APMS.ai

Deep-dive on ONE machine: its current live status + product, and over a period its output, run hours, availability, full time breakdown and most recent stops. Use for 'how is Tube Mill-3 doing', 'status of CNC-12', a single-machine snapshot. Required: machine (name or id); optional: date_range, top (recent stops).

machine_detail

Machine HEALTH PARAMETERS: sensors (temperature, pressure, vibration…), running time since service, manual readings, status signals, counters and energy/flow meters. view=now (default): each parameter's current value, unit, safe/reserve/critical limits and zone; a reading not updated for 15+ minutes is marked stale (last known, not current). view=history: min/avg/max, running hours, counts, time per status, meter use, reserve/critical minutes and resets over a period. view=trend: the READINGS OVER TIME for a graph — name one machine and ONE parameter. Use for 'temperature of X now', 'which parameters are out of range', 'graph of the gearbox temperature this week', 'when was the counter reset'. For which parameters deviated most across the plant use health_analytics; for components shared by several machines use shared_health_analytics.

machine_health

List the machines this user can see with their CURRENT live status (running/idle/stopped/off/maintenance/etc.) and current product. Use for 'what are my machines', 'which are running right now'. Optional 'query' filters by machine name. For rankings/trends/OEE use the analytics capabilities instead.

get_machines

Plant-wide machine analysis: live status mix, top-producing machines, and which machines need attention (stopped/off/maintenance). Use for 'how is the plant', 'which machines are down/idle', 'top machines by output'. Optional: top, date_range. For one machine in depth use machine_detail; for availability/OEE use oee_analytics.

machine_analytics

Maintenance (preventive PM / breakdown). Answers 'what maintenance is due or overdue', 'open work orders', 'maintenance history for a machine', 'who did the most maintenance', 'recurring breakdowns / root causes', 'low/needed spare parts'. Optional: focus (summary|due|history|technicians|recurring|spares), date_range, machine, horizon_days, top. For one work order's details, its checklist or its photos use maintenance_details.

maintenance_analytics

Individual MAINTENANCE requests / work orders (preventive PM and breakdown BDM) with their details and PHOTOS: cause or PM form, schedule, who was assigned, status, overdue days; the work done — who did it, start/end, duration, early/on time/delayed, remarks, corrective measures; for one request its checklist (done, functional, comments, spares used); and cancellations. Photos are download links — give each as a Markdown link; never embed them or add web or generated pictures. Use for 'show maintenance details with photos', 'what was done on Tube Mill 3's breakdown', 'open work orders', 'details of MSR0012'. For counts, due lists, technician workload or recurring faults use maintenance_analytics.

maintenance_details

OEE and machine utilization over a period: availability (run vs operational time) for every machine, performance and quality where the data exists, full OEE when all three are available, plus the plant time breakdown (run/interrupt/wait/setup/idle/maintenance/off). Answers 'OEE', 'availability', 'where is time being lost', 'best/worst machines by availability', and with trend=true 'availability graph / trend over time'. Optional: machine (one machine), date_range, top, bottom (true for worst), trend, bucket. To rank machines against the plant's own median and best use machine_benchmark.

oee_analytics

Operator HMI login attendance over a period — total logins and how many were LATE (after the shift's scheduled start time), with each operator's phone number and employee id so the user can follow up/call them. Answers 'who logged in late this month', 'who was late and give me their number', punctuality/attendance. Optional: date_range, grace_minutes (default 5), late_only (default true), top.

operator_attendance

List the operators assigned to this user's machines and whether each is currently logged in. Use for 'who are my operators', 'who is on shift now'.

get_operators

Operator performance over a period — output, logged-in hours and downtime attributed to each operator. Answers 'top/lowest operators', 'who produced most', operator comparisons. Optional: by (produced|login|downtime), date_range, top, bottom.

