Capability reference

Everything the platform does.

The story is on the main page. This one is the full surface — what Omaya senses, what it works out from that, what it will tell you, and what it will do about it on its own. Written for the reader who wants to check a specific thing rather than be persuaded.

Inputs

What it senses

Omaya reads the signals your building already emits, plus whatever you choose to add. Nothing here requires an app on anyone's phone.

People and assets

Anonymous by default; identified only where you deliberately bind a tag to a person or asset.

  • Bluetooth tags — staff, contractors, trolleys, equipment
  • Radar and presence sensors — headcount in a room and where in it, no identity
  • Door counters — entries and exits at a threshold
  • Unrecognised devices — counted as passing footfall, never identified

Environment

Conditions that decide whether a space is usable, comfortable and compliant.

  • Temperature and humidity
  • Noise level
  • Air quality
  • Leak and supply-level sensors

Building systems

The equipment already installed, brought into the same picture as everything else.

  • Energy meters, down to a single circuit
  • Switches, actuators, lights, air-conditioning and blinds — read and controlled through the smart-home bridge
  • Buttons, panic buttons and call points
  • Gateway health, battery and signal strength
  • Room bookings from your Google or Microsoft 365 calendars

Signals arrive over Bluetooth, Wi-Fi, Matter and LoRaWAN, and over wired links where the equipment provides one. Device families are decoded individually rather than reduced to a lowest common denominator, so a counter reports counts and a meter reports consumption.

Open officeMeeting roomServer roomHall 14 present · 23 °Cbooked 10:00–11:00restricted · armedflow → east radar · 3 31.4 °C ↑ 9° / h nobody present unknown tag Live · one floor
Processing

What it works out

Raw signal is not an answer. Between the sensor and the report, Omaya resolves where something is, how long it stayed and what that means for the space.

Position

Three methods, chosen per venue by what the site can actually support.

  • Presence — which zone heard it best
  • Triangulation — a position from three or more anchors
  • Fingerprinting — matched against a surveyed signal map

Stability

A device on a boundary should not flicker between two rooms all afternoon.

  • Smoothing across successive readings
  • Hysteresis before a zone change is committed
  • Cross-floor penalties so a floor below cannot claim a device
  • Stairs, lifts and escalators modelled, so a path between floors is a real path
  • One zone per device per period, never counted twice
  • Radar checked against a known tag, so the coverage of a sensor is measured, not assumed

Meaning

Derived measures, computed continuously rather than at report time.

  • Dwell — how long a stay lasted, bucketed
  • Occupancy against a zone's capacity
  • Return behaviour — first seen versus coming back
  • Forecast occupancy from observed pattern
  • Habit — where each person usually is, and when each room is usually used
  • Anomalies — a device that broke its own reporting pattern, scored and deduplicated
L5 L4 lift · 2 floors linked Sales · 4Server · restrictedOpen plan · 9 Meeting · 3Training · 1 quiet busy attention same geometry as the wall dashboard · drag to orbit 3D floor plan
A Adib · Staff · badge 3F:2A last seen 2 min ago · Testing Room · Level 4 Locate now → LobbyMeeting roomTesting Room 08:52 09:04 11:20 TODAY · ZONE BY ZONE 08:52 Lobby 4 min 08:56 Meeting room 2 h 08 11:04 Pantry 9 min 11:20 Testing Room 3 h 42 · now L5 Server Room never in 30 days Replay any hour Dwell per zone Return visits Search by person, tag or zone anonymous until a tag is deliberately bound to a person · right to be forgotten built in Entity tracking
Main Meeting Room · today temperature · humidity 58% · CO₂ 640 ppm · noise 41 dB comfort 22–25 °C 30°25°20° 0608101214161820 27 °C alert people 13:30 · 28 °C · empty no alert — nobody to cool 16:40 · 27.4 °C · 5 in alert → facilities, HVAC IF temperature > 27 AND people_count ≥ 1 · proposed by the daily review, accepted by an admin Environment
28Reporting

What it reports

Twenty-eight report types, each answering one question. Grouped here by the question rather than by where they sit in the menu.

