Put the work instruction or changeover guide approved for that line, product and revision in front of the worker in their language, and capture what they solve as a candidate an owner approves.
Take the question as the worker asks it, at the station, in their language, with the work order they are on.
02
Resolve what they are actually running — line, machine variant, product, and the revision in force for it.
Reason
03
Retrieve the approved instruction, changeover guide, setting sheet or quality standard for that combination.
04
Prefer the plant's own standard over a general or vendor source, and say when the two answer differently.
05
Pull past solutions recorded against this line and product, each with the owner who approved it and when.
Decide
06
Stop where the approved content stops, and where the worker's own competency record does not reach.
07
Hold anything no approved document covers as a question for the owner, rather than answering around it.
Out
08
Show the passage with the document, revision and date it came from, in the language the worker asked in.
09
File what a worker solved as a candidate — not as standard — and route it to whoever owns that procedure.
→Product statement
The agent retrieves what is approved and in force, and captures candidates for review. A document owner decides what becomes standard, and a supervisor owns what a worker is authorised to do.
Example workflow
One question, end to end
AgentHuman
1Question askedAt the station, in the worker's language — typed, spoken, or scanned from the work order in front of them
2Line and product resolvedLine, machine variant, product, work order and the document revision in force for that combination today
3Approved content retrievedWork instruction, changeover guide, setting sheet, quality standard and past solutions approved for that line
4Authorisation readThe task checked against the worker's own competency record and what the plant lets that role do unsupervised
No human action required
Stages 1 to 4 run without a person in the loop — the line, the revision in force and the worker's own authorisation are resolved before anything is shown. A question no approved document covers ends that stretch on the spot.
5DecisionSplits on whether approved content covers the question at the revision in force
Covered by content in force
The passage is shown with its source.
Not covered, or past their authorisation
Goes to the owner or the supervisor.
Document owner or supervisor
The owner decides whether a captured solution becomes standard. The supervisor decides what that worker is authorised to do.
Approve · Amend · Reject
Approved — handed back▼
6Answer shown, candidate filedThe passage with its document, revision and date; anything the worker worked out goes to the owner as a candidate
7Outcome evaluatedWhat the owner approved or rejected, what a native speaker corrected, and which answers were served off a stale revision
Rejections
What the owner rejects, and the reason, is counted in the evaluation.
What should not run autonomously
Human approval stays in control
Outside the boundary — human approval required8 items
Publishing captured knowledge as an approved standard.
Revising a work instruction, recipe or setpoint.
Retiring, superseding or reinstating a revision.
Deciding what a worker is authorised to do.
Automation boundaryAgent acts unaided
✓Resolve the line, machine variant, product and revision in force.
✓Retrieve approved content and quote the passage it came from.
✓Show it in the worker's language beside the source it was taken from.
✓File what a worker solved as a candidate and route it to the owner.
The agent writes candidates and questions to your document system, never the standard itself. Usage stays aggregate.
Signing a competency assessment or training record.
Releasing a translation of a safety-critical instruction.
Granting an exception to an approved procedure.
Changing who sees usage data, and at what grain.
Example output
One question at the station, annotated
Everything the agent shows is tied to the line it was asked on and the revision in force there at the time.
Answer output · one questionIllustrative example
Worker asked
Running
Asked in
Answered from
Confidence
Usage recorded
Seal fails after the changeover
Line 4, product B
Polish, spoken
Changeover guide, rev 9
93%
Line and shift, not the person
As receivedThe question in the worker's own words, and the line and product the work order says they are running.
Evidence usedRev 9, in force on line 4Changeover guide, product BOne approved fix here
Why this and not the vendor manualThe builder's manual says otherwise. The plant's own standard is what governs here.
ActionApproveAmendReject
What the score decidesConfidence decides whether it is shown or goes to the owner, never what a worker may do.
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 question at the stationTyped, spoken or scanned from the work order
03Retrieve & capture
Answer from this line's own standard
Use the instruction, changeover guide and setting sheet approved for that line, product and revision — not a general source that reads close enough.
01Approved path
Put the revision in force in their hands
The passage that governs this line today reaches the station in the worker's language, instead of a folder, a laminated sheet of unknown age, or whoever happens to be nearby.
02Human review
Send what is new to the document owner
A fix nobody has written down reaches the person who owns that procedure, with the evidence behind it, rather than spreading between shifts as a habit.
