Nestack Agent Care
Industries / Engineering / R&D / Documentation agent

Engineering AI agent · Documentation

Software Documentation AI Agent

Date every page against the release it was true of, run the code examples rather than proofread them, and hold each revision for the named owner who publishes it.

4–6 weeksTypical delivery
Your stackDeployment
Release-datedNamed owner
Agent CareAfter launch

What this agent does

Drafts and dates the page, never publishes it

In
01

A page is published, and the release it was true of is recorded against it.

02

A claim is made about a security control, and the evidence that would back it is named beside it.

Reason
03

A code example is executed against the release it claims to describe, rather than read for sense.

04

A runbook command is run on a schedule, so a command that no longer exists surfaces before it is needed.

05

A method is renamed, and each page whose example calls it by the old name is listed for revision.

Decide
06

A sunset date is drafted, and the notice period the contract promises is checked against it.

07

A regulated instruction set keeps each superseded version published, under Regulation (EU) 2021/2226.

Out
08

A page passes its currency term unrevised, and it is marked unverified rather than left standing.

09

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

Product statement

Drafting, dating and flagging belong to the agent. Publication belongs to a named documentation owner, who holds editorial responsibility for the page and answers for it once it is live.

Example workflow

One page, change to publication

AgentHuman
1Source change receivedMerged pull request, release tag, schema change or scheduled documentation review
2Sources assembledThe diff, the release it lands in, the pages that cite it and the evidence each claim rests on
3Page drafted and datedThe revision, the release it is dated to, the claims flagged for review and confidence
4Controls appliedExample execution, claim-to-evidence checks, notice-date checks and confidence threshold
No human action required

Stages 1 to 4 run unaided, and nothing is published at any of them — the agent is drafting, and the owner lane opens at the publication gate.

5DecisionSplits at the publication gate
Evidence complete

Goes to the named owner to publish.

Anything unevidenced

Adds a subject-matter read first.

Owner publication

The page is held with its evidence, its flagged claims and what the controls returned.

Publish · Revise · Send to subject-matter review
Published — by the named owner
6Documentation and site records updatedOnly where write access and publishing policy allow it
7Outcome evaluatedClaim currency, example failures, owner corrections and what readers reported after publication
Corrections

Each owner correction is counted in the evaluation.

What should not run autonomously

Human approval stays in control

Outside the boundary — human approval required8 items
Publishing any page to a customer-facing site.
Drafting a customer incident notice.
Asserting that a security control is in place.
Setting the end-date of a support period.
Automation boundaryAgent acts unaided
Date each page against the release it describes.
Execute the code examples a page publishes against that release.
Name the control that would evidence a claim on a security page.
Mark a page unverified once its evidence goes stale.
Nothing reaches a published page except by a named owner, inside the agreed boundaries.
Signing a regulated technical file or a submission.
Deciding that a deprecation notice has been given.
Holding editorial responsibility for a published page.
Changes to publishing rules or currency thresholds.

Example output

One page, annotated

An SOP agent writes the procedures a floor runs on; this one writes what a developer reads and what a regulator later quotes back. Below is one page as the agent leaves it.

Documentation output · single pageIllustrative example
Page
Recorded as
Release
Evidence of record
Confidence
Held for
Authentication reference page
Rate limits described, examples executed
Dated to release
Release record, 3 August 2026
Held unpublished
The named owner, by name
As receivedTaken from the source tree and the release record — the agent vouches for the date, not the design.
What the record holds Source diff Executed example Release record
Why no publication herePublishing a page is a representation the named owner makes and owns.
ActionPublishReviseSend to subject-matter review
What the score decidesBelow the configured threshold a page gets a subject-matter read before the owner 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
Each pageFrom the change that moved it
03Evidence

Where the evidence is used

The same sentence is an engineering aid to a developer, a representation to a regulator and a description a buyer can hold you to; what changes with the reader is who can sue.

01Approved path

True when it was written

One public security statement was described by an employee as aspirational; a page can also decay honestly, because a rename seldom triggers a documentation update.