Who was here, and where

  • Devices detected — distinct devices per space and day
  • Zone detection heatmap — the same, shaded on the floor plan
  • Zone presence — where time was actually spent
  • Sensor trail — zone-by-zone history for one device or entity
  • People count — live headcount, from counters, radar or tags
  • Room usage map — where in a room people actually stand, from radar
  • Movement flow — which zones feed which, and in what order
  • Enter / exit — crossings at a threshold
  • Gender and entry — where a counter reports it

How long, and how often

  • Dwell time — stays bucketed by duration
  • Device returns — first seen versus returning, by interval
  • Last 24 hours — the day so far, live
  • Distance — separation between devices over time
  • Zone compare — two spaces side by side
  • Compare — any period against another
  • Space utilisation — every zone against its capacity, ranked
  • Impact analysis — what changed after an event you mark

Is the estate healthy

  • Device status — online, stale, offline
  • Battery — level and projected replacement
  • Environment — conditions and threshold breaches
  • Button press — call points and request buttons
  • Alerts — what fired, when, and what followed
  • Webhook dead letter — outbound deliveries that failed

Prove it, and take it away

  • Compliance — evidence against a required standard
  • Meeting room — booked against actually used
  • Custom report builder — pick the table, columns and filters
  • Ask in plain language — describe the report, get the table and chart
  • Export — scheduled delivery to inbox or storage

Every report filters by location, venue, zone and date range, converts timestamps to the site's own timezone, and exports to CSV. Readings that could not be placed in a room are attributed to their venue rather than dropped, so a total never quietly loses rows.

Show me Level 4 occupancy by hour this week against capacity Build it 100%50%0 07 08 09 10 11 12 13 14 15 16 17 18 19 capacity Over capacity 15:00–16:00 Tue, Wed, Thu Table + chart CSV export Schedule to inbox Same data as every report Ask for a report
15Automation

What it does without being asked

A rule watches a measure, decides whether a condition holds, and acts. Fifteen measures can be watched, combined in a condition tree with and/or groups, time-of-day and day-of-week windows.

What a rule can watch

  • People count, enter count, exit count, zone density
  • Dwell time, home-zone status
  • Temperature, humidity, noise, air quality
  • Distance between devices
  • Battery level, device status, signal strength
  • Button pressed, and any custom field you define

What it can do about it

  • Notify by email, SMS, WhatsApp or Telegram
  • Raise a job in your maintenance system
  • Call a webhook, with retry and a dead-letter trail
  • Switch lights, air-conditioning, blinds or any device the smart-home bridge exposes — any service, any entity, targeted by the rule that fired
  • Escalate if nobody acknowledges

Rules can be tested against real history before you arm them, so you find out what a threshold would have done last month rather than next month. The assistant's daily review proposes rules too — you accept one and it opens pre-filled in the rule editor.

Intelligence

What it thinks about

The assistant works from what the platform already knows — every zone, device, rule and reading of one organisation — and is built to explain and propose rather than to act on its own.

OAIA heartbeat every 2 h · last 14 min ago · 1 open ASK Which rooms sat empty this week? Three, all on level 5. Training Room was booked 11 h and occupied 2 h — the rest were never booked at all. Shall I lower its capacity to 12 and release the standing booking? PROPOSED ACTION · NEEDS APPROVAL Training Room capacity → 12 Apply Discard /compact /new · read-only · this tenant only FINDINGS · 1 OPEN Gateway L4-02 silent for 3 h Its two neighbours are fine, so this is the unit, not the network. Dev Room is now blind. critical · new · 14:05ack · snooze · won't fix DAILY REVIEW · PROPOSAL Cool the Main Meeting Room only when used Alert above 27 °C, but only while someone is in the room. Cooling an empty room is the waste. IF temperature > 27 AND people_count ≥ 1 THEN notify Accept Dismiss detectors detect · the model explains · a person approves OAIA console
SECURITY WATCH night shift · 02:14 CRITICAL 1 critical, 1 warning in 2 zones 17/17 armed · 2 present ZONES NEEDING ATTENTION L4 Server room Level 4 Restricted 1 Tag 4 in L4 Server room — never seen there before CRITICAL NewOut of habit · 3m No history in this room in 30 days, none of the room's regulars present, 02:14 on a Sunday. Treat as intrusion until seen. → Send a guard to the zone I'M ATTENDING ACKNOWLEDGE judged by the model · detected by the sweep Guard app

OAIA — the operations assistant

Switched on per organisation from the A.I Model card; off by default.