04Build an evidence trail
Retain the question as asked, the documents and revisions served, the language shown, the capture, the owner's decision and the reason for a rejection — on both paths.
Integrations
Typical integrations
Five system groups connect to the same agent. Which of them are in scope is decided in discovery.
Document controlTeamcenter · Windchill SAP DMS · Controlled instruction libraries
MES & production contextSiemens Opcenter · Rockwell FactoryTalk Work orders · product and revision in run
Competency & training recordsSuccessFactors · Workday LMS records · skills matrices
Agent
Connected-worker knowledge
Resolves the line Serves the revision Captures candidates
Integration availability depends on the client's existing systems and API access.
Agent controls
Six layers between the model and the person on the line
Each control wraps the one inside it. An answer clears every layer before a worker reads it, and your document control and competency rules sit outside all six.
L6 · Outermost — last line of defenceInward → L1 · closest to the model
L6Rollback / safe modeFall back to your document system and your supervisors if signals degrade.Roll back
L5Usage-data limitUsage is reported by line, shift and content, not as a measure of a named worker.Aggregate
L4Owner approval gateCaptured knowledge stays a candidate until the document owner approves it.Gate
L3Authorisation boundaryA task past the worker's competency record is shown as who to call, not as a step.Route
L2Revision and languageThe revision in force on that line, in an approved translation — superseded content is withheld.Withhold
L1Line and product scopeNothing is retrieved until the line, machine variant and product in run match.Match
Model coreAnswer drafted — the passage, the document and revision it came from, and confidence
L1 – L2Keep the answer on this line and revision
L3Decides what may be shown as a task
L4 – L5Owner decides canon, usage stays aggregate
L6Pulls automation back when signals degrade
How Nestack evaluates it
Evaluate what was served — not only whether it read well.
Coverage runs the whole depth of the workflow, and every layer is cut by slice.
Surface — the passage the worker reads
Depth of coverage ▼
E1Final-output evaluationWas the passage the one in force for that line and product?
E2Retrieval evaluationRight variant, right revision, and the plant's standard ahead of a general one?
E3Translation fidelityDoes a native speaker read the safety-critical passage the same way?
E4Authorisation boundaryDid it stop where the worker's competency record stops?
E5Slice evaluationHow does accuracy change by language, shift and line?
E6Business outcomeWhat share of captures were approved, and why were the rest rejected?
Floor — the job done to the standard in force
Failure modes
Where each failure originates in the agent
Seven failure modes plotted against the five stages of the agent lifecycle. None of them changes a standard on its own — a document owner approves what becomes canonical, and a supervisor owns what a worker may do. If one gets through and parts have already been made to the wrong instruction, the line is stopped, the material made since that answer was served is contained under your own non-conformance process, and the record shows which passage was shown, at which revision, to whom and when.
Agent lifecycleDirection of processing →
01 · Context1 mode
KW-01
Right content, wrong machine
A variant, tooling or product option this line does not run.
Stage resolvesThe line, the variant, the product and the language
02 · Retrieval2 modes
KW-02
Revision checked, not in force
The document was current; the line was working to an older one.
KW-03
General source, plant differs
A builder's manual answers where the plant's own standard differs.
Stage fetchesThe approved content at the revision in force there
03 · Answer2 modes
KW-04
Translation moves the meaning
A safety-critical instruction reads differently in the second language.
KW-05
Past what the worker may do
Guidance runs on into a task their competency record does not cover.
Stage showsThe passage, its source and where the worker stops
04 · Capture1 mode
KW-06
Workaround captured as standard
A shortcut that worked once is promoted without an owner reading it.
Stage filesWhat a worker solved, as a candidate for the owner
05 · Governance1 mode
KW-07
Usage read as a person's output
Adoption data becomes a ranking of named workers by shift.
Stage tracksApprovals, rejections, revisions and who sees usage
Sev-1 · work is done to the wrong standardSev-2 · a workaround becomes the standardSev-3 · the floor stops asking for it
The people with the most questions get the worst answers
A worker who has run this product for years, in the plant's own language, on a revision that has not moved, gets clean answers. Someone in their second week, reading a second language, on the line that changed on Tuesday, does not.
