MiningManaged AI Agents
Mining AI Agents,
Monitored for Safety
Nestack Agent Care helps mining operators monitor, evaluate, and optimize AI agents used for equipment monitoring, safety procedures, resource planning, and compliance reporting — before small AI errors become safety or regulatory incidents.
Scope
Mining AI agents we build & manage
Mine & fleet4
Safety & people5
Geology & environment5
Permits & commercial4
Observability
What we make observable
Every mining agent session is traced across ten layers — what we capture and the evidence we keep.
- Evidence we keepGoalconstraintsapproval requirement
- Evidence we keepSourceversiontimestamprelevancecitation
- Evidence we keepPlanned sequenceactual sequenceworkflow status
- Evidence we keepTask statusresultretryfailure reason
- Evidence we keepTool nameversioninputoutputpermissionresult
- Evidence we keepModel/versioninput/outputtoken usagelatencycost
- Evidence we keepEvaluation typemetricthresholdresult
- Evidence we keepGuardrail targettriggeractionenforcement result
- Evidence we keepReviewerdecisioncorrectionreason
- Evidence we keepOutcome statusbusiness resultlinked trace
Catalog
Failure modes
Filter failure modes by where they occur in the agent lifecycle—from goals and retrieval to tools, evaluations, guardrails and outcomes.
Knowledge & compliance agents · MIN-01–14
MIN-01Wrong safety-procedure guidance — isolation, lockout, confined space, ground controlSEV-1
MIN-02Stale regulatory content after mine-safety code updatesSEV-2
MIN-03Hallucinated geological or assay dataSEV-2
MIN-04Maintenance-schedule errors on safety-critical equipmentSEV-1
MIN-05Permit / tenement deadline missesSEV-2
MIN-06Leakage of market-sensitive exploration/resource dataSEV-1
MIN-07Injection via contractor documents and site reportsSEV-1
MIN-08Unit conversion errors — tonnage, grade, volumes (metric/imperial)SEV-2
MIN-09Resource-statement boundary breach — JORC-style claims without competent-person sign-offSEV-1
MIN-10Geotech-alert under-escalation — seismic and ground-movement anomalies summarized as routineSEV-1
MIN-11Fatigue-roster breaches — shift plans violating fatigue-management rulesSEV-2
MIN-12Environmental-monitoring misreporting — tailings and discharge readings misstatedSEV-1
MIN-13Contractor-competency gaps — expired tickets and inductions treated as currentSEV-2
MIN-14Dispatch-recommendation drift — haulage and scheduling efficiency creeping downSEV-3
Autonomous field operations · MIN-15–28
MIN-15Digital/physical world divergence — routes and autonomy boundaries released in software without matching ground stateSEV-1
MIN-16Comms-loss stale-command execution — agent resumes outdated commands after network restoreSEV-1
MIN-17Mode confusion — machine silently reverts to autonomous while humans approach for recoverySEV-1
MIN-18Road-condition blindness — programmed speeds on wet roads cause slides, rollovers, collisionsSEV-1
MIN-19Perception degradation and misclassification — dust-blinded LiDAR, reverse blind zones, no person detectionSEV-1
MIN-20Mixed-fleet situational-awareness failure — manned vehicles encroach on invisible autonomous pathsSEV-1
MIN-21Automation over-trust — workers exploit the machine's guaranteed stop as personal protectionSEV-1
MIN-22Goal persistence without comprehension — machine repeatedly rams an obstacle to reach its waypointSEV-1
MIN-23Remote-supervisor overload — span-of-control exceeds human attentionSEV-2