  • Heartbeat every 2, 4, 6, 8, 12 or 24 hours: gateways offline or weak, ingestion gone silent, batteries, devices off their pattern, environment off baseline
  • Speaks only on change — new, escalated or cleared — and tells every administrator
  • Daily review (1, 2, 3 or 7 days): proposes rules, safety and comfort improvements, configuration fixes — conditioned on sense, such as occupancy before comfort
  • Findings acknowledged, snoozed, reopened or marked won't-fix; cleared ones hidden but kept
  • Chat that knows the tenant, the clock and the asker's role; /compact and /new keep it cheap
  • Approved actions it can draft — venue hours, zone capacity, a rule on or off, a device's zone, finding and suggestion states, plus each app's own — applied only by a person with the permission, once

One assistant, every app

Each app you switch on plugs into the assistant; an app you have not switched on is never mentioned.

  • Hears: security incidents and judgements; bookings beside the hours a room was really used; work orders, assets and their service dates; every toilet's score, cleans and SLA breaches; kilowatt-hours beside occupancy and after-hours draw; connector health and webhook deliveries; visits and hosts; compliance verdicts and calibrations; drills and who was missing
  • Says: each app's week goes into the daily review with its own gaps, and its stalls become heartbeat findings — an incident nobody acknowledged, a calendar that stopped syncing, an urgent order nobody took, a dirty toilet with nobody sent, a bridge that stopped answering, a drill overdue
  • Proposes: whitelist a person or set armed hours; release a no-show booking, tune automatic release, make a room bookable; open, re-prioritise or cancel a work order; dispatch a clean, set a toilet's target or trigger; re-send or pause a webhook; run a compliance assessment or switch a profile — all approve-then-apply
  • Never: closes an incident, books or cancels a meeting, marks work or a clean done, edits a standard, touches a shift, changes an endpoint or a key, or starts, ends or marks a roll call
  • Every app's settings page carries Ask OAIA, and a record — an incident, a booking, a work order, a toilet, a verdict, a drill — can be put in front of the chat from the page it lives on

Autopilot (beta)

The only way the assistant ever changes anything without a person clicking Apply. Off by default.

  • Three switches: the platform makes it available per organisation, the organisation picks Off / Shadow / Act, and turns on tiers — Draft (create proposed rules switched off), Configure (a capacity, a venue's hours, an unassigned device's zone), Operate (cooling on for a hot, occupied room; fans for stale air; lights for people in the dark or a zone with an open critical incident; everything off after the radar says a room has been empty ten minutes or the venue has been closed half an hour with nobody counted)
  • Limits in code: three actions per heartbeat, twenty a day, an hour before touching the same thing again, never flipping a device back within thirty minutes, setpoints inside 20–28 °C; every action listed with Undo; an undo pauses that kind for a day, three in a week drop it to Shadow
  • Its list is fixed and reversible; none of the apps' actions above is on it, however the switches are set
  • Switching it to Act, or making it available to an organisation, asks for confirmation that it is beta and can get one wrong

Security judgement

Inside the Security Watch app, for the guard on duty.

  • Every new incident gets a short assessment and a suggested first step from a fixed list
  • Out of habit: a person somewhere they have never been, or a room in use at an hour it never is and no booking — judged against 30 days of habit, so nobody maintains a list of who may enter where
  • Only an "abnormal" verdict becomes an incident; every verdict is recorded and shown to the administrator
  • Detection itself is deterministic and runs without the model

Where the fence is

The parts that let a customer's security team say yes.

  • One organisation per assistant, through read-only views with the organisation baked in
  • A database account that can only read those views, capped at 200 rows and five seconds
  • Secrets and credentials redacted before the model sees a row
  • No shell, no file system, no other tenant — by construction, then tested with injection, jailbreak and cross-tenant requests
  • Bring your own model key with no cap, or use Omaya's service within a monthly allowance set per organisation
  • The platform can withhold the assistant from an organisation; the organisation can switch it off
Worked examples

Nine chains, end to end

Each of these is the sensing, the judgement, the person and the record from the sections above, joined up. None needs a script; all of them are in the product today.

