Draft the review with each assertion tied to the record it came from, keep what the manager changed, and hold the document for the named manager who signs it.
A review is drafted, and the record behind each assertion is named beside it.
02
Ames, No. 23-1039, 5 June 2025: pretext asks whether a stated reason is the true one.
Reason
03
Dominguez-Cruz, 1st Cir., 2 February 2000: shifting explanations let a jury infer pretext.
04
EO 14281, 90 FR 17537: agencies deprioritise disparate impact. Treatment claims are untouched.
05
29 CFR 1602.14: once a charge lands, relevant records are held until final disposition.
Decide
06
Reg (EU) 2026/1744, in force 27 July 2026: Annex III duties wait until 2 December 2027.
07
Article 5(1)(f) was not deferred: emotion inference at work is prohibited, live 2 February 2025.
Out
08
A record is too thin to evaluate, and that thinness is recorded as the finding, not written over.
09
Execute write actions only inside the approval boundaries agreed during implementation.
→Product statement
Drafting, sourcing and holding belong to the agent. The signature belongs to a named manager, who adopts each sentence and answers for it later.
Example workflow
One review, notes to signature
AgentHuman
1Source records receivedGoal records, one-to-one notes, peer input, delivery telemetry and the prior review
2Records ranked and boundWhich note supports which claim, who wrote that note, and the day it was written
3Draft review builtThe narrative, the record behind each assertion, the lines no record reaches and the diff against last cycle
4Controls appliedSource checks, prior-review diffing, protected-material checks and release confidence
No human action required
Stages 1 to 4 run unaided, and nothing reaches an employee at any of them — the agent is drafting, and the manager lane opens at the confidence gate.
5DecisionForks at the release threshold
High confidence
Goes to the named manager to sign.
Low confidence
Adds a business-partner read first.
Manager review
The draft is held with its source records, its unsourced lines and the confidence.
Sign · Attach record · Send to HR
Signed — by the named manager▼
6Review and case records updatedOnly where write access and records policy allow it
7Outcome evaluatedSource accuracy, edit depth, manager corrections and what review found
Corrections
Each manager amendment is counted in the evaluation.
What should not run autonomously
Human approval stays in control
Outside the boundary — human approval required8 items
Signing a review of another adult.
Setting the rating a narrative supports.
Deciding a performance concern exists.
Countersigning a plan or a discharge.
Automation boundaryAgent acts unaided
✓Cite the source record behind each drafted line.
✓Surface any sentence whose evidence the record cannot substantiate.
✓Keep protected-activity material out of the drafting context window.
✓Diff each draft against the review it follows.
Nothing goes into a personnel file except by a named manager, inside the agreed boundaries.
Judging whether the record supports a rating.
Telling anyone a review is defensible.
Choosing what a calibration outcome means.
Changes to the rating, the plan or the file.
Example output
One drafted review, annotated
This serves HR and line managers who may have to explain, years later, who wrote a given sentence in a personnel file; below is one drafted review exactly as the agent leaves it.
Drafted review · single cycleIllustrative example
Report
Draft
Status
Record cited
Confidence
Held for
Mid-year review, one direct report
Two goals met, one carried over from the prior cycle
Draft, unsigned
Goal record, 4 August 2026
Two lines unsourced
The named manager, by name
As receivedDrawn from the goal records and the notes on file, and it asserts nothing that those records do not.
What the record holdsGoal recordOne-to-one notePeer input
Why no signature hereOwning a sentence as your own judgement is an act the manager makes.
ActionSignAttach recordSend to HR
What the score decidesBelow the configured threshold a draft gets an HR read before the manager 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 drafted lineFrom the record that carries it
03Drafting
Where the review is used
The agent vouches for what a record says and the day it was written, not for what a manager believed. C-203/22, 27 February 2025: which data were used, and how, has to be answerable.
01Approved path
Read back in a deposition
SCHUFA, C-634/21: a preparatory score becomes the decision where the human draws strongly on it — and how strongly is a question about manager edits, which a product can measure.
02Human review
What was checked, and not found
No rule checked obliges an employer to keep the notes, the prompt or the drafts a manager rejected. But 29 CFR 1602.14 preserves relevant personnel records until final disposition once a charge is filed, and a pipeline cannot hold what it deleted at the close of the cycle.
04Build an evidence trail
The review, the evidence under it and the manager whose name it carries stay together.