02Human review

What was checked, and not found

No enforcement action consulted turned on a page nobody wrote. Blackbaud was charged over statements it chose to publish and over one incident notice charged twice, as unfair and as deceptive, and it settled without admitting or denying. The Cyber Resilience Act does not bite until December 2027.

04Build an evidence trail

The sentence, the code it describes and the owner who published it stay together.

Integrations

Typical integrations

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

Source and schemasGitHub · GitLab · Bitbucket
OpenAPI and protobuf schemas
Documentation platformsRead the Docs · Docusaurus
Mintlify · MkDocs · Sphinx
Knowledge and runbooksConfluence · Notion · Backstage
PagerDuty runbooks · repository wikis

Agent

Software documentation

Reads the change
Drafts and dates
Holds for the owner

Publishing and reviewNetlify · Vercel · static sites
Docs review and translation systems
Observability & evaluationOpenTelemetry · Langfuse
Supported monitoring/evaluation sources

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

Agent controls

Six filters between the code and the page

Six filters down one channel, the last the closest. What is published is set out in the map below.

L6 · Outermost — last line of defenceInward → L1 · closest to the model
L6Rollback / safe modeNarrow the agent to flagging only when evaluation or production signals degrade.Roll back
L5Version monitoringTrack model, prompt and publishing rules, and note the version each page was drafted under.Track
L4TraceabilityRecord each page, the change under it, the evidence it cited and each revision issued, in sequence.Record
L3Owner publicationHold the page for a named owner; the hold governs release, not whether the sentence is true.Gate
L2Currency guardrailsTest each claim against the evidence named for it, and return a page whose example fails to execute.Restrict
L1Confidence thresholdsRoute an unevidenced or stale page to a subject-matter read before the owner sees it.Require review
Model corePage drafted — the revision, the release it is dated to, the flagged claims and confidence
L1 – L2Test whether a page may stand
L3Leaves the publication to a named owner
L4 – L5Keep the page and the release behind it
L6Marks the page unverified when signals degrade

How Nestack evaluates it

Evaluate the whole publishing chain — not only the page that comes out.

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

Surface — the page a developer reads
Depth of coverage ▼
E1Final-output evaluationDid the page record the release it was actually drafted against?
E2Step-level evaluationDid the agent read the right diff, the right schema and the live publishing rules?
E3Tool evaluationDid it read and write the correct page and the correct section?
E4Confidence calibrationDo low-confidence pages actually attract more owner corrections?
E5Slice evaluationHow does performance change across specific page classes?
E6Business outcomeHow many pages needed a correction before the owner published?
Floor — what a regulator later reads

Failure modes

Where each failure originates in the agent

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

Agent lifecycleDirection of processing →
01 · Retrieval1 mode
QW-03

Stale source read

The schema read is not the one now shipped.

Stage gathersThe diff, the schema, the pages and the release
02 · Reasoning2 modes
QW-04

Claim asserted, not evidenced

A sentence appears with no control behind it.

QW-06

Superseded page read as current

A retired revision is worked as the live one.

Stage proposesThe revision, the flagged claims and the release
03 · Tool / write2 modes
QW-02

Thin page passed forward

A page moves on without the subject-matter read.

QW-05

Revision bound to wrong page

The text is filed against another page.

Stage writesOnly where write access and approval policy allow it
04 · Output1 mode
QW-01

Published, release unrecorded

The record shows a page but not the release under it.

Stage returnsThe page a developer reads and a regulator may quote
05 · Change / Version1 mode
QW-07

Silent currency drift

A control lapses while the page keeps the old claim.

Stage tracksModel, prompt, publishing rules and evidence dates
Sev-1 · a page published on no evidence Sev-2 · a stale claim reaches a reader Sev-3 · evidence degrades, page held back

Affected slices

Security pages absorb the corrections

A set-level currency figure can read clean while security and trust pages carry most of the corrections. Nestack reports the correction rate by page class and by release, not only in total.