A washroom gets busy, a cleaner gets sent

Cleaning by traffic, not by clock — and the evidence writes itself.

  1. 38 visits in the last hour door counter on the Level 4 washroom
  2. Dirty score climbs to 82 visits, occupancy, time since last clean, supply levels
  3. Work order raised priority from the score; the recurring schedule steps aside
  4. Cleaner on shift is pushed absent? it falls to the backup tier; stuck orders escalate
  5. Cleaned, score reset, logged the log is the compliance evidence

A visitor finds Room 4.02 on their own

A route on the real plan, across floors, on the visitor's phone.

  1. Visitor checks in invitation on their phone; the host is told
  2. Route drawn on the plan lobby → lift → Level 4 → Room 4.02, doors and walls respected
  3. Across floors the lift and the stairs are real links between plans
  4. Arrives; the meeting checks itself in presence in the room confirms it; no kiosk tap needed

A meeting room is held and never used

Bookings check themselves in from real presence — or release.

  1. Booked 10:00–11:00 from the organisation's own calendar
  2. Nobody by 10:15 radar and tags agree the room is empty
  3. Booking released organiser told; the room shows free on the kiosk
  4. Booked-versus-used report the rooms that are always held and never used, ranked

Heat in an empty server room

Environment, security and facilities in one chain.

  1. 31.4 °C, up 9° in an hour nobody present; the pattern fits a fault or early fire
  2. Critical incident, assessed the guard app turns red with a first step attached
  3. Guard dispatched escalation to named people by email, SMS or WhatsApp
  4. Work order for facilities HVAC check, tracked to completion

A gateway goes quiet

The assistant tells you what, why and what to do — you approve.

  1. Gateway L4-02 silent for 3 hours its two neighbours are fine
  2. OAIA: the unit, not the network Dev Room is now blind; every administrator told once
  3. Swap drafted, a person approves device reassigned from inventory; nothing applied on its own
  4. Coverage back, finding cleared closed automatically on the next heartbeat

Someone is where they never go

Habit is the permission — nobody maintains a list of who may enter where.

  1. Tag 4 in the L5 server room at 02:14 never there in 30 days
  2. Judged, not listed no regular present, no booking, a dead hour → abnormal
  3. The guard's board turns red assessment and first step attached
  4. Resolved: genuine, false alarm or expected "expected" whitelists it for next time

The room runs itself

Occupancy drives the lights, the air-conditioning and the blinds through the smart-home bridge.

  1. Last person leaves the Training Room radar and tags agree; ten minutes pass
  2. Lights off, air-con to setback, blinds closed three services on the bridge, one rule; any device it exposes
  3. Someone walks in at 14:00 and it is 28 °C air-con back on before they sit down
  4. Energy report shows the saving consumption per circuit against occupancy, week on week

A panic button is pressed

One press, the right people, a record of who came and when.

  1. Button pressed in the Level 5 pantry a wearable or a fixed call point
  2. Critical incident, never suppressed no hours, no whitelist, no baseline stands in the way
  3. Guards pushed; named people called SMS, WhatsApp or email per person; the tree is yours
  4. Attended, resolved, timed press-to-arrival in the log for the review

The alarm sounds; who is still inside?

A head count from the badges already in the building, not a clipboard.

  1. Alarm raised the platform snapshots everyone on site, by zone
  2. Assembly point counts them in a gateway at the muster point ticks off arrivals
  3. Missing: 3, with last seen "Adib — Level 4 Testing Room, 2 min ago"
  4. All clear, evidence kept the drill report is the compliance record
By industry

What it does for a place like yours

Ten kinds of place, one platform. Each card is what a site of that kind actually asks for on day one, what Omaya does about it, and one moment from an ordinary day.

Shopping malls

The problem

Tenants ask for footfall you cannot prove, washrooms are cleaned by the clock, and security sees cameras but not patterns.

What Omaya does
  • Footfall, dwell and flow per floor and zone — the numbers that justify a tenancy or a promotion, from the gateways already in the ceiling.
  • Washrooms cleaned by traffic: a dirty score from visits and supply levels raises a work order and pushes the cleaner on shift.
  • Security Watch for loading bays, plant rooms and after-hours floors; a lost-child or panic press reaches the guards in seconds.

