Draft the declaration from the formulation it was calculated against, mark the values a laboratory would have to support, and hold the artwork for the label owner who signs it.
Ingest the formulation, ingredient specifications and configured rule sets from supported PLM or spec systems.
02
Normalise ingredient names, units and yields, and carry each value with the specification it came from.
Reason
03
Calculate the declared values from the formulation, and keep the calculation attached to the version used.
04
Apply three tolerance rules, not one: added nutrients at declaration, indigenous at four-fifths, limits capped.
05
Test the allergen declaration against both lawful mechanisms, the ingredient list and the Contains statement.
Decide
06
Flag any claim an agency must approve before use, and any term the rules leave undefined.
07
Route the drafted artwork to the named label owner, who decides whether it goes to print.
Out
08
Retain the formulation, the calculation, the flags and the approval against the artwork version.
09
Execute write actions only inside the approval boundaries agreed during implementation.
→Product statement
The agent drafts what the formulation supports; the label owner signs the artwork, and the company answers for the value on the pack when a laboratory tests it.
Example workflow
One product, formulation to artwork
AgentHuman
1Formulation receivedRecipe, ingredient specifications, yields and the configured rule set
2Values calculatedDeclared nutrients, ingredient statement and allergens, each with the specification behind it
3Artwork draftedDeclared panel, flags and confidence
4Controls appliedTolerance checks against the class each nutrient falls in, pre-approval checks, held-act checks and confidence threshold
No human action required
Stages 1 to 4 run unaided, and nothing reaches a printer at any of them — the agent is drafting, and the label owner's lane opens at the confidence gate.
5DecisionBranches at the confidence threshold
High confidence
Goes to the label owner to approve.
Low confidence
Adds a regulatory-affairs read first.
Label-owner approval
The draft is held with its formulation, its flagged claims and the confidence.
Approve · Amend · Send to regulatory review
Approved — released to artwork▼
6Specification systems updatedOnly where write access and approval policy allow it
7Outcome evaluatedReviewer amendments, flagged-claim outcomes, laboratory results and corrections raised after print
Amendments
Every reviewer amendment is counted in the evaluation.
What should not run autonomously
Human approval stays in control
Outside the boundary — human approval required8 items
Submitting a sketch label to FSIS for approval.
Deciding a claim may be used before it is cleared.
Warranting a value against laboratory analysis.
Setting the headroom built into a declared value.
Automation boundaryAgent acts unaided
✓Calculate the nutrition panel from the formulation of record for the named owner.
✓Carry every figure forward with the specification behind it.
✓Test the allergen line against both declaration mechanisms.
✓Draft the artwork copy, and hold it for the named label owner.
Any write happens inside the boundaries agreed at implementation, never ahead of the approval.
Calling a product natural, healthy or organic.
Judging which healthy definition applies to a pack.
Releasing artwork to print or to a converter.
Changes to the rule set, tolerances or approval policy.
Example output
One declaration, annotated
Everything the agent calculates is attached to the formulation it was drawn from.
Label-draft output · single productIllustrative example
Product
Drafted line
Declared value
Formulation of record
Confidence
Where it came from
Retail ready meal
Sodium declared from the formulation and the ingredient specifications
410 mg per serving
Formulation version on file
91%
Supplier specification, keyed at intake
As receivedTaken from the formulation and the ingredient specifications on file — nothing here is written by the agent.
Source records usedFormulation of recordIngredient specificationYield and retention data
Why it stops hereA may-contain line is not a control and a person still decides.
ActionApproveAmendSend to regulatory review
What the score decidesBelow the configured threshold the draft picks up a regulatory 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 productFrom the formulation of record
03Drafting
Draft from the formulation
Draw on the recipe, the ingredient specifications and the rule set configured for the market.
01Approved path
Draft it, the label owner signs
Routine panels and ingredient statements arrive calculated, sourced and flagged.
02Human review
Send the reviewer to the risky claims
The agency pre-approves special claims and not the allergen line, so the flagged claims are where the reviewer starts.
