Answer consumer questions from the label version on the pack in front of them, reproduce what it declares rather than summarising it, and route the allergen question to a trained person.
Ingesting the consumer question and the product identifier from supported service, email or chat channels.
02
Resolving the pack in hand to a label version, and refusing the question when the version will not resolve.
Reason
03
Reading both declaration mechanisms, the ingredient list and any Contains statement, rather than one.
04
Preserving species detail, so a named nut, fish or shellfish is not reduced to a category.
05
Reproducing the declaration as printed, advisory line included, instead of summarising it.
Decide
06
Flagging questions that turn on cross-contact, medical need, or a formulation the label predates.
07
Routing the allergen question to a trained adviser, and confirming the handover completed.
Out
08
Retaining the contact, the label version quoted and the adviser's answer for the retention period.
09
Executing write actions only inside the approval boundaries agreed during implementation.
→Product statement
The agent shows what the label declares; a trained adviser answers the allergen question, and the brand answers for every word either of them sent.
Example workflow
One contact, question to answer
AgentHuman
1Contact receivedConsumer question, product identifier and the channel it arrived on
2Label version resolvedLot code, pack size and market, each tied to the artwork version on file
3Answer assembledDeclared text, flags and confidence
4Controls appliedBoth-mechanism allergen checks, species checks, version-drift checks, held-act checks and confidence threshold
No human action required
Stages 1 to 4 run unaided, and no allergen answer is sent at any of them — the agent is assembling, and the adviser's lane opens at the confidence gate.
5DecisionBranches at the confidence threshold
High confidence
Goes to the adviser to send.
Low confidence
Adds a quality read first.
Adviser handover
The answer is held with the label version, the flags and the confidence.
Send · Rewrite · Escalate to quality
Approved — the answer goes to the consumer▼
6Service records updatedOnly where write access and approval policy allow it
7Outcome evaluatedAdviser rewrites, flagged-question outcomes, version mismatches and complaints raised after the answer went out
Rewrites
Every adviser rewrite is counted in the evaluation.
What should not run autonomously
Human approval stays in control
Outside the boundary — human approval required8 items
Telling a consumer a product is safe for them.
Judging cross-contact risk from a shared line.
Reading an advisory statement as an assurance.
Answering a medical question about an allergy.
Automation boundaryAgent acts unaided
✓Reproduce the declared text exactly as the pack prints it.
✓Read both mechanisms, the ingredient list and the Contains line.
✓Keep the species named, and the version the answer came from.
✓Hand any allergen question straight to a trained adviser.
Any write happens inside the boundaries agreed at implementation, never ahead of the handover.
Confirming a reformulation before the label moves.
Deciding a complaint is not a reportable event.
Speaking for the brand in a recall notification.
Changes to escalation rules or product-data sources.
Example output
One allergen question, annotated
Everything the agent shows is taken from the label version the consumer is holding.
Support output · single contactIllustrative example
Contact
Declared text shown
Label version
Where it was read
Confidence
What happens next
Allergen question
Ingredient list and Contains statement, reproduced as printed
Lot code on pack
Artwork version on file
89%
Handed to a trained adviser
As receivedTaken from the artwork for that lot — nothing on this side is written or summarised by the agent.
Source records usedArtwork for the lotIngredient statementContains statement
Why it stops hereThe label cannot speak to cross-contact and a person still decides.
ActionSendRewriteEscalate to quality
What the score decidesBelow the configured threshold the answer picks up a quality read first.
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 contactFrom the label version
03Answering
Answer from the label
Draw on the artwork, the ingredient statement and the product data configured for the market.
01Approved path
Read the label, not the memory
Routine ingredient and product questions arrive answered, sourced and version-stamped.
02Human review
Send the adviser the ones that matter
Allergen and cross-contact questions are handed over, so an adviser's time goes where the harm sits.
04Build an evidence trail
The answer, the label version it came from and the adviser who took it over stay on the contact.
