the weeks its work is named in. The fifth week carries two kinds of work.

At the end of W6The round closes validation and Agent Care picks up monitoring.

DurationSix-week plan shown · typical delivery 4–6 weeks depending on scope confirmed in discovery.

Next step · Sports & Fitness agent

Build one deployment, on its own side of the line.

Tell us which side you are on — a competition's officials, or a licensed book's desk. Your governing body signs the definitions, or your licensee files the house rules; we build to one of them.

Discuss this agent →

Nestack Agents · Officiating and odds adjustmentAGT-SF-13 · Agent Care available after launch