Main site

Mining AI agent · Exposure records

Worker Exposure & Health Surveillance AI Agent

Trace the exposure record behind a sample — plan coverage, calibration, custody and the clocks a result starts — and hold it for the hygienist, while a physician makes every medical determination.

Typical delivery
4–6 weeks
Deployment
Your stack
Hygienist reads
Person-level
After launch
Agent Care

What this agent does

Assembles the record, not the determination

In

  1. 01

    A shift is sampled, and the pump, the person who wore it and the task actually worked come with the sample.

  2. 02

    A pump is fitted, and its calibration record and pre-shift examination time travel beside that sample.

Reason

  1. 03

    A sample is despatched, and the custody trail is tracked against the transmission window the rule sets.

  2. 04

    A result comes back, and the accreditation in force on the analysis date is checked, not the one current now.

  3. 05

    A result reaches a limit, and the written window opens on the record beside the person named to send it.

Decide

  1. 06

    A plan is read against each similar-exposure group, and the roles nobody sampled this quarter are named.

  2. 07

    A certification nears its re-examination date, and the samples it would cover are named before it lapses.

Out

  1. 08

    A surveillance offer falls due, the offer and the answer are recorded, and the record outlives the job.

  2. 09

    A write runs only inside the approval boundaries agreed at implementation, and never ahead of a signature.

Product statement

The agent assembles and tracks; a person certified under 30 CFR 70.202 signs the sample, and a physician makes the medical determination.

Example workflow

One sampling round, pump to record

  1. 1Shift sampledSampling round, contractor field notes or laboratory portal
  2. 2Record assembledCalibration logs, custody forms, rosters and accreditation certificates, each with its source
  3. 3Coverage comparedGroup coverage, validity flags, clock status and confidence
  4. 4Controls appliedCalibration and custody checks, certification-currency checks, clock checks and confidence threshold

No human action required

Stages 1 to 4 run unaided, and nothing is signed at any of them — the agent is assembling, and the hygienist's lane opens at the confidence gate.

5DecisionBranches at the confidence threshold
High confidence

Goes to the occupational hygienist to read.

Low confidence

Adds a certified-person read first.

Hygienist review

The record is held with its evidence, its named gaps and the confidence.

Accept · Correct · Send for second read

Accepted — record filed for the period

  1. 6Exposure register updatedOnly where write access and approval policy allow it
  2. 7Outcome evaluatedCoverage completeness, invalid-sample causes, notification timeliness and inspection findings

Corrections

A gap found later is refilled by sampling again, not by a late entry.

What should not run autonomously

Human approval stays in control

Outside the boundary — human approval required

8 items

  • Certifying the sample under 30 CFR 70.202.
    • Deciding which limit binds, or that one is exceeded.
    • Notifying a miner that a result reached a limit.
    • Reading an audiogram, a spirometry trace or a film.

  • Automation boundary

    Agent acts unaided

    • ✓Assemble the record from calibration, custody and roster sources.
    • ✓Compare coverage against each similar-exposure group.
    • ✓Run the notification and retention clocks from a recorded time.
    • ✓Name what is missing and hold the record for the hygienist.

    Writes stay inside the boundaries agreed at implementation, and never ahead of a signature.

    • Certifying the corrective-action record after an exceedance.
    • Deciding whether a worker may continue the work.
    • Circulating a health monitoring report to anyone.
  • Changes to sampling rules, clocks or approval thresholds.

Example output

One sampling round, annotated

Everything the agent assembles is attached to the record it was drawn from.

Exposure record output · single sampling round

Illustrative example
Exposure group
Contractor maintenance
Assembled line
Two roles in this group were not sampled in the quarter just closed
Rule cited
30 CFR 70.208
Source of record
Roster and plan
Confidence
86%
Clock
Runs to the quarter end

As received

Taken from the sampling plan, the roster and the calibration log — nothing on this side is written by the agent.

Evidence used

  • Pump calibration log
  • Chain-of-custody form
  • Certification register

Why this is open

The quarter counts valid representative samples, and a person decides what follows.

What the score decides

Below the configured threshold the record goes to the certified person before the hygienist.

Action

AcceptCorrectSend for second read

Value

Where AI adds value

The same four claims, placed at the point in the workflow where each one applies.

Where the value lands

Value 01 – 04

Every sampling round

From the sample record

03Assembly

Take the part the safety

The safety assistant works a shift — SWMS, isolation, permit packs. This one works a person over years.

01Approved path

The sample has to survive

Routine rounds arrive already read against the plan, with their evidence attached.

02Human review

Send review to the gaps

A lapsed certification, a pump examined outside its window or an unsampled role is marked before the hygienist reads.

04

Build an evidence trail

The result, the sampling plan behind it and the person who notified stay on the record.

