Marketing AI agent · asset provenance
Content Generation and Provenance AI Agent
Inspect the file that actually shipped, not the master it came from: read the mark embedded at generation, re-test it after delivery, and hold the asset for the editor who releases it.
- Typical delivery
- 4–6 weeks
- Deployment
- Your stack
- Named editor
- Mark survival
- After launch
- Agent Care
What this agent does
Tests the file, never releases the asset
In
- 01
An asset is generated, and Article 50 of the AI Act has applied since 2 August 2026.
- 02
A synthetic spokesperson ships, and the deep-fake limb of Art. 50(4) lands on a deployer.
Reason
- 03
A voice is cloned, and Art. 3(60) asks whether it resembles an existing person.
- 04
A master is resized for a placement, and the manifest can leave the file without a warning.
- 05
A file is transcoded for an ad server, and the mark either survives that pass or it does not.
Decide
- 06
An asset lands in the CMS, and re-encoding on ingestion is where marks go missing most quietly.
- 07
A format is derived for a feed, and platform re-compression is tested rather than assumed.
Out
- 08
An asset is archived, and Art. 50 lays no record-keeping duty on a deployer.
- 09
Execute write actions only inside the approval boundaries agreed during implementation.
Product statement
The agent records what was generated, embeds or verifies the mark your policy specifies, and re-tests the delivered file. A named editor releases the asset.
Example workflow
One asset, generation to release
- 1Asset evidence receivedGeneration logs, tool manifests, DAM renditions or delivery-pipeline captures
- 2Asset context assembledThe asset, the tool that made it, the paragraph it answers to and the day it was generated
- 3Provenance evidence draftedThe asset, its marks, the renditions derived from it and completeness
- 4Controls appliedMark-presence checks, survival re-tests, deep-fake checks and completeness confidence
No human action required
Stages 1 to 4 run unaided, and nothing is released at any of them — the agent is testing, and the legal lane opens at the completeness gate.
Goes to the releasing editor to approve.
Adds a legal counsel read first.
Legal review
The asset is held with its marks, its renditions and the tool that generated it.
Release · Append evidence · Send to legal review
Released — by a named editor
- 6Asset and rendition records updatedOnly where write access and records policy allow it
- 7Outcome evaluatedMark survival, register coverage, reviewer corrections and what the read found
Corrections
Each legal correction is counted in the evaluation.
What should not run autonomously
Human approval stays in control
Outside the boundary — human approval required
8 items
- Releasing an asset for publication.
- Deciding a deep fake needs no disclosure.
- Settling deployer or provider under Art. 3(3).
- Signing the Code of Practice on Transparency.
Automation boundary
Agent acts unaided
- ✓Record what generated the asset and the tool version behind it.
- ✓Embed or verify whichever mark your own marking policy specifies.
- ✓Re-test the file the pipeline actually ships.
- ✓Flag the rendition that generated marked and reached.
Nothing is released or disclosed except by a named person, inside the agreed boundaries.
- Judging whether an Art. 50(4) exemption applies.
- Telling a market surveillance authority anything.
- Setting the marking policy an asset is held to.
- Changes to masters, renditions or delivery records.
Example output
One asset, annotated
Our campaign copy generation agent drafts headlines and body copy against the brief, the brand voice and the approved claims library; this page is about the file — what is embedded in it, and whether it is still there after delivery.
Register entry · single asset
Illustrative example- Asset
- Synthetic spokesperson, Art. 50(4)
- Recorded as
- Generated marked, re-tested after delivery
- Mark
- Deep fake
- Evidence of record
- Delivery re-test, 3 August 2026
- Confidence
- Held unreleased
- Held for
- The releasing editor, by name
As received
Taken from the generation log and the delivered rendition — it reaches as far as those sources do.
What the record holds
- Generation log
- Embedded mark
- Delivered rendition
Why no release here
Whether a deep fake may ship is an Art. 50(4) call, not a model output.
What the score decides
Below the configured threshold an asset picks up a legal read before the editor sees it.
Action
ReleaseAppend evidenceSend to legal reviewValue
Where AI adds value
The same four claims, placed at the point in the workflow where each one applies.
Where the value lands
Value 01 – 04
Every asset
From the tool that made it
Where the evidence is used
Our advertising pages answer to a client who booked the media; this one answers to the brand legal and privacy functions that live with the asset afterwards.
The mark has to survive
A mark present at generation and absent in the delivered creative is a failure no copy review can detect, which is why the re-test runs at the end of the pipeline.
