Main site

Marketing AI agent · live conversation

Conversational Brand AI Agent

Open the conversation on a disclosure, keep the exchange in the state it opened in, and record the turn where a named person took over, for the legal function that owns the surface.

Typical delivery
4–6 weeks
Deployment
Your stack
Named person
First-turn
After launch
Agent Care

What this agent does

Opens the disclosure, never settles the role

In

  1. 01

    A conversation opens, and Art. 50(1) has been enforceable since 2 August 2026, undeferred.

  2. 02

    A surface is deployed, and Art. 50(1) falls on the provider of the system, not on its deployer.

Reason

  1. 03

    A vendor bot is renamed for the brand, and Art. 3(3) can turn that deployer into a provider.

  2. 04

    A first turn passes, and Art. 50(1) wants the person told at the start of that interaction.

  3. 05

    A notice is thought unnecessary, and the obvious exemption in Art. 50(1) is judged objectively.

Decide

  1. 06

    A person takes the conversation over, and what the customer heard at the opening stops being true.

  2. 07

    A topic sits outside brand policy, and the agent refuses it rather than answering around the edge.

Out

  1. 08

    A transcript is kept, and nothing in Chapter IV obliges a deployer to keep one.

  2. 09

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

Product statement

The agent discloses on the first turn and holds the exchange to that opening. A named person takes over, and legal decides whether the company is a provider.

Example workflow

One conversation, first turn to handover

  1. 1Conversation evidence receivedChat transcripts, surface configurations, handover events or vendor system records
  2. 2Conversation context assembledThe surface, the system behind it, the paragraph it answers to and the day the exchange opened
  3. 3Disclosure evidence draftedThe conversation, its opening notice, the handover events and coverage
  4. 4Controls appliedNotice-presence checks, timing checks, handover checks and completeness confidence

No human action required

Stages 1 to 4 run unaided, and nothing is settled at any of them — the agent is recording, and the counsel lane opens at the completeness gate.

5DecisionSplits at the completeness gate
Evidence sufficient

Goes to the named brand owner to approve.

Anything thin

Takes a brand counsel read first.

Counsel review

The conversation is held with its opening notice, its handover and the surface it ran on.

Approve · Append evidence · Send to counsel

Approved — by a named brand owner

  1. 6Surface and conversation records updatedOnly where write access and retention policy allow it
  2. 7Outcome evaluatedNotice timing, handover capture, reviewer corrections and what counsel found

Corrections

Each counsel correction is counted in the evaluation.

What should not run autonomously

Human approval stays in control

Outside the boundary — human approval required

8 items

  • Deciding which role Art. 3(3) puts the brand in.
    • Approving the wording a surface opens with.
    • Judging a disclosure obvious under Art. 50(1).
    • Deciding that a reserved topic may be answered.

  • Automation boundary

    Agent acts unaided

    • ✓State that the customer is dealing with a machine on the first turn.
    • ✓Carry the opening disclosure through every later turn.
    • ✓Record the turn at which a named person assumed.
    • ✓Refuse the topics the brand policy reserves for a person to answer.

    The role and the surface are settled by a named person, inside the agreed boundaries.

    • Telling a customer that no disclosure was owed.
    • Answering a national market surveillance authority.
    • Setting the policy a live surface is held to.
  • Changes to surfaces, scripts or handover rules.

Example output

One conversation, annotated

Our sibling content agent answers for Art. 50(2) marking on generated assets; this page picks up Art. 50(1) at the moment a person starts talking to the brand.

Conversation record · single exchange

Illustrative example
Conversation
Branded chat surface, Art. 50(1)
Recorded as
Disclosed on the first turn, handover logged
Surface
Brand-named surface
Evidence of record
Handover event, 3 August 2026
Confidence
Held unsettled
Held for
The brand legal owner, by name

As received

Taken from the transcript and the surface configuration — it reaches as far as those sources do.

What the record holds

  • Opening notice
  • Surface configuration
  • Handover event

Why no role call here

Whether the brand is the provider is an Art. 3(3) call, not a model output.

What the score decides

Below the configured threshold the conversation picks up a counsel read before approval.

Action

ApproveAppend evidenceSend to counsel

Value

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 conversation

From the surface it opened on

03Evidence

Where the evidence is used

The shipped advertising pages are agency-side, serving a client who booked the work; this one answers to the brand legal function that decides whether the company is a provider.

01Approved path

Whose system is it

White-labelling a vendor bot as Ask Brand puts the system into service under the brand name, and Art. 3(3) then reads the brand as its provider.

02Human review

What was checked, and not found

Checked and not confirmed: the entry-into-force and Official Journal dates of the AI Act, which we did not verify in primary text; any harmonised standard or implementing act fixing a transparency format, none of which is in force; any published count of signatories to the Code of Practice on Transparency of AI-generated Content; and the operative provision behind the four-month transitional, which we could not locate and which binds providers rather than deployers.