Slice performance — reported separately, not only in aggregateIllustrative example
SliceFailure rateLift Lift vs. thresholdStatus
Security and trust pages11.7%3.7× Review
Runbooks and on-call steps8.3%2.6× Review
Deprecation and release notes5.2%1.6× Watch
Settled reference pages2.6%0.8× Normal
Bar: correction-rate lift vs. settled-reference baseline · scale 0–4.0× · tick marks the 2.0× review threshold 2 of 4 slices over threshold

Evidence-linked improvement

What the security page still claimed

A cycle shuts when the promise no release still keeps is a regression case. That suite is what the next page published is measured against.

Improvement cycle · five stagesSwitchback — the path turns at Improve and returns at Learn
01Detect

Correction rate rises on security and trust pages.

02Diagnose

The security page that was true at the last audit and has been a representation ever since is read back against the controls it names until one cause is left standing.

03Improve

Changes ship numbered, and the pages behind them travel attached.

04Verify

Each touched page case is run again, and one red holds it back.

05Learn

The case is kept, and the publishing rules are amended in that same commit.

Learn → DetectThe return edge. The next page published 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, publishing workflow, evaluation, integration, then production validation and handover.

Workstream Week 1Week 2Week 3Week 4Week 5Week 6
01Doc-set discovery and automation-boundary definition.
02Source, schema and platform assessment.
03Claim-evidence and documentation-policy rule mapping.
04Change and schema ingestion.
05Claim binding and drafting logic.
06Confidence scoring and review routing.
07Owner publication workflow.
08Documentation-platform integration.
09Currency and claim cases.
10Guardrails and publishing controls.
11Page-trail instrumentation.
12Deployment, documentation and Agent Care handover.
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 tier PilotOne doc set, one release train ProductionProduction publishing workflow AdvancedMultiple doc sets / audiences
Introduced at Pilot
Drafting and dating to your release records
Named owner publication
Document-inventory baseline
Introduced at Production
Reporting by page class
Subject-matter review workflow in your systems
Approved publishing write-back
Repository-and-site integration
Introduced at Advanced
Multi-language doc sets
Cross-audience publishing packs
Large documentation estates
Multi-audience publishing controls
Build price From $5,000 From $8,000 Custom quote
Final build priceConfirmed after discovery based on integrations, workflow complexity, page volume, publishing 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 live doc sets and the release each one is dated to Page capture and release-date versioningWeek 1
02Representative pages, schemas and runbooks Source binding, claim logic and the currency baselineWeek 2
03Your publishing calendar and the owners it names Claim-evidence mapping, page binding and the automation boundaryWeek 1
04Access to relevant APIs, feeds or exports Repository, schema and platform assessment, then integration setupWeek 2
05Pages you would not want quoted back Currency cases and the evaluation roundWeek 4
06What no page may promise Confidence scoring, review routing, guardrails and publishing controlsWeek 3
07A named owner who publishes the page Release to the named owner, then pilot and production validationWeeks 5–6
Nothing else is required Deployment, documentation and Agent Care handover are ours.

Delivery timeline

Four phases across six weeks

A band here is as wide as the phase costs, so the fifth week shows a pair and not a tidier blank.

Phase W1W2W3W4W5W6
Discovery W1
Build W2 – W3
Evaluate W4 – W5
Pilot & Launch W5 – W6
Week focus W1Documentation discovery, publishing rules and the automation boundary W2Repository and platform integration and the document-inventory baseline W3Claim binding, drafting logic and publishing controls W4Evaluation suite, currency cases and failure-mode testing W5Platform integration, pilot pages and targeted corrections W6One publishing cycle run under the documentation owner, then Agent Care handover
Reading the bandEach band covers only the weeks its own work is named for, and the fifth week is shared by design.
At the end of W6Once the page 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 · Engineering AI agent

Build a documentation agent around the page your last release never revised.

Silence carries no legal risk, and each true sentence you publish carries a standing obligation to remain true. Show us your security page and the release it was written for. The only defensible position left is documentation that is maintained.

Nestack Agents · Software documentationAGT-ENG-04 · Agent Care available after launch