Integrations
Typical integrations
Five system groups connect to the same agent. Which of them are in scope is decided in discovery.
Performance managementWorkday · Lattice · Culture Amp Goals, ratings and past reviews
Manager notesOne-to-one notes · check-ins What was observed, and when
A cycle-level accuracy figure can read clean while thinly recorded reports carry the bulk of the manager corrections. Nestack reports the correction rate by report class, and not only in total.
Slice performance — reported separately, not only in aggregateIllustrative example
Slice
Failure rate
Lift
Lift vs. threshold
Status
Thinly recorded reports
9.9%
3.7×
Review
Newly transferred reports
7.0%
2.6×
Review
Rating-boundary cases
4.4%
1.6×
Watch
Long-tenured steady reports
2.0%
0.7×
Normal
Bar: correction-rate lift vs. the long-tenured baseline · scale 0–4.0× · tick marks the 2.0× review threshold2 of 4 slices over threshold
Evidence-linked improvement
What an unmeant sentence costs
A loop closes when the sentence the manager never meant is a standing case. That suite is what the next review cycle is measured against.
Improvement cycle · five stagesSwitchback — the path turns at Improve and returns at Learn
01Detect
Correction rate rises on thinly recorded reports.
02Diagnose
The line that entered the file because the deadline was nearer than the evidence is worked backwards until one cause is left standing.
03Improve
Reviews go out numbered, and the evidence beneath them rides with it.
04Verify
One wording case still failing is enough to hold the cycle back.
05Learn
It is kept for good, and the drafting rules change in that same commit.
Learn → DetectThe return edge. The next review 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, review drafting, evaluation, integration, then production validation and handover.
WorkstreamWeek 1Week 2Week 3Week 4Week 5Week 6
01Review narratives and automation-boundary definition.
02Goal, note and telemetry sources.
03Sentence-to-source and provenance-coverage tracking.
04Review-record ingestion.
05Record, goal and employee binding.
06Source checks and review routing.
07Manager signature workflow.
08Review-record integration.
09Wording and evidence cases.
10Guardrails and drafting controls.
11Review-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 team, one review cycleProductionProduction review workflowAdvancedMultiple teams / cycles
Introduced at Pilot
Review drafting to your competencies✓✓✓
Named manager signature✓✓✓
Prior-review baseline✓✓✓
Introduced at Production
Reporting by rating class—✓✓
Manager review workflow in your systems—✓✓
Approved write-back—✓✓
Goal-and-record integration—✓✓
Introduced at Advanced
Conflicting source records——✓
Cross-team calibration packs——✓
Large review populations——✓
Multi-manager wording controls——✓
Build priceFrom $5,000From $8,000Custom quote
Final build priceConfirmed after discovery based on integrations, workflow complexity, review 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 live review cycle and the competencies each report is rated on→Record capture and source versioningWeek 1
02Representative goal, note and telemetry sources→Source binding, drafting logic and the prior-review baselineWeek 2
03Your review calendar and the managers it names→Competency mapping, source binding and the automation boundaryWeek 1
04Access to relevant APIs, feeds or exports→Goal, note and telemetry source assessment, then integration setupWeek 2
05Sentences you would not want exhibited→Wording cases and the failure roundWeek 4
06What no review may assert→Source checks, review routing, guardrails and release controlsWeek 3
07A named manager who signs the review→Manager sign-off 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
Two of these phases do share the fifth week, and no band was widened to make the column look neat.
PhaseW1W2W3W4W5W6
DiscoveryW1
BuildW2 – W3
EvaluateW4 – W5
Pilot & LaunchW5 – W6
Week focusW1Cycle discovery, competency mapping and the automation boundaryW2Source integration and the prior-review baselineW3Review drafting, source logic and release controlsW4Evaluation suite, wording cases and failure-mode testingW5Review-record integration, pilot drafts and targeted correctionsW6One review cycle run under the named manager, then Agent Care handover
Reading the bandEach bar spans only the weeks its own work is named for, and week five carries two.
At the end of W6Once the review record validates, Agent Care picks the agent up.
DurationSix-week plan shown · typical delivery 4–6 weeks depending on scope confirmed in discovery.
Next step · HR AI agent
Build a review drafting agent around the sentence your last cycle cannot account for.
Show us one review cycle your managers run and the notes behind the last review written. If nobody can say which sentences the manager composed, the file holds a document with a name on it and no author. A review no one can account for comes back as a finding.