MIN-24Autonomous rail command misassignment — human-mode overrides transmitted to unmanned trainsSEV-1
MIN-25Fleet-wide software-update common-cause failure — one bad update touches every machine at onceSEV-1
MIN-26Operator skill fade — manual competence atrophies until the hardest handover momentsSEV-2
MIN-27Alarm flooding and nuisance-alarm habituation — real alerts lost in the noiseSEV-2
MIN-28Emergent no-fault accidents — every component works as designed, the interaction failsSEV-1
Geoscience, planning & process models · MIN-29–37
MIN-29Sample-bias propagation into grade models — biased inputs fail reconciliation at the millSEV-2
MIN-30Prospectivity survivorship bias — the model highlights where explorers already lookedSEV-3
MIN-31Geometallurgical model staleness — throughput predictions drift as ore migrates into unseen domainsSEV-2
MIN-32Schedule-optimizer infeasible plans — perfect objective value, impossible executionSEV-2
MIN-33Ventilation-on-demand unsafe degradation — energy optimizer under-ventilates on blind sensorsSEV-1
MIN-34Process-control soft-sensor drift — the controller quietly loses value or gets switched offSEV-3
MIN-35Tailings-monitoring false negatives — blind satellite data displayed as “stable”SEV-1
MIN-36Digital-twin divergence — decisions made against a fictional assetSEV-3
MIN-37Cross-site model transfer failure — one site's model silently mispredicts everywhere elseSEV-2
OT, cyber & data integration · MIN-38–40
MIN-38GNSS spoofing/jamming — fleet positioning corrupted by RF interferenceSEV-1
MIN-39Sensor-integrity corruption — agent acts confidently on drifted, desynced or adversarial dataSEV-1
MIN-40Agent over-privilege across IT/OT — one compromised agent can command the whole fleetSEV-1
Enterprise & commercial agents · MIN-41–50
MIN-41Trading-agent state corruption — the agent trades against a false picture of its own bookSEV-1
MIN-42AI-generated ESG / Scope 3 misstatement — unexplainable numbers in external reportsSEV-2
MIN-43Procurement agent on dirty master data — wrong or duplicate critical-spares orders at machine speedSEV-2
MIN-44Community / Indigenous communications without cultural authority — fluent text papering over consentSEV-1
MIN-45Diligence and title hallucination — missed clauses, invented cases, wrong jurisdictionSEV-2
MIN-46Royalty / streaming misinterpretation — the same wrong reading compounds every periodSEV-2
MIN-47Safety-critical translation errors — fluent but meaning-inverted safety instructionsSEV-1
MIN-48HR chatbot entitlement misrepresentation — confident wrong answers bind the companySEV-2
MIN-49Machine-speed disclosure breach — AI-drafted wording moves the market before IR can correctSEV-2
MIN-50Stale-authority retrieval — superseded mine plans and SOPs served as currentSEV-1
A · Safety & compliance assistants (SWMS, isolation procedures)
SF-01Stale isolation point01 · RetrievalSEV-1
SF-02Superseded revision read01 · RetrievalSEV-2
SF-03Generic SWMS wording02 · DraftingSEV-2
SF-04Stored energy omitted02 · DraftingSEV-1
SF-05Permit gap not raised03 · VerificationSEV-2
SF-06Over-flagging floods review04 · Handoff / writeSEV-3
SF-07Procedure change untracked05 · Change / VersionSEV-1
B · Maintenance-planning agents for critical equipment
MP-01Pre-rebuild data read01 · RetrievalSEV-2
MP-02Statutory date not surfaced01 · RetrievalSEV-1
MP-03Sensor fault becomes a job02 · PlanningSEV-3
MP-04Real defect scored as noise02 · PlanningSEV-1
MP-05Isolation missing from pack03 · VerificationSEV-1
