Main site

Mining AI agent · Maintenance planning

Maintenance-Planning AI Agent (Critical Equipment)

Turn condition data and inspection findings into a work list the shutdown window can hold, with the parts dates checked — while the superintendent, the reliability engineer and the statutory position keep every approval.

Typical delivery
4–6 weeks
Deployment
Your stack
Window approval
Named person
After launch
Agent Care

What this agent does

Plans the window, does not approve it

In

  1. 01

    Take the shutdown window, the asset list and the open defect notifications from the maintenance system.

  2. 02

    Read condition-monitoring output, inspection findings and the parts position for each critical asset.

Reason

  1. 03

    Turn condition data and inspection findings into candidate jobs against the asset's own standard job plans.

  2. 04

    Assemble the work pack — task steps, the isolations the job needs, trades, lifting resources and permits to request.

  3. 05

    Check each job's long-lead parts against the promised arrival date and the window it is planned into.

Decide

  1. 06

    Flag jobs the window cannot hold, parts that will not land in time, and statutory work approaching its date.

  2. 07

    Route what it cannot resolve to the planner, the reliability engineer or the superintendent who owns the window.

Out

  1. 08

    Present the draft work list, the packs and the parts exposure — as proposals, with the evidence beside them.

  2. 09

    Retain every reading and finding used, the job plan revision, the rationale and every planner amendment.

Product statement

The agent plans, assembles and checks. Approving the window, deferring statutory work, issuing an isolation and return to service stay with the named person.

Example workflow

One window, end to end

  1. 1Window openedA fixed window on the shutdown calendar, its duration, the asset and the crews available
  2. 2Condition and defects readVibration, oil, thermography and wear data, inspection findings and open defect notifications
  3. 3Candidate jobs builtEach finding matched to the asset's standard job plan, its duration, trades and long-lead parts
  4. 4Window fitted, parts checkedJobs sequenced against the window, statutory work placed first, parts read against promised dates

No human action required

Stages 1 to 4 run without a person in the loop — reading, matching and the parts check finish before anyone is asked to read anything. Nothing is approved in that stretch.

5DecisionSplits on plan confidence and whether statutory or registered plant is involved
Routine job, parts on site

Reaches the planner as a complete draft.

Statutory work or a parts risk

Goes to the reliability engineer before it goes further.

Planner or maintenance superintendent

Reads the draft work list, the packs, the parts dates and the flagged jobs, then decides what the window will hold.

Accept plan · Amend · Request review

Plan accepted — handed back

  1. 6Plan routed for approvalHanded to the planner as a proposal; no window, deferral, isolation or return to service is approved by the agent
  2. 7Outcome evaluatedWhat was added or dropped at the pre-shutdown review, what overran, and where the parts actually were

Amendments

Scope a planner adds or drops is counted in the evaluation.

What should not run autonomously

Human approval stays in control

Outside the boundary — human approval required

8 items

  • Approving a shutdown window or a change to it.
    • Deferring or cancelling a statutory inspection.
    • Extending a mandated overhaul or a life-limited interval.
    • Authorising work on a winder, hoist or registered plant.

  • Automation boundary

    Agent acts unaided

    • ✓Turn condition data and inspection findings into candidate jobs.
    • ✓Assemble the work pack from the standard job plan.
    • ✓Check long-lead parts against the window's dates.
    • ✓Show which jobs fall out of scope when the window moves or shortens.

    Write actions run only inside the approval boundaries agreed during implementation. A statutory inspection is never one.

    • Issuing an isolation certificate or a permit to work.
    • Certifying a component fit for return to service.
    • Changing a maintenance strategy, task or interval.
  • Placing or expediting a long-lead parts order.

Example output

One job in the window, annotated

Everything the agent proposes is attached to the job and the shutdown window it came from.

Draft plan · one job, one window

Illustrative example
Job as raised
SAG mill pinion change-out
Raised from
Vibration alarm and inspection
Long-lead part
On order
Proposed
Plan into next window
Confidence
86%
Window
Not approved by the agent

As received

The job as the inspection raised it, what triggered it and where the part stands — nothing on this side is rewritten.

Evidence used

  • Vibration route history
  • Bearing inspection finding
  • Job plan, current revision

Why the parts flag

The pinion's promised date falls inside the window, not before it.

What the score decides

Confidence decides how hard the planner reads the pack, not what the window may hold.

Action

Accept planAmendRequest review

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 job competing for a window

Condition alarm, inspection finding or defect

03Planning & packing

Work to the asset's own plan

Use the site's standard job plans, task intervals, statutory dates and the parts position current for that window.

01Approved path

Stop the plan drifting from the plant

The work list is built from the condition and defect position as it stands this week, so the planner argues about scope rather than rebuilding the list.

02Human review

Put the parts risk in front of a person

Jobs whose long-lead parts will not land before the window reach the reliability engineer while the scope can still be changed.