04Build an evidence trail
The declaration, the formulation it was calculated from and the signer stay with the artwork.
Integrations
Typical integrations
Five system groups connect to the same agent. Which of them are in scope is decided in discovery.
Specification and PLMTraceGains · Genesis R&D Formulation and spec libraries
ERP and item masterSAP · Infor · NetSuite Item master · bills of materials
Artwork and packagingEsko · Loftware Artwork management · proofing
Agent
Label drafting
Reads the formulation Calculates the panel Holds for approval
Rule sets and referencesNutrient data · retention factors Regulatory reference libraries
Integration availability depends on the client's existing systems and API access.
Agent controls
Six layers between the model and the artwork
Controls stack inward. What the stack does not catch is set out in the map below.
L6 · Outermost — last line of defenceInward → L1 · closest to the model
L6Rollback / safe modeNarrow the agent to data assembly when evaluation or production signals degrade.Roll back
L5Version monitoringTrack model, prompt, rule-set and tolerance-configuration changes.Track
L4Artwork trailRecord the formulation, the calculation, the flags and the approval.Record
L3Label-owner holdHold the draft for the named label owner; on a generically approved label there is no other reviewer behind them.Gate
L2Claim guardrailsTest the draft against the three tolerance rules and the claims an agency must clear; a failure returns the draft. A rule set on file is tested; a market's practice is not.Restrict
L1Confidence thresholdsRoute low-confidence drafts to a regulatory read before the owner sees them.Require review
Model coreDraft produced — declared panel, ingredient statement, flagged claims and confidence
L1 – L2Test whether a draft may stand
L3Puts the release in the owner's hands
L4 – L5Keep the value and the formulation behind it
L6Narrows to data assembly when signals degrade
How Nestack evaluates it
Evaluate the drafting workflow — not only the panel that printed.
Coverage runs the whole depth of the workflow, and every layer is cut by slice.
Surface — the label the shopper reads
Depth of coverage ▼
E1Final-output evaluationDid every declared value match the formulation it was calculated from?
E2Step-level evaluationDid the agent use the right formulation version and rule set?
E3Tool evaluationDid it read and write the correct product and the correct field?
E4Confidence calibrationDo low-confidence drafts actually attract more reviewer amendments?
E5Slice evaluationHow does performance change across specific product families?
E6Business outcomeHow many drafts needed an amendment, or a correction after print?
Floor — the value the company must defend
Failure modes
Where each failure originates in the agent
Seven ways a label goes wrong, placed by stage.
Agent lifecycleDirection of processing →
01 · Retrieval1 mode
BJ-03
Superseded specification
A value is read from a spec the formulation has moved past.
Stage gathersFormulation, ingredient specs, yields and rule sets
02 · Reasoning2 modes
BJ-04
One tolerance band applied
A single band is used where three separate rules govern.
BJ-06
Claim drafted as cleared
A claim needing agency approval is drafted as though approved.
Stage proposesDeclared panel, flagged claims and confidence
03 · Tool / write2 modes
BJ-02
Draft moved on early
A draft advances with flagged claims still unresolved.
BJ-05
Allergen missed in the list
An allergen declared only in the ingredient list is not seen.
Stage writesOnly where write access and approval policy allow it
04 · Output1 mode
BJ-01
Species left generic
A named nut, fish or shellfish is reduced to a category.
Stage returnsThe artwork the label owner approves and the pack carries
05 · Change / Version1 mode
BJ-07
Silent rule-set regression
A model or rule change widens what the agent will assert.
Stage tracksModel, prompt, rule set and tolerance version
Sev-1 · a draft prints unapprovedSev-2 · a wrong value reaches the artworkSev-3 · source degrades, draft routes to review
An aggregate amendment rate averages two different populations: artwork that barely moves between print runs, and artwork redrawn because the formulation changed underneath it. Nestack reports the slice rather than the average.