MP-06Parts date read as firm04 · Handoff / writeSEV-2
MP-07Silent job-plan regression05 · Change / VersionSEV-2
C · Geological / assay data copilots
GA-01Certificate not reconciled01 · RetrievalSEV-1
GA-02Superseded certificate used01 · RetrievalSEV-2
GA-03Method change read as geology02 · ReconcilingSEV-2
GA-04Over-limit result carried02 · ReconcilingSEV-1
GA-05Sample swap not caught03 · VerificationSEV-1
GA-06Real failure buried in the pack04 · Handoff / writeSEV-3
GA-07Control limit quietly widened05 · Change / VersionSEV-1
D · Tenement & permit tracking agents
TP-01Superseded grant read01 · RetrievalSEV-2
TP-02Stale registry extract01 · RetrievalSEV-3
TP-03Clock started on the wrong date02 · DatingSEV-1
TP-04Spend counted to the wrong ground02 · DatingSEV-2
TP-05Evidence does not discharge03 · Evidence matchSEV-2
TP-06Heritage duty reduced to a date04 · Handoff / writeSEV-1
TP-07Rule-set change re-dates quietly05 · Change / VersionSEV-1
E · Logistics & dispatch assistants
LG-01Superseded permit read01 · RetrievalSEV-2
LG-02Stale berth line-up01 · RetrievalSEV-3
LG-03Plan needs a rest rule broken02 · PlanningSEV-1
LG-04Delay stops at the load-out02 · PlanningSEV-2
LG-05Axle limits pass, gross over03 · Limit checkSEV-1
LG-06Stale cargo declaration attached04 · Handoff / writeSEV-1
LG-07Timetable change re-times quietly05 · Change / VersionSEV-1
F · Autonomous fleet & remote-operations support agents
AR-01Boundary live but not marked01 · RetrievalSEV-1
AR-02Stale permission or sign-on01 · RetrievalSEV-2
AR-03Exception mode read as stopped02 · AssemblySEV-1
AR-04Manned unit in the path missed03 · Permission checkSEV-1
AR-05Detection read as complete03 · Permission checkSEV-2
AR-06Alarm volume floods the queue04 · Handoff / writeSEV-3
AR-07Network change untracked05 · Change / VersionSEV-2
G · Process-control & monitoring copilots
PC-01Drifting analyser read as ore01 · RetrievalSEV-2
PC-02Deposition reading read as ordinary01 · RetrievalSEV-1
PC-03Correlation given a direction02 · AnalysisSEV-3
PC-04Proposal built on a stale envelope02 · AnalysisSEV-1
PC-05Permissive not read into the check03 · Envelope checkSEV-1
PC-06Output adds to the operator's load04 · Handoff / writeSEV-3
PC-07Philosophy change untracked05 · Change / VersionSEV-2
H · Commercial, ESG & trading agents
CE-01Provisional read as final01 · RetrievalSEV-1
CE-02Boundary moves under the figure02 · PreparationSEV-2
CE-03Assured and unassured mixed02 · PreparationSEV-1
CE-04Claim with nothing behind it03 · VerificationSEV-1
CE-05Exposure read short of the mandate03 · VerificationSEV-1
CE-06Time-barred claim evidence04 · Handoff / writeSEV-3
CE-07Restatement arrives unmarked05 · Change / VersionSEV-2
I · Tailings storage facility governance agents
DG-03As-built never ingested01 · RetrievalSEV-3
DG-04Superseded trigger level02 · ReasoningSEV-1
DG-06Deviations added, not assessed02 · ReasoningSEV-1
DG-02Old review interval carried03 · Tool / writeSEV-1
DG-05Date received, not conducted03 · Tool / writeSEV-2
DG-01EPRP checked by date only04 · OutputSEV-2
DG-07Silent trigger drift05 · Change / VersionSEV-2
J · Mineral resource & reserve reporting agents
DJ-03Extract taken after the date01 · RetrievalSEV-3
DJ-04Unsupported Table 1 row02 · ReasoningSEV-1
DJ-06Factor extrapolated silently02 · ReasoningSEV-1
DJ-02Movement netted to one line03 · Tool / writeSEV-1
DJ-05Stale consent carried on03 · Tool / writeSEV-2
DJ-01Figure without lineage04 · OutputSEV-2
DJ-07Silent code regression05 · Change / VersionSEV-2