For exampleSaturday 15:10 — Level 2 food court at 92% of capacity, the L2 washroom score hits 80 and a cleaner is dispatched, the security board stays green.

Theme parks & attractions

The problem

Crowds move faster than radios, queues overflow into walkways, and a missing child is a park-wide search.

What Omaya does
  • Live density per queue and plaza on a wall screen, with alerts before a zone reaches its safe capacity.
  • Wristband tags locate a guest or a group in seconds; roll call at a gathering point during an evacuation drill.
  • Outdoor heat and noise watched per zone, so shade, water and staff go where the readings say — and the record proves it.

For example14:40 — the coaster queue crosses 85% and the plaza reads 34 °C; the ride team is paged, misting is switched on, and the operations log shows both.

Offices & corporate campuses

The problem

Meeting rooms are booked and empty, desks look full on the plan and are not, and the air-con runs for nobody.

What Omaya does
  • Booked-versus-used for every room; a booking nobody arrives for is released and the organiser told.
  • Lights and air-conditioning follow occupancy through the smart-home bridge — off ten minutes after the last person leaves.
  • Visitors check in on their phone, the host is told, and a route to the room is drawn across floors; the AI assistant reviews the site daily and proposes what to automate next.

For example10:15 — Training Room booked since 10:00 and still empty, so it is released; at 18:20 its lights and AC switch off on their own.

Hotels & resorts

The problem

Guest flow is felt, not measured; function rooms run climate for empty hours; housekeeping and security learn of problems late.

What Omaya does
  • Lobby, F&B and pool-deck occupancy by hour, so staffing and buffets match the guests who are actually there.
  • Function and banquet rooms: booked-versus-used, and climate setback the moment a room empties.
  • Staff panic buttons and after-hours presence reach security; trolleys and luggage carts are tracked; washrooms are cleaned by traffic.

For example22:30 — the ballroom emptied at 22:05, so its air-con dropped to setback; a housekeeper's panic press in the L8 corridor reached the guard app in four seconds.

Medical centres & hospitals

The problem

Equipment is searched for instead of used, visitors get lost, waiting areas overflow, and compliance evidence is assembled after the fact.

What Omaya does
  • Infusion pumps, wheelchairs and beds located in seconds; an asset that leaves its home zone raises an alert.
  • Waiting-area occupancy and wait time live on a screen; visitors are routed to the right clinic on their phone.
  • Pharmacy cold-chain and air-quality readings kept as compliance evidence; restricted rooms watched; call points for staff.

For example09:20 — Clinic B waiting area at 28 with an average wait of 41 minutes, so a second counter opens; a wheelchair leaving Ward 3 without a porter is flagged.

Retail stores

The problem

Sales are counted; the people who did not buy are not. Layout changes are argued about instead of measured.

What Omaya does
  • Entries and exits per door, dwell per display, returning versus first-time visitors — conversion with a denominator.
  • Compare this week to last after a layout change; heatmaps show the cold corner before the stock does.
  • Chiller temperature and store air quality kept as evidence; staffing set by the real peak hour, not the assumed one.

For exampleWeek 37 — the new endcap raised dwell in Zone C by 38% with no change in entries; the compare report goes to the merchandising meeting as-is.

Education

The problem

Lecture halls are timetabled at capacity and half full, labs are used after hours unseen, and a fire drill is a clipboard.

What Omaya does
  • Utilisation per hall and lab against the timetable, so scheduling follows how rooms are really used.
  • Roll call from the badges already on campus when the alarm sounds; who is missing and where they were last seen.
  • Lab CO₂, noise and after-hours presence watched; lights and air-con off in empty rooms.

For exampleTuesday 11:00 — Hall A timetabled for 200 holds 68 for the fourth week; the space report proposes moving the class and freeing the hall.

Event & exhibition centres

The problem

Headcount is a turnstile total, not who is in which hall now; exhibitors want dwell they cannot get; navigation is signage.

What Omaya does
  • Live headcount per hall against capacity on a wall screen, with alerts before a hall is full.
  • Movement flow between halls and dwell at booths, reported per exhibitor.
  • Attendees routed to a booth or a session on their phone; incidents and crowding reach the security team as they happen.

