Publisher Yield & Supply-Chain Integrity AI Agent

What this agent does

Checks the record, not the decision to publish it

A seller file is pulled from every property — ads.txt, app-ads.txt and the ad server's record.

The SupplyChain object is read alongside it, as the payment path it shows and nothing more.

Reason

A declared seller is checked against the domain's own file and that counterparty's sellers.json listing.

A mismatch — a cloned file, a stale domain, an unlisted reseller — is flagged with its evidence.

A floor or yield change is drafted with the fill, price and reader trade-off it is projected to cause.

Decide

A direct-sold order is checked against ad-server delivery before any yield change is proposed.

Every flag, mismatch and floor change is routed to the named ops lead, never resolved alone.

Out

The file checked, the mismatch found and the ops lead's decision are retained against the property.

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

→ Product statement

The agent checks records and prepares evidence with the trade-off attached; the named ops lead decides what publishes, because the reader isn't in the auction.

Example workflow

One change, signal to publish

AgentHuman

1Signal receivedProperty refresh, floor-change request, direct-sold order or a spoofing alert

2Evidence assembledSeller files, sellers.json entries, delivery data and floor history, each with its source

3Change draftedRecord correction, floor or yield adjustment, flagged mismatch and confidence

4Controls appliedCross-file checks, trade-off log, spoof-pattern checks and confidence threshold

No human action required

Stages 1 to 4 run unaided, and nothing changes at any of them — the agent recommends, and the ops lead's lane opens at the confidence gate.

5DecisionBranches at the confidence threshold

High confidence

Goes to the ops lead to approve.

Low confidence

Adds a second review first.

Ops-lead review

The change is held with its evidence, its flagged mismatches and the confidence.

Approve · Edit · Escalate

Approved — published live▼

6Live systems updatedOnly where write access and approval policy allow it

7Outcome evaluatedRecord accuracy, flag outcomes, floor performance and post-publish corrections

Edits

Every ops-lead edit is counted in the evaluation.

What should not run autonomously

Human approval stays in control

Outside the boundary — human approval required8 items

Publishing any change to a live seller record.

Changing a floor price or yield rule.

Blocking or terminating a buyer or reseller.

Accepting or rejecting a direct-sold order.

Automation boundaryAgent acts unaided

✓Cross-check every property's authorised-seller file.

✓Read the SupplyChain object as payment-flow evidence, never as full technical custody.

✓Name the MFA taxonomy and version behind any classification it reports.

✓Flag a record mismatch or yield trade-off for the ops.

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

Asserting that inventory is fraudulent or spoofed.

Committing to a remedy outcome in the Google ad-tech case.

Adding a new authorised reseller to the file.

Changes to taxonomy definitions, floor policy or approval rules.

Example output

One seller-file check, annotated

Everything the agent flags is attached to the record it was drawn from.

Publisher-yield output · single propertyIllustrative example

Property

Finding

Record status

Evidence source

Confidence

Attribution

Mid-tier sports domain

Reseller present in ads.txt but absent from its own sellers.json listing

sellers.json: absent

This week's file crawl

88%

Ops-lead name on file

As receivedTaken from this week's ads.txt crawl and the counterparty's sellers.json — nothing on this side is written by the agent.

Records checked Live ads.txt crawl Counterparty sellers.json SupplyChain payment path

Why it's flaggedThe ads.txt file matches and a person still decides and it is logged..

ActionApproveEditEscalate

What the score decidesBelow the configured threshold the flag picks up a second review before it reaches the ops lead.

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 propertyFrom the seller-record feed

03Checking

Cross-check every property's file

Cross-check each domain's ads.txt against every counterparty's sellers.json entry.

01Approved path

A file is not a guarantee

ads.txt and sellers.json let buyers cross-check who may sell your inventory — nothing in either file stops a bad actor from cloning it wholesale onto a lookalike domain.