What was checked, and not found
The enacting provision of Regulation (EU) 2026/1744 behind the 2 December 2026 marking transitional was not located in the operative text, the OJ publication and entry-into-force dates of the AI Act were not verified against primary text, no harmonised standard or implementing act on marking formats was found in force, and no signatory count for the Code of Practice on Transparency of AI-generated Content is published.
Build an evidence trail
The asset, the mark embedded in it and the editor who released it stay together.
Integrations
Typical integrations
Five system groups connect to the same agent. Which of them are in scope is decided in discovery.
Generation tools and models
- Image, video and voice tools
- Generation logs and manifests
Asset management
- DAM
- CMS renditions
- Master and derivative records
Delivery and distribution
- Ad server
- social platforms
- Delivered file captures
Agent
Content generation provenance
- Reads the assets
- Tests the marks
- Holds for the editor
Records and case systems
- Legal tooling
- ticketing
- Disclosure and review records
Observability & evaluation
- OpenTelemetry
- Langfuse
- Supported monitoring/evaluation sources
Integration availability depends on the client's existing systems and API access.
Agent controls
Six presses between the model and the editor
Six presses run in sequence, the last the heaviest. Whatever comes out whole is drawn in the map below.
L6 · Outermost — last line of defence
Inward → L1 · closest to the model
- L1 – L2
- Test whether an asset may ship
- L3
- Puts the release in a person's hands
- L4 – L5
- Keep the asset and the mark behind it
- L6
- Withholds the release when signals degrade
How Nestack evaluates it
Evaluate the whole assembly — not only the register entry that comes out.
Coverage runs the whole depth of the workflow, and every layer is cut by slice.
Surface — the record an authority reads
- E1Final-output evaluationDid the entry record what the asset actually carries?
- E2Step-level evaluationDid the agent read the right asset, the right rendition and the live delivery path?
- E3Tool evaluationDid it read and write the correct asset record and the correct mark?
- E4Confidence calibrationDo low-confidence assets actually attract more legal corrections?
- E5Slice evaluationHow does performance change across specific asset types?
- E6Business outcomeHow many assets needed a correction before the editor released?
Floor — the register the brand answers for
Failure modes
Where each failure originates in the agent
Seven failure modes, each named at the stage where it first appears.
Agent lifecycle
Direction of processing →
01 · Retrieval
1 mode
- KV-03
Stale rendition read
The rendition read is not the one now being served.
Stage gathers
The assets, the tools, the marks and the renditions
02 · Reasoning
2 modes
- KV-04
Mark asserted, not tested
A mark is recorded present without a re-test.
- KV-06
Provider duty read onto us
Art. 50(2) marking is worked as our own duty.
Stage proposes
The assets, their marks and completeness
03 · Tool / write
2 modes
- KV-02
Thin asset passed forward
An asset moves on without the legal read.
- KV-05
Bound to the wrong master
A mark is filed against the wrong asset.
Stage writes
Only where write access and approval policy allow it
04 · Output
1 mode
- KV-01
Released, evidence unrecorded
The record shows a release but not what supported it.
Stage returns
The record an editor releases and an authority reads
05 · Change / Version
1 mode
- KV-07
Silent marking regression
A pipeline change strips the mark, not the record.
Stage tracks
Model, prompt, marking rules and asset fields
- Sev-1 · a deep fake shipped undisclosed
- Sev-2 · wrong mark reaches the register
- Sev-3 · source degrades, asset held back
Affected slices
Synthetic video absorbs the corrections
A type-level mark-survival figure can read clean while synthetic video and voice carry most of the rework. Nestack reports the correction rate by asset type, not only in total.
Slice performance — reported separately, not only in aggregate
Illustrative example| Slice | Failure rate | Lift | Lift vs. threshold | Status |
|---|---|---|---|---|
| Synthetic video and voice | 11.4% | 3.7× | Review | |
| Social-derived formats | 8.1% | 2.6× | Review | |
| Display and banner renditions | 5.1% | 1.6× | Watch | |
| Photography and stills | 2.3% | 0.7× | Normal |
Bar: correction-rate lift vs. photography baseline · scale 0–4.0× · tick marks the 2.0× review threshold
2 of 4 slices over threshold
Evidence-linked improvement
What a stripped mark costs
A cycle shuts when the stripped manifest is a regression case. That suite is what the next asset released is measured against.
Improvement cycle · five stages
Switchback — the path turns at Improve and returns at Learn
- 01
Detect
Correction rate rises on synthetic video and voice.