Integrations
Typical integrations
Five system groups connect to the same agent. Which of them are in scope is decided in discovery.
Service desk and channelsZendesk · Salesforce Service Email · chat · social inbox
Product and label dataArtwork and specification systems Item master · lot records
Consumer recordsCRM · complaint logs Case history · retention sets
Agent
Consumer support
Reads the label Assembles the answer Hands to an adviser
Quality and complaintsComplaint intake · adverse events Recall and hold notices
Integration availability depends on the client's existing systems and API access.
Agent controls
Six layers between the model and the consumer
Every layer wraps the next. What none of them catches is in the map below.
L6 · Outermost — last line of defenceInward → L1 · closest to the model
L6Rollback / safe modeFall back to signposting when evaluation or production signals degrade.Roll back
L5Version monitoringTrack model, prompt, product-data and escalation-rule changes.Track
L4Contact trailRecord the label version, the text shown, the flags and the handover.Record
L3Adviser handoverHand allergen contacts to a trained adviser; the handover governs who answers, not whether the label is current.Gate
L2Answer guardrailsTest the answer against both declaration mechanisms and the held-act list; a failure returns the answer. Printed text is tested; the line the food ran on is not.Restrict
L1Confidence thresholdsRoute low-confidence answers to a quality read before they go out.Require review
Model coreAnswer assembled — declared text, label version, flagged questions and confidence
L1 – L2Test whether an answer may stand
L3Puts the reply in an adviser's hands
L4 – L5Hold the answer and the label version behind it
L6Falls back to signposting when signals degrade
How Nestack evaluates it
Evaluate the answering workflow — not only the reply that was sent.
Coverage runs the whole depth of the workflow, and every layer is cut by slice.
Surface — the answer the consumer reads
Depth of coverage ▼
E1Final-output evaluationDid the text shown match the label version it was read from?
E2Step-level evaluationDid the agent resolve the right pack, lot and market?
E3Tool evaluationDid it read the correct artwork and the correct field?
E4Confidence calibrationDo low-confidence answers actually attract more adviser rewrites?
E5Slice evaluationHow does performance change across specific contact reasons?
E6Business outcomeHow many answers needed a rewrite, or a correction after they went out?
Floor — the answer the brand answers for
Failure modes
Where each failure originates in the agent
Seven ways an answer goes wrong, placed by stage.
Agent lifecycleDirection of processing →
01 · Retrieval1 mode
BI-03
Stale product record
The answer is read from a spec the pack has moved past.
Stage gathersConsumer question, product identifier, artwork and rules
02 · Reasoning2 modes
BI-04
Contains line assumed
An allergen declared only in the ingredient list is missed.
BI-06
Category answer given
A named nut, fish or shellfish is answered as a group.
Stage proposesDeclared text, flagged questions and confidence
03 · Tool / write2 modes
BI-02
Answer sent early
An allergen contact is answered before a person sees it.
BI-05
Advisory read as clearance
A may-contain line is treated as though it settled the question.
Stage writesOnly where write access and approval policy allow it
04 · Output1 mode
BI-01
Version drift unflagged
The label quoted is not the label on the pack in hand.
Stage returnsThe answer an adviser sends and the consumer relies on
05 · Change / Version1 mode
BI-07
Silent rule regression
A model or rule change widens what the agent will assert.
Stage tracksModel, prompt, product data and escalation rules
Sev-1 · an allergen answer goes outSev-2 · a wrong label version is quotedSev-3 · source degrades, answer routes to review
The consumer under-counted in an aggregate is the one holding a pack that never printed a Contains line: a small share of contacts The cohorts that carry it are named, not averaged away..
Slice performance — reported separately, not only in aggregateIllustrative example
Slice
Failure rate
Lift
Lift vs. threshold
Status
Allergen questions
5.1%
3.8×
Review
Reformulated products
3.0%
2.2×
Review
Packs with no Contains line
2.2%
1.6×
Watch
Routine product questions
1.1%
0.8×
Normal
Bar: adviser-rewrite-rate lift vs. routine-question baseline · scale 0–4.0× · tick marks the 2.0× review threshold2 of 4 slices over threshold
Evidence-linked improvement
A cycle ends in a standing case
The loop shuts when the miss is a case in the suite, not when it has been explained. That suite is what the next consumer contact is measured against.