K · Mine closure, rehabilitation & provisioning agents
DK-03Stale disturbance extent01 · RetrievalSEV-3
DK-04Undated unit rate02 · ReasoningSEV-1
DK-06Levy basis reused02 · ReasoningSEV-1
DK-02Provision left behind03 · Tool / writeSEV-1
DK-05Status counted twice03 · Tool / writeSEV-2
DK-01Range and method omitted04 · OutputSEV-2
DK-07Silent rate-set drift05 · Change / VersionSEV-2
L · Water discharge & exceedance certification agents
DM-03Superseded limit value01 · RetrievalSEV-3
DM-04Awareness timed to the inbox02 · ReasoningSEV-1
DM-06Averaging basis misapplied02 · ReasoningSEV-1
DM-02Reportability closed by silence03 · Tool / writeSEV-1
DM-05Sample type not checked03 · Tool / writeSEV-2
DM-01Signatory not on file04 · OutputSEV-2
DM-07Silent limit-rule regression05 · Change / VersionSEV-2
M · Worker exposure & health surveillance record agents
DV-03Superseded sampling plan01 · RetrievalSEV-3
DV-04Coverage read as complete02 · ReasoningSEV-1
DV-06Accreditation checked late02 · ReasoningSEV-1
DV-02Clock started from the file03 · Tool / writeSEV-1
DV-05Refusal held off-record03 · Tool / writeSEV-2
DV-01Notification not raised04 · OutputSEV-2
DV-07Silent clock-rule drift05 · Change / VersionSEV-2
N · Ground control & geotechnical decision-record agents
DW-03Post-processed catalogue01 · RetrievalSEV-3
DW-04Superseded trigger table02 · ReasoningSEV-1
DW-06Design reconciled to itself02 · ReasoningSEV-1
DW-02Zone declared verbally03 · Tool / writeSEV-1
DW-05Notification to a vacant role03 · Tool / writeSEV-2
DW-01Escalation not evidenced04 · OutputSEV-2
DW-07Silent threshold drift05 · Change / VersionSEV-2
O · Mineral royalty return agents
DX-03Certificate never ingested01 · RetrievalSEV-3
DX-04Standard moisture factor02 · ReasoningSEV-1
DX-06Deduction claimed by analogy02 · ReasoningSEV-1
DX-02Vendor-sourced due date03 · Tool / writeSEV-1
DX-05Final pricing never raised03 · Tool / writeSEV-2
DX-01Quantity basis mismatch04 · OutputSEV-2
DX-07Silent schedule drift05 · Change / VersionSEV-2
P · Explosives inventory & licence-currency agents
ED-03Magazine code missed01 · RetrievalSEV-3
ED-04Return booked as receipt02 · ReasoningSEV-1
ED-06Clock started on Monday02 · ReasoningSEV-1
ED-02Count entered as reconciled03 · Tool / writeSEV-1
ED-05Site total nets to zero03 · Tool / writeSEV-2
ED-01Variance never surfaced04 · OutputSEV-2
ED-07Silent licence drift05 · Change / VersionSEV-2
Q · Emergency response & statutory notification agents
EE-03Clock read from the finding01 · RetrievalSEV-3
EE-04Injury reflex applied02 · ReasoningSEV-1
EE-06Window run from submission02 · ReasoningSEV-1
EE-02Back-dated certification03 · Tool / writeSEV-1
EE-05Roster counted, not coverage03 · Tool / writeSEV-2
EE-01Investigators not named04 · OutputSEV-2
EE-07Silent event-class drift05 · Change / VersionSEV-2
R · Minerals supply-chain due-diligence evidence agents
EF-03Ticket never ingested01 · RetrievalSEV-3
EF-04Template default origin02 · ReasoningSEV-1
EF-06Criterion mapped by analogy02 · ReasoningSEV-1
EF-02Prior-year answer reused03 · Tool / writeSEV-1
EF-05Certificate quietly expired03 · Tool / writeSEV-2
EF-01Custody chain breaks04 · OutputSEV-2
EF-07Silent scheme drift05 · Change / VersionSEV-2
Guardrails
Critical guardrails for Mining agents
Ten controls that hold regardless of prompt, plan or pressure. Open one to see what it protects, what trips it, what the agent is forced to do, who may release it, and what is written to the record.
