Turn the inbound post into structured fields, score each field against the page region it was read from, keep the document as the evidence, and hand the record to a named reviewer.
A document arrives by post, portal, email or scan, and it is registered before a field is read out of it.
02
A field is read, and the page and the region it came off travel with the value from there on.
Reason
03
A value comes back confident, and the score is filed as a control on the read, not as a finding that it is right.
04
A supplier name lifts cleanly off a letterhead belonging to the printer, and the field is wrong at full confidence.
05
A document says invoice and behaves like a statement, so the type it announces is treated as a claim as well.
Decide
06
A duplicate arrives on a second channel in another format, and it is matched back rather than read in again.
07
A handwriting sits over a printed line, and it is raised as unread rather than quietly passed over.
Out
08
A record goes to a reviewer, and the document it came from stays attached to it, page by page.
09
Execute write actions only inside the approval boundaries agreed during implementation.
→Product statement
Reading, scoring and holding belong to the agent. Accepting a field, posting the record and paying against it belong to a named reviewer.
Example workflow
One document, post to acceptance
AgentHuman
1Document receivedPostal scan, supplier email, portal download, fax or a shared-drive drop
2Type and pages settledWhat the document appears to be, where it starts and ends, and the channel it came in on
3Fields read and scoredThe value, the page and region it came off, the score and what could not be read
4Controls appliedDuplicate checks, type checks, in-context checks and field confidence
No human action required
Stages 1 to 4 run unaided, and nothing is posted at any of them — the agent is reading, and the reviewer lane opens at the confidence gate.
5DecisionSplits at the confidence gate
Above the threshold
Goes to the named reviewer to accept.
Anything below
Adds a second read first.
Reviewer acceptance
The record is held with its fields, their scores and the document they were read from.
Accept · Correct · Send to second read
Accepted — by the named reviewer▼
6Back-office records updatedOnly where write access and records policy allow it
7Outcome evaluatedField accuracy, score calibration, reviewer corrections and what review found
Corrections
Each reviewer correction is counted in the evaluation.
What should not run autonomously
Human approval stays in control
Outside the boundary — human approval required8 items
Approving a document for payment.
Posting an extracted record to a system of record.
Deciding a low-confidence field is good enough.
Paying anything against a document.
Automation boundaryAgent acts unaided
✓Read whatever arrives into a structured record.
✓Score each field and carry the page region it was read from with it.
✓Keep the original beside the record it produced.
✓Route anything below the threshold to a second read, and hold the rest.
Nothing is posted or paid except by a named reviewer, inside the agreed boundaries.
Judging what a document actually is.
Accepting a field no page supports.
Setting the threshold fields are accepted at.
Changes to extraction rules or thresholds.
Example output
One inbound document, annotated
This serves a back office that has to answer, months later, where a figure in a record came from; below is one document exactly as the agent leaves it.
Extraction output · single documentIllustrative example
Document
Recorded as
Read from
Evidence of record
Confidence
Held for
Supplier invoice, scanned post
Supplier name, read confident
Page one, letterhead
Original scan, 4 June 2026
Held unaccepted
The named reviewer, by name
As receivedTaken from the scanned document on file, and it asserts nothing the page does not carry.
What the record holdsPage and regionOriginal scanArrival channel
Why no acceptance hereDeciding a field is good enough is a judgement the reviewer makes.
ActionAcceptCorrectSend to second read
What the score decidesBelow the configured threshold the field gets a second read before the reviewer sees it.
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 documentFrom the channel it arrived on
03Evidence
Where the original is held
Freight document processing reads bills of lading, rate confirmations and customs paperwork; this is the back office inbound post, whatever it happens to be.
01Approved path
A field is a claim
A supplier name read cleanly off a letterhead can belong to the printer rather than the supplier: the read was good, the score was high, and the field is still wrong.
02Human review
What was checked, and not found
Checked across the document types in scope: nothing published says what a confidence score has to mean, and nothing sets the level a field may be accepted at, so the threshold is a product decision that gets written down and reported by document type rather than in total.
04Build an evidence trail
The document, the field extracted from it and the reviewer who accepted it stay together.
Integrations
Typical integrations
Five system groups connect to the same agent. Which of them are in scope is decided in discovery.