Improvement cycle · five stagesSwitchback — the path turns at Improve and returns at Learn
01Detect
Adviser-rewrite rate rises in a contact slice.
02Diagnose
The adviser who picked the contact up walks it back beside the label version quoted, until the cause narrows to one.
03Improve
Whatever changes ships against a version, with the contacts that prompted it attached.
04Verify
Nothing ships until the affected cases pass a second time.
05Learn
The suite grows by one case; so does the allergen guardrail set.
Learn → DetectThe return edge. The next contact meets 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, answering workflow, evaluation, integration, then production validation and handover.
WorkstreamWeek 1Week 2Week 3Week 4Week 5Week 6
01Contact workflow discovery and boundary definition with your quality team.
02Service, CRM and product-data assessment.
03Label-version, market and escalation-rule mapping for each brand.
04Contact ingestion and version resolution.
05Answer assembly and text binding.
06Confidence scoring and handover routing.
07Adviser handover workflow.
08Service-desk and product-data integration.
09Allergen-answer regression cases.
10Guardrails and escalation controls.
11Contact-trail instrumentation.
12Deployment, documentation 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 marketProductionProduction service deskAdvancedMultiple brands / markets
Introduced at Pilot
Answering from your label versions✓✓✓
Adviser handover✓✓✓
Answer-accuracy baseline✓✓✓
Introduced at Production
Reporting by contact reason—✓✓
Handover workflow in your systems—✓✓
Approved write-back—✓✓
Product-data integration—✓✓
Introduced at Advanced
Multi-market label rules——✓
Multi-stage quality approvals——✓
High contact volume——✓
Multi-brand support controls——✓
Build priceFrom $5,000From $8,000Custom quote
Final build priceConfirmed after discovery based on integrations, workflow complexity, contact 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 contact reasons and the channels they arrive on→Contact ingestion and reason mappingWeek 1
02Answers your advisers have already sent→Answering baseline, label-text extraction and version bindingWeek 2
03Your product data and the label-version source→Label-version, market and escalation-rule mappingWeek 1
04Access to relevant APIs, feeds or exports→Service, CRM and product-data assessment, then integration setupWeek 2
05Answers you would not want relied on→Allergen cases and failure-mode testingWeek 4
06Where an answer must stop and wait for a person→Confidence scoring, handover routing, guardrails and escalation controlsWeek 3
07Trained advisers to take the handovers→Handover workflow, then pilot and production validationWeeks 5–6
Nothing else is requiredDeployment, documentation and Agent Care handover are ours.
Delivery timeline
Four phases across six weeks
The bands follow real work rather than a plan, so evaluation and pilot genuinely share the fifth week.
PhaseW1W2W3W4W5W6
DiscoveryW1
BuildW2 – W3
EvaluateW4 – W5
Pilot & LaunchW5 – W6
Week focusW1Contact workflow discovery, escalation mapping and the automation boundaryW2Source integration and the answering baselineW3Answering workflow, confidence logic and escalation controlsW4Evaluation suite, allergen guardrails and failure-mode testingW5Service-desk integration, pilot contacts and targeted correctionsW6A live consumer queue answered under supervision, then Agent Care handover
Reading the bandA band covers the weeks its work is actually named in, and the fifth carries two of them.
At the end of W6Once the queue validates, Agent Care owns the running agent.
DurationSix-week plan shown · typical delivery 4–6 weeks depending on scope confirmed in discovery.
Next step · Food & Beverage AI agent
Build a support agent that shows the label and hands the allergen question over.
Bring your product data, your label versions and the advisers who take the handovers. The cost of a wrong allergen answer is not a refund, which is why what we will put in writing is the control and not a resolution rate.