Slice performance — reported separately, not only in aggregateIllustrative example
Slice
Failure rate
Lift
Lift vs. threshold
Status
Reformulated products
9.5%
3.5×
Review
Claim-bearing packs
7.8%
2.9×
Review
Supplier-supplied values
5.1%
1.9×
Watch
Stable single-market packs
1.6%
0.6×
Normal
Bar: reviewer-amendment-rate lift vs. stable-pack 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 test
An apology does not close a cycle; a case the next release must pass does. That suite is what the next declaration drafted for print is measured against.
Improvement cycle · five stagesSwitchback — the path turns at Improve and returns at Learn
01Detect
Reviewer-amendment rate rises in a product slice.
02Diagnose
No amendment is read on its own — the drafts and the formulations under them are read together until the cause narrows to one.
03Improve
The correction is versioned, with the labels that motivated it attached.
04Verify
A failing case holds the release until it passes.
05Learn
The case is added permanently, and the label rules move with it.
Learn → DetectThe return edge. The suite the next draft meets carries one more case.
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, drafting workflow, evaluation, integration, then production validation and handover.
WorkstreamWeek 1Week 2Week 3Week 4Week 5Week 6
01Label workflow discovery and boundary definition with regulatory affairs.
02PLM, ERP and artwork source assessment.
03Rule-set, tolerance-class and claim-scope mapping for each market.
04Formulation ingestion and normalisation.
05Panel calculation and value binding.
06Confidence scoring and claim-flag routing.
07Label-owner approval workflow.
08Specification and artwork integration.
09Allergen and tolerance cases.
10Guardrails and approval controls.
11Artwork-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 site, one product familyProductionProduction specification systemsAdvancedMultiple markets / brands
Introduced at Pilot
Drafting to your formulations and rules✓✓✓
Label-owner approval✓✓✓
Declaration-accuracy baseline✓✓✓
Introduced at Production
Reporting by product family—✓✓
Approval workflow in your systems—✓✓
Approved write-back—✓✓
Specification-system integration—✓✓
Introduced at Advanced
Multi-market claim rules——✓
Multi-stage regulatory approvals——✓
High artwork volume——✓
Multi-market label controls——✓
Build priceFrom $5,000From $8,000Custom quote
Final build priceConfirmed after discovery based on integrations, workflow complexity, artwork 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 formulations and the fields each one carries→Formulation ingestion and field mappingWeek 1
02Labels you have already put into print→Drafting baseline, value extraction and source bindingWeek 2
03Your rule sets, tolerances and market scope→Rule-set, tolerance-class and claim-scope mappingWeek 1
04Access to relevant APIs, feeds or exports→PLM, ERP and artwork assessment, then integration setupWeek 2
05Labels you would not want printed→Tolerance cases and the evaluation suiteWeek 4
06What no draft may declare on its own→Confidence scoring, claim routing, guardrails and approval controlsWeek 3
07The named label owner who approves artwork→Approval 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
Each band covers the weeks the work really takes, so week 5 carries evaluation and launch together.
PhaseW1W2W3W4W5W6
DiscoveryW1
BuildW2 – W3
EvaluateW4 – W5
Pilot & LaunchW5 – W6
Week focusW1Label workflow discovery, rule-set mapping and the automation boundaryW2Source integration and the drafting baselineW3Drafting workflow, confidence logic and approval controlsW4Tolerance cases, held-act guardrails and failure-mode testingW5Artwork integration, pilot labels and targeted correctionsW6One label cycle drafted under the regulatory team, then handover
Reading the bandA band sits on the weeks its work is named in, and the fifth holds two kinds of it.
At the end of W6Validation finishes on live artwork and Agent Care assumes monitoring.
DurationSix-week plan shown · typical delivery 4–6 weeks depending on scope confirmed in discovery.
Next step · Food & Beverage AI agent
Build a labelling agent around the value your formulation can support.
Front-of-package is still a proposal and two healthy definitions are in circulation, so the rule set is configured for your market rather than assumed. Tell us who signs the artwork — that name is where the drafting workflow ends, and the draft is held for them.