04

Build an evidence trail

Retain the readings and findings used, the job plan revision, the parts dates, the confidence and every planner amendment — on both paths.

Integrations

Typical integrations

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

  • Work management

    • SAP PM
    • Pronto
    • Maximo
    • Work orders
    • notifications

  • Condition monitoring

    • Vibration routes
    • oil analysis
    • Thermography
    • online sensors

  • Shutdown scheduling

    • Primavera P6
    • MS Project
    • Shutdown calendars
    • resource plans

Agent

Maintenance & shutdown planning

  • Reads condition data
  • Builds the work pack
  • Routes for approval

  • Parts & procurement

    • Warehouse stock
    • reservations
    • Purchase orders
    • supplier dates

  • Observability & evaluation

    • OpenTelemetry
    • Langfuse
    • Supported monitoring/evaluation sources

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

Agent controls

Six layers between the model and the shutdown plan

Each control wraps the one inside it. A draft plan clears every layer before a planner reads it, and the approval sits outside all six.

L6 · Outermost — last line of defence

Inward → L1 · closest to the model

L6Rollback / safe modeReturn planning to the maintenance team if evaluations or production signals degrade.Roll back
L5Change controlRecord the readings used, the job plan revision, the proposal, the named approver and every amendment.Record
L4Named-person gateWindow approval, deferral, isolation and return to service stay with the named position.Gate
L3Statutory holdStatutory inspections and mandated overhauls are read from the calendar and placed before discretionary work; any the agent cannot date is raised.Hold
L2Job plan matchSteps, trades and durations are checked against the standard job plan; jobs without one are flagged.Flag
L1Source and readingEach job carries the reading, finding or interval it was raised from.Cite
Model corePlan proposed — candidate jobs, work packs, the parts position and confidence
L1 – L2
Decide whether a proposed job may stand
L3
Decides what is placed before discretionary work
L4 – L5
Keep approval with a person and the record intact
L6
Pulls automation back when signals degrade

How Nestack evaluates it

Evaluate the whole plan — not only the work list a planner reads.

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

Surface — the draft plan the planner opens

  1. E1Final-output evaluationDid the proposed work list fit the window as it was actually worked?
  2. E2Step-level evaluationDid it read the current job plan, task interval and inspection finding?
  3. E3Tool evaluationDid it resolve the correct asset, work order and parts reservation?
  4. E4Statutory recallWas every statutory inspection and mandated overhaul placed and dated?
  5. E5Slice evaluationHow does plan quality change across specific job cohorts?
  6. E6Business outcomeHow much scope was added or dropped, and what overran?

Floor — the work the crew actually completes in the window

Failure modes

Where each failure originates in the agent

Seven failure modes plotted against the five stages of the agent lifecycle.

Agent lifecycle

Direction of processing →

  1. 01 · Retrieval

    2 modes

    • MP-01

      Pre-rebuild data read

      Trend data from before an overhaul is treated as current.

    • MP-02

      Statutory date not surfaced

      A due inspection is not read from the calendar.

    Stage gathers

    Condition data, findings, job plans and the parts position

  2. 02 · Planning

    2 modes

    • MP-03

      Sensor fault becomes a job

      A faulty transducer raises work that takes window time.

    • MP-04

      Real defect scored as noise

      A finding is dismissed and never reaches the work list.

    Stage proposes

    Candidate jobs, durations, resources and the sequence

  3. 03 · Verification

    1 mode

    • MP-05

      Isolation missing from pack

      The pack omits an isolation the job actually needs.

    Stage checks

    Statutory dates, parts arrival and window capacity

  4. 04 · Handoff / write

    1 mode

    • MP-06

      Parts date read as firm

      A promised date is presented as a confirmed one.

    Stage presents

    The draft plan the planner reads and the pack it carries

  5. 05 · Change / Version

    1 mode

    • MP-07

      Silent job-plan regression

      A job-plan change moves durations with no record.

    Stage tracks

    Model, prompt, job-plan and task-interval changes

  • Sev-1 · a crew or a statutory duty is exposed
  • Sev-2 · a wrong plan reaches the planner
  • Sev-3 · planning degrades, more is amended
See the complete Mining failure-mode catalogue

Affected slices

Plan quality tracks how much history the asset has

Plan quality is a function of history: if the site has done the job many times the estimate holds; if the machine came back from a rebuild last month, or the part is still on order, it does not. Nestack reports performance by slice, not only in total.

Slice performance — reported separately, not only in aggregate

Illustrative example
SliceFailure rateLiftLift vs. thresholdStatus
Rebuilt assets, no history4.2%2.8×Review
Newly instrumented assets3.3%2.2×Review
Long-lead parts on order2.6%1.7×Watch
Routine conveyor change-outs1.1%0.7×Normal

Bar: amended-or-dropped job rate, lift vs. routine change-out baseline · scale 0–4.0× · tick marks the 2.0× review threshold

2 of 4 slices over threshold

Evidence-linked improvement

One overrun changes the job plan, not just the schedule

A job that overran is not closed by fixing one window. The job plan, the alarm threshold or the parts rule behind it is changed under change control.