operator_analytics

WHY the PRR score is what it is: each KPI's score across every scored cycle, ordered WEAKEST FIRST, with attainment and average actual vs target where the KPI has a numeric target. Use for 'why is our score low', 'which KPI is dragging us down', 'where are we losing points', 'KPI performance breakdown'. Optional: top (default 15), machine, date_range or start_date/end_date. Scores only — carries no reward points.

prr_kpi_breakdown

PRR performance score as a timeline — one point per day, week or month. Use for 'is our score improving', 'score trend', 'how did performance move this quarter'. Optional: bucket (day|week|month, default day), machine, date_range or start_date/end_date. Scores only — carries no reward points.

prr_score_trend

PRR performance SCORES for the unit over a period, ranked. Answers 'how did we score', 'best/worst performing machines', 'top operators', 'which team scored highest', 'which role is underperforming'. Returns the unit's consolidated score, the same score for the immediately preceding window, and a ranking. Required: none. Optional: by (machine|operator|team|role|level, default machine), top, machine, date_range or start_date/end_date. IMPORTANT: this is the SCORE flow — it never returns reward points, budget, earned/earnable amounts or wallet balances, and those cannot be derived from it.

prr_score_analytics

Compare THIS period against the immediately-preceding equal-length period — production, run hours, downtime and availability, with the change and % change. Answers 'is this month better than last', 'how does this week compare', period-over-period trend. Optional: date_range (the current period).

period_compare

Executive plant summary over a period — production output and run hours, live machine status mix, plant availability, time breakdown, and the top products + top downtime causes. Answers 'how is the plant doing', daily/weekly/monthly summary, executive report. Optional: date_range. Start here for 'how is the plant doing'; drill down with production_analytics, downtime_analytics or oee_analytics.

summary_analytics

List the products configured on this user's machines. Optional 'search' filters by product name. Use for 'what products do we run'.

list_products

Production totals, rankings and trends over a period — answers 'top/lowest products this month', output by machine/operator/shift, comparisons and production trends / graphs over time. Optional: machine (one machine), by (product|machine|operator|shift), date_range, top, bottom (true for worst), trend (true for a time series), bucket (hour|day|week|month). For output per hour use production_pace; split by shift use shift_performance; against the previous period use period_compare.

production_analytics

Output PACE — units per hour per machine and plant-wide, plus performance vs the ideal cycle time where configured. Answers 'are we on track today', 'production rate', 'how fast are we running'. Optional: machine, date_range (default today), top.

production_pace

Quality deep-dive: which quality PARAMETERS went out of range (by lost time and event count), which MACHINES deviate most, and each machine's first-pass yield from produced-vs-scrap. Answers 'quality problems', 'which parameter is out of spec', 'first pass yield', 'which machine has the worst quality'. Optional: top, critical_only (excludes reserve-band deviations), machine, date_range or start_date/end_date. For scrap as a percentage of raw material use material_scrap_analytics; for rejected pieces by reason use rejection_analytics.

quality_analytics

The most recent stoppages (latest first) with machine, reason, duration and time. Answers 'what are the latest stops', 'recent breakdowns', 'why did things stop today'. Optional: machine (name/id; omit for all), date_range (default this_week), top. For totals by reason use downtime_analytics; for a stop's photos, voice notes and comment use stop_details.

recent_stops

REJECTED PIECES entered on the HMI (the rejection flow) — totals, setup vs production, the rejection rate (rejected ÷ pieces counted, piece-counted products only), a breakdown by reason, category, product, machine, operator, shift or phase, the latest entries with their reasons, comments and photo links, and with trend=true a graph over time. Use for 'rejections today', 'top rejection reasons this month', 'rejection rate of product X', 'who rejected most', 'show the latest rejection entries'. Not scrap (material_scrap_analytics) and not quality-parameter deviations (health_analytics kind=quality). Default this month (last 7 days for a trend). Photos are download links — never embed them or add web or generated pictures.