GR-01No agent command to autonomous trucks, drills or trainsOverride defined
Target
Fleet-management and OT command channels for autonomous haul trucks, drills, trains and loaders.
Trigger
Any tool call that would issue, modify or resume a machine mission or command.
Action — enforced
Command is blocked at the gateway; agent may draft mission changes for the autonomy supervisor’s console.
Human override
Autonomy supervisor executes from the FMS console under their own credentials; the agent path stays read-only.
Logged evidenceattempted command · machine id · agent and session ids · gateway verdict · timestamp
GR-02No isolation or ground-control guidance outside controlled proceduresOverride defined
Target
Safety answers — isolation, lockout, confined-space entry, ground control and emergency response.
Trigger
Safety intent with no matching controlled procedure at the current effective revision, in any language.
Action — enforced
Agent refuses to paraphrase, serves the controlled procedure verbatim with revision id, and alerts the site safety office.
Human override
Site safety manager publishes or remaps the controlled document; no ad-hoc textual release.
Logged evidencequery · procedure id and revision · language served · serve or refuse outcome · timestamp
GR-03No market-sensitive resource data released outside disclosure controlsNo override
Target
Exploration results, assay databases, resource models and drafts feeding ASX / JORC announcements.
Trigger
Output channel or recipient outside the named insider list for that project.
Action — enforced
Response is denied and reported to the disclosure officer; agent may quote only published announcements.
Human override
None — cannot be overridden in session
Logged evidencerequested dataset · requester identity · insider-list check result · denial id · timestamp
GR-04No instruction in contractor documents or site reports ever executedNo override
Target
Inbound documents — contractor reports, site inspections, invoices, lab certificates and vendor manuals.
Trigger
Directive or tool-steering content detected inside any retrieved or uploaded document.
Action — enforced
Document is handled as inert data; embedded directives are stripped, quarantined and reported, never executed.
Human override
None — cannot be overridden in session
Logged evidencedocument hash · contractor id · detected directive · quarantine id · timestamp
GR-05No geotechnical alert downgraded or summarised awayOverride defined
Target
Seismic, ground-movement, tailings and slope-stability monitoring feeds and their shift summaries.
Trigger
Summarisation or triage that lowers an alert’s severity or omits it from handover.
Action — enforced
Alert keeps its source severity and routes to the geotechnical engineer; agent may add context, never dispositions.
Human override
Geotechnical engineer closes the alert in the monitoring system with recorded rationale.
Logged evidencealert id · sensor source · original severity · escalation recipient · acknowledgement timestamp
GR-06No resource or reserve statement without competent-person sign-offOverride defined
Target
External-facing text stating tonnages, grades, resources or reserves for any tenement.
Trigger
Draft contains JORC-style figures without a competent person’s recorded attribution and consent.
Action — enforced
Draft is held from every external channel; agent may compile internal workings marked not-for-release.
Human override
Named competent person signs off in the disclosure workflow before any release.
Logged evidencedraft hash · figures quoted · competent person named · consent record · release state · timestamp
GR-07No tailings or discharge reading altered in reportingOverride defined
Target
Environmental monitoring — tailings, water discharge, dust and emissions data feeding regulator reports.
Trigger
Drafted value diverges from the instrument-of-record reading or an exceedance is omitted.
Action — enforced
Submission is blocked; agent must quote instrument values verbatim and flag every exceedance to the environment lead.
Human override
Environmental superintendent corrects data at the source historian; the report then regenerates.
Logged evidencereport id · instrument values · drafted values · exceedance flags · submitter identity · timestamp
GR-08No autonomy-zone change released without field verificationOverride defined
Target
Autonomy boundaries, road closures, speed limits and operating modes in the fleet-management system.
Trigger
Software zone or mode change lacking a matching field confirmation from the ground crew.
Action — enforced
Change stays staged and machines hold current boundaries; agent may schedule the field-verification task.
Human override
Mine controller releases the change after the documented field-verification checklist is complete.