Improvement cycle · five stages

Switchback — the path turns at Improve and returns at Learn

  1. 01

    Detect

    Added-or-dropped scope or overruns move in a cohort.

  2. 02

    Diagnose

    Either the reading was wrong or the duration was — the window says which.

  3. 03

    Improve

    The job plan or parts rule goes through change control, with an approver.

  4. 04

    Verify

    Re-planned against held-out windows from the affected cohort.

  5. 05

    Learn

    That window is kept as a regression case and the rule enters the planning standard.

  6. Learn → Detect

    The return edge. A change to a task interval is a strategy change, made by a named approver.

Typical build scope

Twelve workstreams across six weeks

The build scope read against the delivery timeline. Week structure follows the six-week plan — discovery, assets and calendars, planning and packing logic, evaluation, integration, then production validation and handover.

Workstream

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

  1. 01Workflow discovery and automation-boundary definition.Week 1
  2. 02Asset register and criticality assessment.Week 1, Week 2
  3. 03Statutory inspection and overhaul calendar.Week 1, Week 2
  4. 04Condition-monitoring and defect data access.Week 2
  5. 05Standard job plans and duration estimates.Week 2, Week 3
  6. 06Work-pack assembly and isolation listing.Week 3
  7. 07Long-lead parts and supplier date checks.Week 3, Week 4
  8. 08Window fitting and scope-change costing.Week 4
  9. 09Evaluation suite, statutory recall and regression cases.Week 4, Week 5
  10. 10Planner review and amendment capture.Week 5
  11. 11Work-management integration and write-back.Week 5, Week 6
  12. 12Observability, deployment 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 asset class, one siteProductionProduction maintenance integrationAdvancedMulti-site / multi-commodity
Introduced at Pilot
Candidate jobs from condition and defects✓✓✓
Work-pack assembly and isolation listing✓✓✓
Long-lead parts and supplier date checks✓✓✓
Statutory and overhaul dates placed first✓✓✓
Window fitting and scope-change costing✓✓✓
Approval stays with the named person✓✓✓
Baseline evaluation✓✓✓
Introduced at Production
Planner review workflow and write-back—✓✓
Observability and evaluation—✓✓
Introduced at Advanced
Multi-site and multi-commodity calendars——✓
Multiple maintenance and planning systems——✓
Build priceFrom $5,000From $8,000Custom quote
Final build price
Confirmed after discovery based on condition-data sources, maintenance-system and parts integrations, the number of sites, asset classes and shutdown calendars, 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 shutdown calendar and the windows already committed

    Statutory inspection and overhaul calendar

    Week 1

  2. 02The asset register and how you rank criticality

    Asset register and criticality assessment

    Week 1

  3. 03Access to the maintenance system, condition data and stock

    Condition-monitoring and defect data access

    Week 2

  4. 04Your standard job plans, durations and trade requirements

    Standard job plans and duration estimates

    Week 2

  5. 05Supplier lead times and how a promised date gets confirmed

    Long-lead parts and supplier date checks

    Week 3

  6. 06Real shutdowns that overran, and the scope you dropped

    Evaluation suite, statutory recall and regression cases

    Week 4

  7. 07Named planners and a reliability engineer to review plans

    Planner review workflow, then pilot plans 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

Phases are drawn over the weeks they actually occupy. Week 5 carries both the evaluation work and the first plans a planner reviews.

Phase

W1

W2

W3

W4

W5

W6

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

Week focus

W1Shutdown calendar, asset criticality and the automation boundary

W2Maintenance system, condition data and the parts position wired in

W3Job-plan matching and work-pack assembly on the first asset class

W4Evaluation suite, statutory recall and scope-change costing

W5Work-order write-back, supervised plans and targeted corrections

W6A window planned and worked, scope changes counted, then handover

Reading the band
The statutory calendar is tested against last year's actual dates in week 4. A plan drawn before that test would be a plan drawn on an untested calendar.
At the end of W6
Draft plans have been through a window the site actually worked and what was added or dropped has been counted, then Agent Care takes over monitoring.
Duration
Six-week plan shown · typical delivery 4–6 weeks depending on scope confirmed in discovery.

Next step · Mining AI agent

Build a maintenance-planning agent around your shutdown calendar.

Show us your shutdown calendar, your standard job plans and how a defect reaches a work order today. What comes back is one window planned to your own job plans, with each long-lead part marked against a promised date rather than a confirmed one.

Typical delivery
4–6 weeks
Deployment
Your maintenance stack
Window approval
Named person, always
After launch
Agent Care available

Nestack Agents · Maintenance & shutdown planning

AGT-MN-02 · Agent Care available after launch

Build a maintenance-planning agent

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

About you
Your setup

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