rejection_analytics

Machine reliability: MTBF (mean time between failures), MTTR (mean time to repair), failure count, downtime and run-vs-stop % per machine, ordered LEAST RELIABLE FIRST. Answers 'which machine breaks down most', 'MTBF/MTTR', 'reliability report', 'what should maintenance prioritise'. Every stop except machine-raised (system) alarms counts as a failure. run_vs_stop_pct is not OEE availability — for availability use oee_analytics. Optional: top, machine, date_range or start_date/end_date. For which reasons cause the downtime use downtime_analytics.

reliability_metrics

Scrap and raw-material use over a period, with SCRAP PERCENTAGE: scrap ÷ raw material used × 100 in the raw material's unit (e.g. 0.2 kg scrapped of 1 kg used = 20%). Returns the overall scrap %, scrap % per machine or per product (worst first), the top scrap types and raw materials used with their units. A group whose units cannot be compared is reported as not measured, never as 0%. Answers 'what is our scrap %', 'which machine/product has the most scrap', 'scrap by type', 'raw material consumed'. Optional: by (machine|product|scrap_type|raw_material, default machine), machine, top, date_range or start_date/end_date. For quality-parameter deviations and first-pass yield use quality_analytics; for rejected pieces by reason use rejection_analytics.

material_scrap_analytics

Product SETUP / changeover time — which products or machines take the longest (or shortest) to set up, plant setup totals, and how setup time is trending. Answers 'which products take longest to set up', 'setup time by machine', 'is our changeover time improving', 'setup trend'. This is a DIFFERENT thing from downtime (setup is planned configuration time, not a failure). Optional: by (product|machine, default product), machine (filter one), top, bottom (true for shortest/fastest), trend (true for a time series), bucket (hour|day|week|month).

setup_analytics

Shared-health pools — components shared across several machines, where one counter is consumed by many contributors. Returns each pool, its member machines, which member is consuming it fastest, and which members are paused. Answers 'shared health pools', 'which machine is wearing out the shared component', 'pool status'. Optional: machine, date_range or start_date/end_date. For one machine's own parameters use machine_health.

shared_health_analytics

Performance split by SHIFT over a period — output, run hours, availability, downtime and stops per shift. Answers 'which shift performs best', 'compare shifts', 'shift-wise production/downtime'. Optional: date_range.

shift_performance

Individual machine stops WITH what people attached to them: the comment, PHOTOS and VOICE NOTES (audio), plus the stop's reasons (machine-raised, acknowledged, authorised), times, operator, shift, product and who authorised it; includes a stop still running. Use for 'show me the photos of the breakdown on Tube Mill 3', 'any pictures or audio for yesterday's stops', 'what did the supervisor note about that stop'. Every photo and voice note is a download link (valid 24 hours): give each to the user as a Markdown link with its file name; never embed it or add web or generated pictures in its place. By default only stops with photos or voice notes, latest first, this month. For totals by reason use downtime_analytics; for just the latest stops and their reasons, recent_stops is lighter.

stop_details

WHEN downtime happens — stop minutes and event counts by hour of day or by day of week, with the worst slot called out. Answers 'when do we lose most time', 'is there a pattern to our stoppages', 'which hour/day is worst', 'do stops cluster around shift change'. Optional: grain (hour|weekday, default hour), machine, date_range or start_date/end_date. For which reasons cause the downtime use downtime_analytics.

stop_pattern_analysis

Forecasts likely stoppages for what is running NOW or planned for TOMORROW (or a date), from each machine's own history: expected stops and downtime in the planned hours, the most likely stop reasons with the chance of each, the hours it usually stops, health parameters out of range now or recently, and maintenance due or overdue, with a high/medium/low risk per machine. Answers 'what stoppages can I expect today/tomorrow', 'which machines are at risk', 'how do I avoid stoppages in the next run'. Use the evidence to recommend preventive actions. Optional: when (now|tomorrow|YYYY-MM-DD, default now), hours (for now, default 8), machine, lookback_days (7-90, default 30), top.

stoppage_forecast