Logged evidencezone delta · requesting identity · field confirmation record · releasing identity · effective timestamp
GR-09No queued mission command replayed after comms lossOverride defined
Target
Command queues and mission buffers spanning network outages, restarts and shift changes.
Trigger
Network restore detected with commands queued before the outage still awaiting execution.
Action — enforced
Queued commands are invalidated, never replayed; agent requests fresh missions reflecting current ground state.
Human override
Autonomy supervisor re-issues each mission manually after reviewing current site state.
Logged evidenceoutage window · invalidated command ids · machine states at restore · reissue identity · timestamp
GR-10No community or heritage communication sent without cultural authorityOverride defined
Target
Outbound communications to Traditional Owners, community stakeholders and heritage regulators.
Trigger
Draft referencing cultural heritage, consent or agreement matters staged for external send.
Action — enforced
Send is held; agent may prepare background material for the heritage and community team’s review.
Human override
Heritage and communities manager sends after consultation with the recognised cultural authority.
Logged evidencedraft hash · recipient · consultation record · approving identity · send timestamp
Oversight
Human review — triggers, decisions and evidence
When a defined risk trigger fires, the affected action is routed to a named reviewer. Every decision is recorded with its correction, escalation and final outcome for full traceability.
- ConfidenceLow-confidence geotech alert
- Financial impactHigh-value procurement
- Identity / change riskContractor competency change
- Irreversible actionAutonomy or isolation change
- Policy riskMarket-disclosure conflict
- Safety controlGuardrail override
- Quality failureFailed critical evaluation
- Revieweridentity + role
- Decisionapprove / reject / amend
- Correctionwhat changed
- Escalationwho, why and severity
- Final outcomereleased / blocked / returned for rework
7 triggers · any one halts the agent
1 record · 5 fields, every time
Compliance
Regulatory mapping
- 01 Goal
- 02 Retrieval
- 03 Workflow
- 04 Task
- 05 Tool
- 06 LLM
- 07 Evaluation
- 08 Guardrail
- 09 Human review
- 10 Outcome
Isolation, permits & procedure currency
Current procedures listed, conductors isolated and tested, confined-space entry permitted, machinery blocked before maintenance; an agent serving superseded text voids each.
Coal Mining Safety and Health Regulation 2017 (Qld) ss 11, 21(3) · Work Health and Safety Regulation 2011 (Qld) s 67 · 30 CFR 56.14105
Lifecycle layer:02 Retrieval · 04 Task · 08 Guardrail · 10 Outcome
- MIN-01
- MIN-02
- MIN-47
- MIN-50
- SF-01
- SF-02
- SF-04
- SF-05
- MP-05
Evaluations
Baseline evaluation suite — in detail
Baseline evaluations are completed during onboarding and repeated based on the selected plan. Agents that fail critical checks remain restricted until they pass re-testing.
- Detailed case sets
- 34
- Failure modes covered
- 50
- Retired & rotated / quarter
- 10%
- Audit-ready scorecard
- Monthly
Output evaluation5 suites · 320 cases
150 casesSafety-procedure groundingcatches MIN-01
60 casesRegulation freshnesscatches MIN-02
100 casesAssay & unit accuracycatches MIN-03 · MIN-08
40 casesPermit-deadline trackingcatches MIN-05
50 casesData isolationcatches MIN-06
60 patternsContractor-doc injectioncatches MIN-07
50 casesDisclosure-boundary probescatches MIN-09
60 casesGeotech-escalation setcatches MIN-10
60 casesFatigue-rule setcatches MIN-11
60 casesEnviro-report fidelitycatches MIN-12
50 casesCompetency-check setcatches MIN-13
50 casesDispatch regressioncatches MIN-14
50 casesCritical-maintenance verificationcatches MIN-04
60 casesWorld-model integritycatches MIN-15
70 casesDegraded-comms & recovery behaviorcatches MIN-16 · MIN-17
60 casesEnvironment & perception limitscatches MIN-18 · MIN-19
90 casesHuman-factors interaction setcatches MIN-20 · MIN-21 · MIN-23 · MIN-26 · MIN-27
60 casesMission-safety interlockscatches MIN-22 · MIN-24 · MIN-25 · MIN-28
80 casesModel drift & reconciliationcatches MIN-29 · MIN-31 · MIN-34 · MIN-36 · MIN-37
70 casesPlan feasibility & life-safety controlcatches MIN-30 · MIN-32 · MIN-33 · MIN-35
60 patternsInput integrity & privilegecatches MIN-38 · MIN-39 · MIN-40
60 casesCommercial-agent reconciliationcatches MIN-41 · MIN-43 · MIN-46
100 casesExternal-content & liability gatescatches MIN-42 · MIN-44 · MIN-45 · MIN-47 · MIN-48 · MIN-49 · MIN-50
Use your work email to unlock the full grid. We use it to send the requested Agent Care material and qualify business inquiries. We do not sell or share your email.