04

Build an evidence trail

The conversation, the disclosure it opened with and the person who took over stay together.

Integrations

Typical integrations

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

  • Conversational surfaces

    • Web chat
    • in-app assistant
    • Surface configuration records

  • Vendor and platform systems

    • Bot platform
    • contracts
    • System and naming records

  • Contact centre and handover

    • Agent desktop
    • queue events
    • Handover and transfer records

Agent

Conversational brand disclosure

  • Reads the conversations
  • Tests the disclosure
  • Holds for the brand owner

  • Case and retention systems

    • Counsel tooling
    • ticketing
    • Disclosure and escalation records

  • Observability & evaluation

    • OpenTelemetry
    • Langfuse
    • Supported monitoring/evaluation sources

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

Agent controls

Six thresholds between the model and the brand owner

Six thresholds crossed in turn, the last the narrowest. Whoever gets through is drawn in the map below.

L6 · Outermost — last line of defence

Inward → L1 · closest to the model

L6Rollback / safe modeNarrow the agent to disclosure recording when evaluation or production signals degrade.Roll back
L5Version monitoringTrack model, prompt and disclosure rules; the Digital Omnibus, Regulation (EU) 2026/1744, deferred Chapter III high-risk duties only.Track
L4TraceabilityRecord each conversation, the notice it opened with, the handover it carried and every read of it.Record
L3Brand owner releaseHold the conversation for a named brand owner; the hold governs approval, not whether Art. 50(1) landed on the brand at all.Gate
L2Disclosure guardrailsTest each surface against the disclosure policy you configure; the Code of Practice on Transparency, final 31 July 2026, is voluntary, and not signing it does not constitute non-compliance.Restrict
L1Confidence thresholdsRoute a thin conversation to a counsel read first; Art. 50(1) binds providers, and a brand-named surface can make the brand one.Require review
Model coreEvidence assembled — the conversation, its notice, the handover and coverage
L1 – L2
Test whether a record may stand
L3
Leaves the approval with a named person
L4 – L5
Keep the conversation and the disclosure behind it
L6
Hands to a person when signals degrade

How Nestack evaluates it

Evaluate the whole assembly — not only the conversation record that comes out.

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

Surface — the transcript a regulator reads

  1. E1Final-output evaluationDid the record show what the customer was actually told?
  2. E2Step-level evaluationDid the agent read the right surface, the right session and the live configuration?
  3. E3Tool evaluationDid it read and write the correct conversation and the correct handover?
  4. E4Confidence calibrationDo low-confidence conversations actually attract more counsel corrections?
  5. E5Slice evaluationHow does performance change across specific surfaces?
  6. E6Business outcomeHow many conversations needed a correction before approval?

Floor — the account the brand must give

Failure modes

Where each failure originates in the agent

Seven failure modes, each placed at the stage where it first shows.

Agent lifecycle

Direction of processing →

  1. 01 · Retrieval

    1 mode

    • LL-03

      Stale surface read

      The configuration read is not the one now serving customers.

    Stage gathers

    The surface, the session, the notice and the handover

  2. 02 · Reasoning

    2 modes

    • LL-04

      Disclosure asserted, untested

      A notice is recorded shown without a check.

    • LL-06

      Provider role read as settled

      Art. 3(3) is treated as already answered.

    Stage proposes

    The conversations, their notices and coverage

  3. 03 · Tool / write

    2 modes

    • LL-02

      Thin record passed forward

      A record moves on without the counsel read.

    • LL-05

      Bound to the wrong session

      A handover is filed against the wrong conversation.

    Stage writes

    Only where write access and approval policy allow it

  4. 04 · Output

    1 mode

    • LL-01

      Approved, disclosure unrecorded

      The record shows approval but not what the customer was told.

    Stage returns

    The record a brand owner approves and counsel reads

  5. 05 · Change / Version

    1 mode

    • LL-07

      Silent disclosure regression

      A surface change drops the notice, not the record.

    Stage tracks

    Model, prompt, disclosure rules and record fields

  • Sev-1 · a conversation opened undisclosed
  • Sev-2 · a handover reaches no record
  • Sev-3 · surface degrades, agent hands over
See the complete Marketing failure-mode catalogue

Affected slices

Brand-named chat absorbs the corrections

A surface-level disclosure figure can read clean while the brand-named chat carries most of the rework. Nestack reports the correction rate by surface, not only in total.

Slice performance — reported separately, not only in aggregate

Illustrative example
SliceFailure rateLiftLift vs. thresholdStatus
Brand-named web chat8.6%3.6×Review
In-app assistant6.1%2.6×Review
Messaging channels3.8%1.6×Watch
Vendor-hosted help widget2.0%0.8×Normal

Bar: correction-rate lift vs. vendor-widget baseline · scale 0–4.0× · tick marks the 2.0× review threshold

2 of 4 slices over threshold

Evidence-linked improvement

What an undisclosed handover costs

A cycle closes when the undisclosed handover is a regression case. That suite is what the next conversation logged is measured against.