- 02
Diagnose
The mark that was in the master and gone from the file the ad server delivered is read back until one cause remains.
- 03
Improve
The change ships numbered, and the assets that forced it ride with it.
- 04
Verify
Nothing releases while one touched asset case is still red.
- 05
Learn
It is retained for good, and the marking rules are amended in that same commit.
Learn → Detect
The return edge. The next release is measured 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, provenance assembly, evaluation, integration, then production validation and handover.
Workstream
Week 1Week 2Week 3Week 4Week 5Week 6
- 01Mark-survival discovery and automation-boundary work.Week 1
- 02Generation, DAM and delivery sources.Week 1, Week 2
- 03Asset-to-paragraph and mark-coverage rule mapping.Week 1, Week 2
- 04Asset and rendition ingestion.Week 2
- 05Asset, mark and record binding.Week 2, Week 3
- 06Completeness scoring and review routing.Week 3
- 07Editor release workflow.Week 3, Week 4
- 08Ad-server and CMS integration.Week 5
- 09Provenance and survival cases.Week 4, Week 5
- 10Guardrails and release controls.Week 4
- 11Asset-trail instrumentation.Week 5, Week 6
- 12Deployment, documentation and Agent Care handover.Week 6
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 asset type, one quarter | ProductionProduction release workflow | AdvancedMultiple brands / markets |
|---|---|---|---|
| Introduced at Pilot | |||
| Provenance assembly to your assets | ✓ | ✓ | ✓ |
| Releasing editor control | ✓ | ✓ | ✓ |
| Generated-asset baseline | ✓ | ✓ | ✓ |
| Introduced at Production | |||
| Reporting by asset type | — | ✓ | ✓ |
| Release workflow in your systems | — | ✓ | ✓ |
| Approved write-back | — | ✓ | ✓ |
| Delivery-pipeline integration | — | ✓ | ✓ |
| Introduced at Advanced | |||
| Multi-brand estates | — | — | ✓ |
| Cross-market evidence packs | — | — | ✓ |
| Large asset libraries | — | — | ✓ |
| Multi-format marking controls | — | — | ✓ |
| Build price | From $5,000 | From $8,000 | Custom quote |
- Final build price
- Confirmed after discovery based on integrations, workflow complexity, asset volume, approval controls and deployment requirements.
- Separate from build
- Build 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 bring
We build with it
01Your assets and the tools that generate them
→Asset inventory mapping and mark capture
Week 102Representative masters, renditions and delivered files
→Record binding, marking logic and the survival baseline
Week 203Your marking policy and the formats it names
→Asset mapping, mark binding and the automation boundary
Week 104Access to relevant APIs, feeds or exports
→Generation, DAM and delivery-source assessment, then integration setup
Week 205Assets you would not want traced
→Survival cases and failure-mode testing
Week 406What no provenance mark may establish
→Completeness scoring, review routing, guardrails and release controls
Week 307A named editor to release the asset
→Release workflow, then pilot and production validation
Weeks 5–6
Nothing else is required
Deployment, documentation and Agent Care handover are ours.
Delivery timeline
Four phases across six weeks
Every band below is worked time and not drawn space, and so the fifth of them has to carry a pair.
Phase
W1
W2
W3
W4
W5
W6
- DiscoveryW1
- BuildW2 – W3
- EvaluateW4 – W5
- Pilot & LaunchW5 – W6
Week focus
W1Content workflow discovery, asset mapping and the automation boundary
W2Source integration and the mark-survival baseline
W3Provenance assembly, marking logic and release controls
W4Evaluation suite, survival cases and failure-mode testing
W5Delivery integration, pilot assets and targeted corrections
W6One publishing quarter run under the content lead, then Agent Care handover
- Reading the band
- Each bar covers only the weeks its own work is named for. The fifth holds a pair because the work does.
- At the end of W6
- Validation closes on live releases, and Agent Care picks up the watch.
- Duration
- Six-week plan shown · typical delivery 4–6 weeks depending on scope confirmed in discovery.
Next step · Marketing AI agent
Build a provenance agent around the rendition that left your master marked and reached the ad server bare.
Show us one asset and the file your ad server delivered. Not a copy review. A file test, run at the far end of the pipeline, on the rendition that shipped. Art. 50 lays no record-keeping duty on deployers, so the register is voluntary evidence built against Art. 99 exposure.
- Typical delivery
- 4–6 weeks
- Deployment
- Your assets
- Named editor
- Mark survival
- After launch
- Agent Care available
Nestack Agents · asset provenance
AGT-MK-03 · Agent Care available after launch