Domain-expert review
Client-designated subject-matter experts review evaluation criteria, pass thresholds and industry-specific risks before baseline approval.
Test-case rotation
Evaluation cases are refreshed regularly to reduce memorisation, limit overfitting and maintain meaningful performance measurement.
Scorecard integration
Scorecards compare results with the approved baseline, show performance trends and flag material declines for review and escalation.
Client-specific extensions
Where included in scope, evaluations may be expanded using approved incidents, workflows, policies, data patterns and industry-specific risks.
Monitoring
Change-aware monitoring
When agent performance changes, Nestack correlates the shift with changes to the agent, prompt, model, tools, knowledge base, guardrails and evaluation suite.
- Week 1 · 98.7%
- Week 2 · 98.6%
- Week 3 · 98.8%
- Week 4 · 98.7%
- Week 5 · 98.9%
- Week 6 · 98.7%
- Week 7 · 98.8%
- Week 8 · 93.7%
- Week 9 · 93.5%
- Week 10 · 98.7%
- Week 11 · 98.8%
- Week 12 · 98.9%
Week readouthover or select
Week 8of 12
- 04Tooltools 11.3
93.7%Procedure-currency rate
- 7 layers stamped on every run · 12-week window
- Catches MIN-25 · fleet-wide software-update failure
Something missing?
Don’t see your agent’s issue here?
Every AI environment is different. Share what you’re seeing, and we’ll review the behaviour, assess the risk and recommend the evaluations or controls that may help.
No commitment. Even if you never become a client, we’ll tell you what we think is happening.
Process
Universal incident runbook
Severity is assigned based on business impact, customer harm, data exposure, operational disruption and overall scope.
- SEV-1 Critical
- SEV-2 Major
- SEV-3 Moderate
- SEV-4 Minor
Automated monitoring or human review identifies unusual behaviour. Alerts are recorded and routed according to severity.
Outcomes
Not just that it ran.
What it delivered.
Observability shows the agent ran. It can’t show the permit condition was met or what the work cost. Where outcome data exists, we trace each result to its session — and a named reviewer signs off the month.
- Issued
- Monthly, per engagement
- Traced
- Every figure to its session
- Signed
- By your engagement reviewer
- Used for
- Client reporting, partner review, the AgentOps scorecard
Nestack AgentOps
Mining fleet · monthly statement
- Work permit issued2,140
- Shift plan approved620
- Environmental reading logged8,940
- Contractor competency verified1,080
- Statutory reports filed5 of 5
- Workflows delivered12,780
- Outcome success rate98.6%
- Human correction required179 · 1.4%
Every figure linked to its source trace · exportable for review and audit support
Cost control
Keep mining AI agent costs under control
Token spend is monitored, optimised and reported as part of Agent Care — and savings never come at the expense of quality, because every change is verified against your evaluation baseline.
We review token spend by agent, workflow, model, and session so you can understand where AI costs are coming from.
Running mining AI agents in production?
Get a free assessment of one agent. We’ll review its behaviour, run a baseline evaluation and highlight potential risks and performance gaps.
Loading open times…
Open times
Select an available date above to view open 45-minute times from our calendar.