Improvement cycle · five stages

Switchback — the path turns at Improve and returns at Learn

  1. 01

    Detect

    Correction rate rises on the brand-named chat.

  2. 02

    Diagnose

    The moment a person took the conversation over and nobody told the customer is read back until one cause remains.

  3. 03

    Improve

    The change ships numbered, and the conversations that forced it ride with it.

  4. 04

    Verify

    Nothing releases while one touched conversation case is still red.

  5. 05

    Learn

    It is retained for good, and the disclosure rules are amended in that same commit.

  6. Learn → Detect

    The return edge. The next exchange 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, disclosure assembly, evaluation, integration, then production validation and handover.

Workstream

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

  1. 01Disclosure-state and automation-boundary work.Week 1
  2. 02Surface, vendor and handover sources.Week 1, Week 2
  3. 03Surface-to-paragraph and role-determination mapping.Week 1, Week 2
  4. 04Conversation and transcript ingestion.Week 2
  5. 05Surface, notice and record binding.Week 2, Week 3
  6. 06Completeness scoring and review routing.Week 3
  7. 07Brand owner approval workflow.Week 3, Week 4
  8. 08Contact-centre and CRM integration.Week 5
  9. 09Disclosure and handover cases.Week 4, Week 5
  10. 10Guardrails and escalation controls.Week 4
  11. 11Conversation-trail instrumentation.Week 5, Week 6
  12. 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 tierPilotOne surface, one quarterProductionProduction approval workflowAdvancedMultiple surfaces / markets
Introduced at Pilot
Disclosure assembly to your surfaces✓✓✓
Brand owner approval control✓✓✓
Deployed-surface baseline✓✓✓
Introduced at Production
Reporting by surface—✓✓
Approval workflow in your systems—✓✓
Approved write-back—✓✓
Messaging-channel integration—✓✓
Introduced at Advanced
Multi-market surfaces——✓
Cross-surface record packs——✓
High conversation volume——✓
Multi-surface disclosure controls——✓
Build priceFrom $5,000From $8,000Custom quote
Final build price
Confirmed after discovery based on integrations, workflow complexity, conversation 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.

  1. 01Your surfaces and the systems behind them

    Surface inventory mapping and notice capture

    Week 1

  2. 02Representative transcripts and handover events

    Record binding, disclosure logic and the coverage baseline

    Week 2

  3. 03Your disclosure policy and the wording it names

    Surface mapping, role questions and the automation boundary

    Week 1

  4. 04Access to relevant APIs, feeds or exports

    Surface, vendor and handover-source assessment, then integration setup

    Week 2

  5. 05Conversations you would not want replayed

    Handover cases and the evaluation suite

    Week 4

  6. 06What no chat transcript may establish

    Completeness scoring, review routing, guardrails and approval controls

    Week 3

  7. 07A named brand owner to approve the record

    Approval 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

These widths measure the work and not the drawing, which is why a single week carries two phases.

Phase

W1

W2

W3

W4

W5

W6

  1. DiscoveryW1
  2. BuildW2 – W3
  3. EvaluateW4 – W5
  4. Pilot & LaunchW5 – W6

Week focus

W1Conversation workflow discovery, surface mapping and the automation boundary

W2Source integration and the disclosure-coverage baseline

W3Record assembly, disclosure logic and approval controls

W4Evaluation suite, handover cases and failure-mode testing

W5Channel integration, pilot surfaces and targeted corrections

W6One deployment year run under the brand lead, then Agent Care handover

Reading the band
A bar runs across the weeks its own work is named in. Two phases share the fifth because the work does.
At the end of W6
Once the conversation record validates, Agent Care assumes the agent.
Duration
Six-week plan shown · typical delivery 4–6 weeks depending on scope confirmed in discovery.

Next step · Conversational AI agent

Build a disclosure agent around the surface your customers take for a person.

Show us one branded surface and the turn it opens on. Art. 50(1) names the provider, not the deployer, and a bot put into service under your own name can make you that provider under Art. 3(3). Chapter IV asks no deployer for a log, so yours is voluntary evidence against Art. 99.

Typical delivery
4–6 weeks
Deployment
Your surfaces
Named person
First-turn
After launch
Agent Care available

Nestack Agents · brand conversation

AGT-MK-09 · Agent Care available after launch

Build a conversational brand agent

Four questions so the call starts from your actual setup — then pick a time that suits you.

About you
Your surfaces

No obligation. We’ll map the workflow, name the automation boundary and tell you if an agent is the wrong answer.