Slice performance — reported separately, not only in aggregateIllustrative example
Slice
Failure rate
Lift
Lift vs. threshold
Status
Non-primary-language users
7.8%
3.9×
Review
Newly-hired workers
5.0%
2.5×
Review
Recently revised instructions
3.5%
1.8×
Watch
Steady runs, current revision
1.2%
0.6×
Normal
Bar: wrong-or-superseded-answer rate vs. steady-run baseline · scale 0–4.0× · tick marks 2.0×2 of 4 slices over threshold
Evidence-linked improvement
A rejected candidate is worth as much as an approved one
What the owner turned down, and why, is the record that stops the same workaround being captured again and worked to next shift.
Improvement cycle · five stagesSwitchback — the path turns at Improve and returns at Learn
01Detect
Answers served off a stale revision, rejected captures, or a cohort that stopped asking.
02Diagnose
Traced to the effective-revision list, the line and product key, the translation or the capture prompt.
03Improve
The retrieval key, the translation or the instruction itself changes under your document control, with a named approver.
04Verify
Re-run over stored questions from that line, including every passage a native speaker corrected.
05Learn
An approved candidate becomes content; a rejected one becomes a case the agent must not serve again.
Learn → DetectThe return edge. Content becomes standard when the document owner says so — the approval is the change, not the capture.
Typical build scope
Twelve workstreams across six weeks
The build scope read against the delivery timeline. Week structure follows the six-week plan — discovery, content and record access, retrieval and language, evaluation, then capture, approval and handover.
WorkstreamWeek 1Week 2Week 3Week 4Week 5Week 6
01Workflow discovery and boundary definition.
02Line, product and revision-in-force mapping.
03Document control and content-source access.
04Competency and authorisation mapping.
05Retrieval by line, product and revision.
06Plant standard ahead of general sources.
07Language delivery and approved translations.
08Evaluation suite and held-out question sets.
09Capture workflow and candidate routing.
10Owner approval and rejection reasons.
11Usage reporting agreed with worker reps.
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 line, one product familyProductionProduction document integrationAdvancedMulti-plant / multi-language
Introduced at Pilot
Answers from your own approved content✓✓✓
Line, product and revision-in-force matching✓✓✓
Every answer cited to document and revision✓✓✓
Authorisation read from your training records✓✓✓
Baseline evaluation✓✓✓
Introduced at Production
Capture routed to the document owner—✓✓
Approval and rejection workflow—✓✓
Observability and evaluation—✓✓
Introduced at Advanced
Approved translations and native-speaker review——✓
Aggregate usage reporting agreed with worker reps——✓
Multi-plant and enterprise controls——✓
Build priceFrom $5,000From $8,000Custom quote
Final build priceConfirmed after discovery based on the lines and content types in scope, document-control and MES integrations, the state of your revision and competency records, the languages on the floor 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 document control, and who owns each procedure→Document control and content-source accessWeek 1
02The revision each line and product is actually working to→Line, product and revision-in-force mappingWeek 1
03Work instructions, changeover guides and setting sheets→Retrieval by line, product and revisionWeek 2
04Competency records, and what each role may do unsupervised→Competency and authorisation record mappingWeek 2
05The languages and reading levels on your floor→Language delivery and approved translationsWeek 3
06Questions your operators actually ask, with the right answers→Evaluation suite, held-out question sets and failure-mode testingWeek 4
07A named document owner and your worker representatives→Approval workflow, and the usage reporting you agree with themWeeks 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 held-out question sets and the first questions asked from the floor.
PhaseW1W2W3W4W5W6
DiscoveryW1
BuildW2 – W3
EvaluateW4 – W5
Pilot & LaunchW5 – W6
Week focusW1Workflow discovery, document owners and the revision-in-force listW2Content-source access, competency records and retrieval by lineW3Plant-standard precedence, language delivery and approved translationsW4Evaluation suite, held-out questions and native-speaker translation reviewW5Capture and approval workflow, and the first questions from the floorW6Operators ask live on one line, usage reporting agreed, then Agent Care starts
Reading the bandSafety-critical passages are read back by a native speaker in week 4, before a worker sees one in week 5. A translation nobody checked is the one that hurts someone.
At the end of W6Workers have asked real questions on one line, a document owner has approved or rejected every candidate captured, and the usage report has been agreed with your worker representatives.
DurationSix-week plan shown · typical delivery 4–6 weeks depending on scope confirmed in discovery.
Next step · Manufacturing AI agent
Build a knowledge copilot around your own document control.
Show us one line, the instructions and changeover guides that govern it, and the revision each is on today. We'll answer your operators' own questions from your own content, show which revision each answer came from, and put every capture in front of the person who owns that procedure.