Integrations

Typical integrations

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

  • Sampling and hygiene data

    • Gravimetric and CPDM results
    • Noise dosimetry records

  • Laboratory and accreditation

    • Analytical laboratory reports
    • Accreditation certificates

  • People and rosters

    • HR roster
    • contractor lists
    • Certification registers

Agent

Exposure record assembly

  • Reads the sample
  • Checks the coverage
  • Holds for review

  • Scheduling and records

    • Surveillance appointment diary
    • Records archive
    • retention

  • Observability & evaluation

    • OpenTelemetry
    • Langfuse
    • Supported monitoring/evaluation sources

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

Agent controls

Six checks between the model and the record

Six checks, outermost first. What the whole set still misses is drawn in the map below.

L6 · Outermost — last line of defence

Inward → L1 · closest to the model

L6Rollback / safe modeHold assembly at draft-only when evaluation or production signals degrade.Roll back
L5Version monitoringTrack model, prompt, clock-rule and sampling-plan configuration changes.Track
L4Record traceabilityRecord the sources, the comparison, the corrections and what stayed open.Record
L3Hygienist reviewHold records for the named hygienist; the gate governs release, not whether the accepted record is complete.Gate
L2Policy guardrailsTest records against calibration, custody, certification and clock rules; a failure returns the record.Restrict
L1Confidence thresholdsRoute low-confidence records to the certified person before the hygienist sees them.Require review
Model coreRecord assembled — group coverage, validity flags, clock status and confidence
L1 – L2
Test whether a record may stand
L3
Puts the read in a hygienist's hands
L4 – L5
Keep the result and the plan behind it
L6
Reverts to record assembly when signals degrade

How Nestack evaluates it

Evaluate the assembly workflow — not only the finished record.

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

Surface — the record an inspector reads

  1. E1Final-output evaluationDid each item in the record match the source it came from?
  2. E2Step-level evaluationDid the agent use the right group, the right plan and the right period?
  3. E3Tool evaluationDid it read and write the correct sampling record and field?
  4. E4Confidence calibrationDo low-confidence records actually attract more hygienist corrections?
  5. E5Slice evaluationHow does performance change across specific exposure groups?
  6. E6Business outcomeHow many records reached the hygienist with a gap, and how many were refilled?

Floor — the outcome the operator answers for

Failure modes

Where each failure originates in the agent

Seven failure modes, placed at the stage where each one begins.

Agent lifecycle

Direction of processing →

  1. 01 · Retrieval

    1 mode

    • DV-03

      Superseded sampling plan

      The group was read from a plan the revision replaced.

    Stage gathers

    Calibration logs, custody forms and roster records

  2. 02 · Reasoning

    2 modes

    • DV-04

      Coverage read as complete

      A job title places a crew in the wrong exposure group.

    • DV-06

      Accreditation checked late

      Currency is read at report date, not analysis date.

    Stage proposes

    Group coverage, validity flags and confidence

  3. 03 · Tool / write

    2 modes

    • DV-02

      Clock started from the file

      The window is dated from when the report arrived.

    • DV-05

      Refusal held off-record

      An offer declined by email never reaches the record.

    Stage writes

    Only where write access and approval policy allow it

  4. 04 · Output

    1 mode

    • DV-01

      Notification not raised

      The written window under 30 CFR 62.110 closes unflagged.

    Stage returns

    The record the hygienist reads and an inspector reads

  5. 05 · Change / Version

    1 mode

    • DV-07

      Silent clock-rule drift

      A model or rule change narrows what is flagged.

    Stage tracks

    Model, prompt, clock rules and plan configuration

  • Sev-1 · assembled outside the boundary
  • Sev-2 · a gap reaches the filed record
  • Sev-3 · lab data degrades, record holds
See the complete Mining failure-mode catalogue

Affected slices

One exposure group can carry most of it

A programme-level sampling-coverage figure can read complete while a few exposure groups carry nearly all of the unusable samples. Nestack reports the unusable-sample rate by group, not only in total.

Slice performance — reported separately, not only in aggregate

Illustrative example
SliceFailure rateLiftLift vs. thresholdStatus
Contractor maintenance crews8.2%3.7×Review
Blast crews and drillers5.9%2.7×Review
Pre-strip and haul operators3.2%1.5×Watch
Designated-area sampling1.1%0.5×Normal

Bar: unusable-sample lift vs. the designated-area baseline · scale 0–4.0× · tick marks the 2.0× review threshold

2 of 4 slices over threshold

Evidence-linked improvement

The loop ends in a regression case

The loop shuts when the voided sample is a regression case. That suite is what the next result returned is measured against.

Improvement cycle · five stages

Switchback — the path turns at Improve and returns at Learn

  1. 01

    Detect

    Unusable samples rise in one exposure group.