A type-level review-rate figure can read clean while handwritten and annotated forms carry most of the corrections. Nestack reports the correction rate by document type, not only in total.
Slice performance — reported separately, not only in aggregateIllustrative example
Slice
Failure rate
Lift
Lift vs. threshold
Status
Handwritten and annotated forms
8.9%
3.7×
Review
Multi-page batch scans
6.4%
2.7×
Review
Statements and credit notes
4.0%
1.7×
Watch
Structured supplier invoices
1.7%
0.7×
Normal
Bar: correction-rate lift vs. structured-invoice baseline · scale 0–4.0× · tick marks the 2.0× review threshold2 of 4 slices over threshold
Evidence-linked improvement
What a confident wrong field costs
A cycle closes when the field accepted below threshold is a regression case. That suite is what the next batch cleared is measured against.
Improvement cycle · five stagesSwitchback — the path turns at Improve and returns at Learn
01Detect
Correction rate rises on handwritten and annotated forms.
02Diagnose
The invoice whose supplier name came back confident and wrong is taken apart page by page until the read that produced it is found.
03Improve
The change ships numbered, with the documents that caused it attached.
04Verify
One document case still failing is enough to stop the release.
05Learn
One case joins the suite, one line joins the extraction rules.
Learn → DetectThe return edge. The next batch cleared runs 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, field extraction, evaluation, integration, then production validation and handover.
WorkstreamWeek 1Week 2Week 3Week 4Week 5Week 6
01Document-inventory and automation-boundary work.
02Inbound channel and capture sources.
03Field-definition and confidence-threshold mapping.
04Document ingestion and page splitting.
05Field, page and document binding.
06Confidence scoring and review routing.
07Reviewer acceptance workflow.
08Back-office system integration.
09Extraction and confidence cases.
10Guardrails and review controls.
11Document-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 document type, one siteProductionProduction intake workflowAdvancedMultiple types / channels
Introduced at Pilot
Field extraction to your record✓✓✓
Named reviewer acceptance✓✓✓
Document-type baseline✓✓✓
Introduced at Production
Reporting by document type—✓✓
Reviewer workflow in your systems—✓✓
Approved write-back—✓✓
Inbound-channel integration—✓✓
Introduced at Advanced
Multi-format duplicate matching——✓
Cross-entity document packs——✓
Large daily intake——✓
Multi-language extraction controls——✓
Build priceFrom $5,000From $8,000Custom quote
Final build priceConfirmed after discovery based on integrations, workflow complexity, document 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 document types and the fields each one has to yield→Field definition and page-region bindingWeek 1
02Representative documents from each inbound channel→Ingestion, page splitting and the extraction baselineWeek 2
03Your acceptance thresholds and the reviewers they name→Field mapping, threshold setting and the automation boundaryWeek 1
04Access to relevant APIs, feeds or exports→Inbound channel and capture assessment, then integration setupWeek 2
05Extractions you would not want re-keyed→Confidence cases and failure-mode testingWeek 4
06What no extracted field may prove→Confidence scoring, review routing, guardrails and acceptance controlsWeek 3
07A named reviewer who accepts the record→Acceptance 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
No band was padded to reach the next column; the pair in week five is a real overlap, not a gap.
PhaseW1W2W3W4W5W6
DiscoveryW1
BuildW2 – W3
EvaluateW4 – W5
Pilot & LaunchW5 – W6
Week focusW1Document-type discovery, field definition and the automation boundaryW2Channel integration and the extraction baselineW3Page splitting, confidence logic and acceptance controlsW4Evaluation suite, confidence cases and failure-mode testingW5Back-office system integration, pilot intake and targeted correctionsW6One month of intake run under the back-office lead, then Agent Care handover
Reading the bandA band sits on the weeks its own work is named for and no others, and week five is genuinely shared.
At the end of W6When the extraction record validates, Agent Care takes the agent on.
DurationSix-week plan shown · typical delivery 4–6 weeks depending on scope confirmed in discovery.
Next step · Operations AI agent
Build a document processing agent around the field that came back wrong with a green tick beside it.
Show us a week of inbound post and the fields your team re-keys out of it. We will read one batch as it arrived, mark where a confident field and the page underneath it disagree, and hand each field back to a named reviewer.