02Human review

Send review to the flagged mismatches

Cloned files, unlisted resellers and floor changes are marked, so the ops lead's read starts where risk concentrates.

04Build an evidence trail

The record, the source it was read from and the ops lead who published it stay on the domain.

Integrations

Typical integrations

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

Ad server & inventoryGoogle Ad Manager · Prebid
Xandr · Equativ

Seller-record filesads.txt · app-ads.txt
sellers.json · SupplyChain

Programmatic demandSSP and exchange feeds
Direct-sold order data

Agent

Publisher yield & supply-chain integrity

Reads the file
Flags the mismatch
Holds for the ops lead

Ops workflowTicketing · approval tools
Slack · email escalation

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 record

Each control wraps the one inside it. What the stack does not catch is named in the map below it.

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

L6Rollback / safe modeFall back to reporting only when evaluation or production signals degrade.Roll back

L5Version monitoringTrack changes to the model, prompt, taxonomy version and seller-file rules.Track

L4TraceabilityRecord the file checked, the mismatch found, the evidence and the ops lead's decision.Record

L3Ops-lead approvalHold the change for the named ops lead; it governs publish, not whether the record is accurate.Gate

L2Policy guardrailsTest every change against configured floor limits and seller-file rules; a failure returns it.Restrict

L1Confidence thresholdsRoute low-confidence matches and floor changes to a second ops review.Require review

Model coreRecommendation proposed — record check, floor evidence and confidence

L1 – L2Test whether a flag may stand

L3Puts the change in the ops lead's hands

L4 – L5Keep the record and the source behind it

L6Falls back to reporting only when signals degrade

How Nestack evaluates it

Evaluate the checking workflow — not only the final flag.

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

Surface — the record buyers see

Depth of coverage ▼

E1Final-output evaluationDid the flagged mismatch match the live seller-record files?

E2Step-level evaluationDid the agent use the current file, taxonomy version and floor history?

E3Tool evaluationDid it read the correct property and the correct counterparty file?

E4Confidence calibrationDo low-confidence flags actually attract more ops-lead escalations?

E5Slice evaluationHow does accuracy change across specific property types?

E6Business outcomeHow many flags needed an ops-lead correction after publish?

Floor — the outcome the publisher answers for

Failure modes

Where each failure originates in the agent

Seven failure modes, mapped to where the agent introduces each one.

Agent lifecycleDirection of processing →

01 · Retrieval1 mode

SY-03

Cached file snapshot

The seller file read is a cached copy, not this domain's live version.

Stage gathersSeller files, sellers.json entries, delivery data and floor history

02 · Reasoning2 modes

SY-04

Cross-taxonomy MFA claim

An MFA clearance from one vendor's taxonomy is reported as if every taxonomy agrees.

SY-06

Payment path read as full trail

SupplyChain data is read as the technical path, not just who gets paid.

Stage proposesRecord mismatch, evidence read and confidence

03 · Tool / write2 modes

SY-02

Parse failure misread

A sellers.json fetch error is treated as proof a partner is unauthorised.

SY-05

First-price model, hybrid path

A floor model trained on first-price data runs unadjusted against a second-price path.

Stage writesOnly where write access and approval policy allow it

04 · Output1 mode

SY-01

Trade-off omitted

A floor or fill recommendation reaches the ops lead with no reader-experience trade-off attached.

Stage returnsThe record and flag the ops lead approves

05 · Change / Version1 mode

SY-07

Silent taxonomy drift

An MFA taxonomy or model version update widens what the agent will flag as a match.

Stage tracksModel, MFA taxonomy version and it is logged.

Sev-1 · change published outside the boundary Sev-2 · a wrong flag reaches the ops lead Sev-3 · file degrades, flag routes to review

See the complete Advertising failure-mode catalogue →

Affected slices

Network health can hide one weak property

A network-wide record score can look clean while a handful of properties carry most of the defects. Nestack reports the record-defect rate by property, not only in total.