  2. 02

    Diagnose

    The pump the worker took off at crib and nobody recorded is read back until one cause remains.

  3. 03

    Improve

    Any change ships numbered, with the results that caused it attached.

  4. 04

    Verify

    One exposure case still failing is enough to hold the release.

  5. 05

    Learn

    One case joins the suite, one line joins the exposure record.

  6. Learn → Detect

    The return edge. Detection next time starts from a longer suite than this one.

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, assembly workflow, evaluation, integration, then production validation and handover.

Workstream

Week 1Week 2Week 3Week 4Week 5Week 6

  1. 01Exposure workflow discovery and boundary setting.Week 1
  2. 02Sampling and laboratory source assessment.Week 1, Week 2
  3. 03Sampling plan, clock and retention rule mapping.Week 1, Week 2
  4. 04Sample and result ingestion, normalised.Week 2
  5. 05Coverage comparison and source binding.Week 2, Week 3
  6. 06Confidence scoring and exception routing.Week 3
  7. 07Hygienist review workflow.Week 3, Week 4
  8. 08Laboratory and roster integration.Week 5
  9. 09Sampling and notification cases.Week 4, Week 5
  10. 10Guardrails and privacy controls.Week 4
  11. 11Exposure-trail instrumentation.Week 5, Week 6
  12. 12Deployment, documentation and Agent Care handover.Week 6

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 tierPilotOne site, one exposure groupProductionProduction sampling systemsAdvancedMultiple sites / schemes
Introduced at Pilot
Assembly to your sampling plan✓✓✓
Hygienist review gate✓✓✓
Sampling-coverage baseline✓✓✓
Introduced at Production
Reporting by exposure group—✓✓
Review routing in your systems—✓✓
Approved write-back—✓✓
Laboratory-result integration—✓✓
Introduced at Advanced
Multi-scheme sampling rules——✓
Multi-stage hygiene approvals——✓
High sampling volume——✓
Multi-site retention controls——✓
Build priceFrom $5,000From $8,000Custom quote
Final build price
Confirmed after discovery based on integrations, workflow complexity, transaction volume, approval controls and deployment requirements.
Separate from build
Build 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.

  1. 01Your sampling plan and exposure-group structure

    Sample and result ingestion and evidence mapping

    Week 1

  2. 02Representative laboratory reports and calibration logs

    Assembly baseline, coverage extraction and source binding

    Week 2

  3. 03Your clocks, retention periods and certification register

    Clock, retention and certification mapping, and the boundary

    Week 1

  4. 04Access to relevant APIs, feeds or exports

    Sampling and laboratory assessment, then integration setup

    Week 2

  5. 05Records you would not want subpoenaed

    Pump-calibration cases and failure testing

    Week 4

  6. 06What no notification may withhold

    Confidence scoring, exception routing, guardrails and privacy controls

    Week 3

  7. 07Named hygienists to read the records

    Hygienist review workflow, then pilot and production validation

    Weeks 5–6

Nothing else is required

Deployment, documentation and Agent Care handover are ours.

Delivery timeline

Four phases across six weeks

Every band is exactly as wide as the weeks its phase consumes, so the fifth legitimately carries two.

Phase

W1

W2

W3

W4

W5

W6

  1. DiscoveryW1
  2. BuildW2 – W3
  3. EvaluateW4 – W5
  4. Pilot & LaunchW5 – W6

Week focus

W1Exposure workflow discovery, plan mapping and the automation boundary

W2Laboratory integration and the assembly baseline

W3Assembly workflow, confidence logic and review controls

W4Evaluation suite, privacy controls and failure-mode testing

W5Roster integration, pilot exposure groups and targeted corrections

W6One monitoring cycle run under the occupational hygienist, then Agent Care handover

Reading the band
A bar covers only the weeks its own work is named in. The week 5 doubling is two phases at once.
At the end of W6
Once the sampling round validates, Agent Care assumes the agent.
Duration
Six-week plan shown · typical delivery 4–6 weeks depending on scope confirmed in discovery.

Next step · Mining AI agent

Build an exposure-record agent around your sampling plan and your hygienist.

Show us your sampling plan, your calibration logs and your clocks. Not a system that reads a medical result — one that assembles the record around it and dates what is contested, including the 2024 silica rule, whose compliance dates were stayed as at 18 August 2026.

Typical delivery
4–6 weeks
Deployment
Your plan and lab
Hygienist reads
Person-level
After launch
Agent Care available

Nestack Agents · Exposure records

AGT-MN-13 · Agent Care available after launch

Build an exposure-record agent

Four questions so the call starts from your actual setup — then pick a time that suits you.

About you
Your monitoring

No obligation. We’ll map the workflow, name the automation boundary and tell you if an agent is the wrong answer.