Maintain the inclusion and exclusion lists, classify inventory against the suitability policy a person set, filter pre-bid and report where ads ran — the brand owns the policy and every category boundary.
Read the brand's suitability policy, its inclusion and exclusion lists, and the version each of them is on.
02
Take the inventory as it arrives — domain, app, channel, page, video, podcast or retail-media placement.
Reason
03
Classify content and inventory against the policy's categories and risk tiers, and record which tier it fell in.
04
Keep the floor a brand will not fund separate from the tiers that this brand alone has chosen to avoid.
05
Mark anything it could not read — wrong language, non-text format, thin page — as unclassified, not as safe.
Decide
06
Propose pre-bid filters and post-bid flags, and hold every list change and category move for the policy owner.
07
Route flagged placements, news and sensitive-event adjacency and unclassified inventory to human review.
Out
08
Write approved list changes to the platforms that accept them, and report where ads ran and what went unread.
09
Retain the policy version, the classification, its evidence and every block, allow and reviewer decision.
→Product statement
The agent applies a policy a person set and surfaces what it could not classify. It does not decide where a category boundary sits, and it guarantees nothing.
Example workflow
One placement, end to end
AgentHuman
1Placement seenA bid request or a delivered impression on a domain, app, channel, video, podcast or retail-media placement
2Policy and lists readThe brand's suitability policy, its tiers, its lists and the version each is on, stamped with the time read
3Content classifiedCategory and risk tier against that policy, with the language, format and evidence the classification rests on
4Filters and flags proposedPre-bid filters, post-bid flags and list additions or removals, with anything it could not read marked unclassified
No human action required
Stages 1 to 4 run without a person in the loop — the classification, the filter proposal and the list difference are finished before anyone is asked to read anything.
5DecisionSplits on classification confidence and whose line the category sits on
Classified, inside the floor
Reaches the policy owner ready to apply.
Unclassified or on the brand's own line
Held with the reason named, not applied.
Policy owner and account lead
The policy owner decides where the category boundary sits and clears every list change; the account lead signs the report that goes to the client.
Approve · Move the boundary · Send back
Approved — handed back▼
6Lists and reports updatedOnly the list changes a person approved, then the where-it-ran report back to the client
7Outcome evaluatedFalse blocks against a human-reviewed sample, missed adjacency, and classifier accuracy by language
Boundary moves
Every category boundary a person moves is recorded against the policy version.
What should not run autonomously
Human approval stays in control
Outside the boundary — human approval required8 items
Setting or moving a suitability category boundary.
Adding a publisher to an exclusion list.
Removing a publisher from the inclusion list.
Blocking a news outlet or a whole section.
Automation boundaryAgent acts unaided
✓Classify content and inventory against the policy's categories and tiers.
✓Mark what it could not read as unclassified, and say why.
✓Propose pre-bid filters, post-bid flags and list changes for approval.
✓Assemble the where-it-ran report and flag adjacency for review.
Write actions run only inside the approval boundaries agreed during implementation. Moving a category boundary and blocking a publisher are not among them.
Widening a keyword block across live campaigns.
Changing the policy version a campaign runs on.
Clearing a flagged placement as acceptable.
Signing the where-it-ran report sent to a client.
Example output
One placement, annotated
Everything the agent proposes is attached to the placement it judged.
Suitability output · single placementIllustrative example
Placement
Language
Policy
Classification
Confidence
Proposed action
News site, in-article video
Non-English video
Read today
Death, injury or conflict
61%
Held, not blocked
As receivedThe placement, the language and format handed to the classifier, and the policy version it was judged against.
Evidence usedPage text and transcriptPublisher on inclusion listPolicy tier, dated
Why it is heldThe category is on this brand's own line, not the floor — and that line is a person's call.
ActionApproveMove the boundarySend back
What the score decidesIt decides whether a person reads it first, not whether the content was safe.
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 placement, every campaignFrom bid requests and delivery logs
03Suitability policy
Apply this brand's own line
Classify against the client's own suitability policy and tiers, dated and versioned, with the floor kept separate from what this brand avoids.
01Approved path
Take the list work off the buyer
The classification, the list difference and the filter proposal are done before a buyer opens the platform, so the hour goes on the boundary rather than the spreadsheet.
02Human review
Surface what it could not read
Inventory in a language or format the classifier is weak on is marked unclassified and sent to a person now, instead of scoring as low risk and running while the report says it was read.
04Build an evidence trail
Retain the policy version, the classification and its evidence, every block, allow and unclassified call, every boundary a person moved, and the accreditation each vendor actually holds — on both paths.
Integrations
Typical integrations
Five system groups connect to the same agent. Which of them are in scope is decided in discovery.
A block rate in total does not say who was blocked
A policy can look correct in aggregate while a few cohorts — news pages, non-English inventory and identity vocabulary — carry nearly all the blocks a reviewer would reverse. Nestack reports performance by slice, not only in total.