Slice performance — reported separately, not only in aggregateIllustrative example

Slice	Failure rate	Lift	Status
Newly acquired or migrated domains	7.6%	3.9×	Review
Inventory resold through intermediaries	5.1%	2.9×	Review
App and CTV properties	3.4%	1.8×	Watch
Owned-and-operated web domains	1.9%	0.8×	Normal

Bar: record-defect rate lift vs. the owned-and-operated baseline · scale 0–4.0× · tick marks the 2.0× review threshold 2 of 4 slices over threshold

Evidence-linked improvement

The loop closes on a case, not a fix

A cycle closes when the spoofed listing is a case the next release has to survive. That suite is what the next file published is measured against.

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

01Detect

Record-defect rate rises in a property slice.

02Diagnose

The seller record that was still correct last quarter is checked against every property until one domain explains it.

03Improve

The fix ships against a version, with the domains that exposed it attached.

04Verify

Release is held until the affected listing cases pass again.

05Learn

The case joins the permanent suite and the seller rules move with it.

Learn → DetectThe return edge. The next check 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, checking workflow, evaluation, integration, then production validation and handover.

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

01Ad-ops discovery and boundary definition and it is logged..

02Ad-server, SSP and file-host assessment.

03Seller-file and floor-policy rule mapping and rule mapping.

04Record intake and property normalisation.

05Cross-check logic and evidence binding.

06Confidence scoring and mismatch routing.

07Ops-lead approval workflow.

08Ad-server and SSP integration.

09Authorised-seller regression cases.

10Guardrails and publishing controls.

11Domain-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 property, one server ProductionProduction ad-server access AdvancedMultiple properties / brands

Introduced at Pilot

Checks against your files and rules✓✓✓

Ops-lead approval✓✓✓

Record-accuracy baseline✓✓✓

Introduced at Production

Reporting by property—✓✓

Escalation workflow in your tools—✓✓

Approved record updates—✓✓

Ad-server integration—✓✓

Introduced at Advanced

Multi-taxonomy MFA rules——✓

Multi-stage ops approvals——✓

High request volume——✓

Multi-property seller 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 property list and current seller-file setup → Property ingestion and record mappingWeek 1

02Representative seller-file history → Cross-check baseline and evidence bindingWeek 2

03Your floor policy and approved change rules → Floor-policy and approval-boundary mappingWeek 1

04Access to relevant APIs, feeds or exports → Ad-server and SSP assessment, then integration setupWeek 2

05Records you would not want published → Spoofing cases and failure-mode testingWeek 4

06What no listing may assert → Confidence scoring, mismatch routing, guardrails and approval controlsWeek 3

07Named ops leads to review flags → Ops-lead approval 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

Each band covers the weeks the work really takes, which is why week 5 carries evaluation and pilot together.

Phase W1W2W3W4W5W6

Discovery W1

Build W2 – W3

Evaluate W4 – W5

Pilot & Launch W5 – W6

Week focus W1Ad-ops discovery, floor-policy mapping and the automation boundary W2Source integration and the cross-check baseline W3Checking workflow, confidence logic and approval controls W4Evaluation suite, guardrails and failure-mode testing W5Ad-server integration, pilot properties and targeted corrections W6One reporting cycle run under the ad-ops lead, then Agent Care handover

Reading the bandA bar spans only the weeks its work is named in — the week 5 overlap is real, not padding.

At the end of W6Validation closes on live domains, and Agent Care picks up monitoring.

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

Next step · Advertising AI agent

Build a publisher-yield agent around your ad-ops workflow.

Show us your properties, your seller-file setup and who signs off on changes. If a property's record has drifted from what its resellers report, we'll map the check, set the automation boundary and name what stays with the ops lead.

Discuss this agent →

Nestack Agents · Publisher yield & integrityAGT-AM-13 · Agent Care available after launch

Publisher Yield & Supply-Chain Integrity AI Agent (Sell-Side)