For example13:05 — Hall 3 at 96% and rising, so entry is paused at the north door and the flow report shows the crowd coming from the keynote.

Manufacturing & warehouses

The problem

Tools and trolleys go missing, lone workers are out of sight, and heat and noise limits are checked on a form once a year.

What Omaya does
  • Assets, forklifts and tools located on the plan; an asset that moves after hours or leaves its zone raises an incident.
  • Lone-worker check-in, panic buttons and restricted plant rooms handled by Security Watch.
  • Temperature, noise and air quality per zone against the standard, kept as compliance evidence; a sensor gone silent is an alert, not a surprise.

For example02:10 — a pallet trolley leaves Bay 4 after hours and the night guard is dispatched; the noise report for Line 2 is ready for the audit.

Smart buildings & facility management

The problem

Many sites, many dashboards, and energy spent on rooms nobody is in.

What Omaya does
  • One view across sites: occupancy, environment, device health and work orders, each tenant's data kept separate.
  • Energy per circuit against occupancy, so waste is visible as waste; lights, air-conditioning and blinds driven by presence.
  • The AI assistant checks every site on a heartbeat, explains what changed, and proposes the next rule; lobby screens show the building live.

For exampleMonday 08:00 — the assistant reports a gateway swapped overnight, two rooms cooled while empty last week, and a draft rule to fix it awaiting approval.

13Integration

What it connects to

Bringing data in

Gateways and bridges speak to Omaya over whichever transport they support.

  • Message-broker, HTTP, TCP and UDP gateway endpoints
  • Smart-home bridge: read any entity it knows, and switch lights, climate and covers back through it
  • Twelve-plus gateway makes supported out of the box
  • Auto-discovery of devices a gateway starts hearing
  • Google and Microsoft 365 calendars for room bookings
  • Your identity provider for administrator sign-in, with group-to-role mapping

Sending it out

Alerts, exports and events, to where your team already works.

  • Email, SMS, WhatsApp, Telegram
  • Outbound webhooks with signed payloads
  • External maintenance and CMMS systems
  • Object storage for scheduled report delivery
  • Wall-mounted dashboards for a floor or lobby, including a live 3D floor plan
  • A public API with interactive documentation
Modules

Ready-made for a specific job

The platform underneath is the same. These are pre-built for problems common enough to be worth solving once.

Meeting rooms

Booked against actually occupied — find the rooms held and never used, and free them.

Washroom hygiene

Cleaning triggered by traffic rather than by clock, with supply levels and leak detection.

Energy

Consumption per circuit against occupancy, so waste is visible as waste.

Facility requests

Button and app requests routed to whoever handles them, tracked to completion.

Lobby dashboards

A screen showing live occupancy, air quality or availability, without a login — including a live 3D floor plan.

Security Watch

For the security team: armed hours, restricted zones, panic buttons, heat that looks like fire, coverage lost, and out-of-habit presence judged by AI. Guards get a phone app with a one-glance board; escalation goes to named people by email, SMS or WhatsApp.

Roll call

Emergency muster: a snapshot of everyone on site, who has reached the gathering point, and who is missing.

Visitors

Registration, check-in and check-out, host notification, and a visitor app the organisation brands as its own.

Compliance

Evidence against a required standard, collected as it happens rather than reconstructed later.

Operations

How it runs

Separation

  • Each customer's data in its own store, not a shared table with a filter
  • Roles and per-page permissions
  • Every administrative action recorded in an audit trail
  • Retention windows you set, enforced automatically
  • Single sign-on per organisation; direct login can be switched off
  • A usage page per organisation: AI allowance, SMS, WhatsApp, email, webhooks, alerts — with failures listed

Keeping itself current

  • 64 scheduled background tasks, from ingestion to report rollups
  • Gateway health watched continuously, offline raised as an alert
  • Forecasts and aggregates rebuilt on their own schedule
  • Failed outbound deliveries retried, then surfaced rather than lost

Reach

  • Interface in English and Malay, with six further locales in progress
  • Right-to-left layouts supported
  • Each site keeps its own timezone; reports convert to it
  • Works on a phone, a desk browser and a wall screen

Not sure which part you need?

Most sites start with one question — a floor that feels crowded, rooms nobody can book, a cleaning round on the wrong schedule — and grow from there.

Back to the overview What's new