Slice performance — reported separately, not only in aggregateIllustrative example
Slice
Failure rate
Lift
Lift vs. threshold
Status
Identity and social-issue terms
5.9%
3.8×
Review
News and breaking-event pages
4.5%
2.9×
Review
Non-English pages and video
2.9%
1.9×
Watch
Steady-state curated deals
0.9%
0.6×
Normal
Bar: false-block lift vs. curated-deal baseline · scale 0–4.0× · tick marks the 2.0× review threshold2 of 4 slices over threshold
Evidence-linked improvement
Nobody is updating the categories you inherited
The shared category definitions were written by a group that has closed. They live on inside vendor tools, so a cycle that never re-reads them drifts.
Improvement cycle · five stagesSwitchback — the path turns at Improve and returns at Learn
01Detect
False blocks, missed adjacency or reviewer reversals move in one slice.
02Diagnose
Traced to a list, a keyword, the classifier, the policy version or a vendor category.
03Improve
The list, rule or boundary is changed, re-approved by the policy owner and version-linked.
04Verify
Re-run against reviewed placements, including the ones a person reversed.
05Learn
The reversal becomes a regression case and the boundary enters the policy record.
Learn → DetectThe return edge. Each cycle re-dates the lists and re-reads the vendor categories, because nobody outside your policy record keeps them current.
Typical build scope
Twelve workstreams across six weeks
The build scope read against the delivery timeline. Week structure follows the six-week plan — discovery, policy and lists, classification and filtering, evaluation, reporting, then production validation and handover.
WorkstreamWeek 1Week 2Week 3Week 4Week 5Week 6
01Policy discovery and automation-boundary definition.
02Floor and tier definition with the policy owner.
03Inclusion, exclusion and allow-list inventory.
04Verification and classification vendor connections.
05Content and inventory classification logic.
06Pre-bid filter and post-bid flag configuration.
07News and sensitive-event adjacency rules.
08Flagged-placement review workflow.
09False-block sampling against human review.
10Evaluation suite, slices and regression cases.
11Where-it-ran reporting into the warehouse.
12Observability, deployment and Agent Care handover.
12 workstreams · 6 weeks · bar shows the weeks a workstream is active — several run in parallelFinal 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 tierPilotOne brand, one channelProductionProduction pre-bid controlsAdvancedMulti-market / multi-channel
Introduced at Pilot
Policy and tier configuration✓✓✓
Content and inventory classification✓✓✓
Inclusion and exclusion list management✓✓✓
Named policy-owner sign-off✓✓✓
Baseline evaluation✓✓✓
Introduced at Production
Pre-bid filters on approved platforms—✓✓
Flagged-placement review workflow—✓✓
False-block sampling against human review—✓✓
Where-it-ran reporting and observability—✓✓
Introduced at Advanced
News and sensitive-event adjacency rules——✓
Multi-language and enterprise controls——✓
Build priceFrom $5,000From $8,000Custom quote
Final build priceConfirmed after discovery based on the channels and platforms in scope, the number of suitability policies, verification vendors, review controls, reporting depth 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 suitability policy, and the person who owns it→Policy discovery and automation-boundary definitionWeek 1
02Where the floor ends and your own line begins→Floor and tier definition with the policy ownerWeek 1
03The inclusion, exclusion and allow-lists you run today→List inventory, de-duplication and version controlWeek 2
04Access to your verification, DSP and reporting APIs→Vendor connections and content classification logicWeek 2
05The position you want to hold on news and live events→Adjacency rules and flagged-placement review workflowWeek 3
06Placements you regretted, and blocks you had to reverse→Evaluation suite, false-block sampling and regression casesWeek 4
07Named policy owners and reviewers→Review routing, where-it-ran reporting and production validationWeeks 5–6
Nothing else is requiredDeployment, documentation and Agent Care handover are ours.
Delivery timeline
Four phases across six weeks
Phases are drawn over the weeks they actually occupy. Week 5 carries both the false-block sampling and the first filters applied to a live campaign.
PhaseW1W2W3W4W5W6
DiscoveryW1
BuildW2 – W3
EvaluateW4 – W5
Pilot & LaunchW5 – W6
Week focusW1Policy in scope, where the floor ends and who owns the lineW2Vendor connections, list inventory and the classification baselineW3Pre-bid filters, post-bid flags and news adjacency rulesW4Review workflow, false-block sampling and evaluation slicesW5First filters applied under approval and targeted correctionsW6Where-it-ran reporting, production validation and Agent Care handover
Reading the bandThe false-block sample and the review workflow are built in week 4, before a filter touches a live campaign in week 5. The bars show that dependency, not a smooth ramp.
At the end of W6Filters have run under a named owner's approval and a blocked sample has been read back by a person, then Agent Care takes over monitoring.
DurationSix-week plan shown · typical delivery 4–6 weeks depending on scope confirmed in discovery.
Next step · Advertising AI agent
Build a brand-safety agent around your own suitability policy.
Show us the policy you run today, the lists behind it and the last few placements you had to explain to a client. We'll run one channel through classification and read a sample of what your lists block against a human review, so you see both sides of the error before anything is scoped.
