Skip to main content
Product / Alex AI

Ask Alex
anything.

Alex is the conversational layer over QuantumEye. The ninth module, and the one that knows the other eight. Ask the day's questions in plain English. Talk a new automation rule into existence. Alex drafts it, you confirm in the dashboard. Role-aware. Audit-logged. Built on real platform APIs.

16 of 30 intents live todayRBAC enforced server-sideAudit-logged
AAlex · Store Manager · IllustrativeLive
What happened overnight at my store?
search_events
Quiet night. No overnight incidents. • After-Hours Guard was armed overnight • No motion alerts across the active cameras • One scheduled goods-in arrival, whitelisted • All cameras back online before opening
Anything I should look at today?
get_business_intelligence
Two things: 1. Late-afternoon surge looks under-staffed against your daily average, worth checking the roster. 2. A pending watchlist match from yesterday is awaiting your review.
In the product

Ask in plain English. Get an answer, not a search.

Alex turns a question into the right tool call against your live data, then narrates the result, with every action logged.

app.quantumeye.io/search

Ask Alex

AI

Natural-language search across your estate

Illustrative
What happened overnight at Northgate?
search_events3 results · 1 store · 0.4s
A
Alex
Northgate

Quiet night. The After-Hours Guard automation stayed armed from 22:00 and nothing tripped a watchlist or restricted-zone rule. The only movement was the 04:00 goods-in delivery on CAM-02, which was whitelisted, so no alert was raised.

04:02Whitelisted entryCAM-02 · Goods-in
#QE-STAFF · scheduled delivery
Confirmed
04:11Motion · loading bayCAM-02 · Goods-in
Matched the 4am goods-in window
Confirmed
01:47Door held openCAM-05 · Side door
Auto-closed · no person detected
Pending
Role-aware · every action audit-logged
What Alex does today

16 tools, live. Read, draft, and act, with confirmation.

Alex doesn't make answers up. Every response is a call against a real QuantumEye API, search_events, get_individual_profile, draft_rule, update_event_status, approve_theft_for_report and the rest. If a tool returns nothing, Alex says so.

01

Search & investigate events

What happened overnight? Show pending theft events. What's the audit chain on this incident? Cross-referenced with your face graph and prior events.

02

Lookup individuals & watchlists

Tell me everything about person X. Who's whitelisted in the Suppliers group? Is this face on the watchlist? Surfaces profile, history, and last-seen across the estate.

03

Business intelligence

Footfall today vs yesterday. False-alarm rate this week. Detection accuracy week-over-week. The morning brief turned into a chat.

04

Talk a rule into existence

"Set up a PPE alert for the stockroom." "Alert me if more than 8 people queue at the kiosk." Alex drafts a ZoneRule from your sentence, polygon, type, threshold. You confirm in the dashboard before it goes live.

05

Confirm, reject, approve

Confirm a theft or mark a false alarm. Approve a confirmed theft for the police report. Toggle a rule on or off. Every action requires inline confirmation and is server-side RBAC-gated.

06

Reports & notes

Draft the police report for the confirmed concealment, face, clip, audit chain, prior events. Pin an audit-logged note to an event or an individual.

Three illustrative conversations

Ops briefing. Watchlist lookup. A rule, talked into existence.

Each thread maps to a real Alex tool. The interactions below are illustrative wording, the underlying tool calls are exactly what runs in the product today.

AAlex · Area Manager · IllustrativeLive
How are my stores doing today?
get_business_intelligence
Footfall is tracking close to your regional average vs the same day last week. Two stores worth attention: • Store A: a pending watchlist match awaiting your review • Store B: footfall down meaningfully on the same day last week, worth asking the manager why
Show me the watchlist match
Opening the event…
AAlex · Store Manager · IllustrativeLive
Is this person on our banned list?
get_individual_profile
Yes, on your estate watchlist. Prior matches recorded at other sites in your group. Profile and audit chain available.
Draft the police report
draft_report
Report drafted. Face image, clip and prior events attached. Tap to review before forwarding.
AAlex · QE Administrator · IllustrativeLive
Set up a PPE alert for the stockroom.
draft_rule
Drafted a ZoneRule: • Zone: Stockroom (CAM-09) • Type: PPE compliance • Required: hi-vis + hairnet • Severity: warn Review the polygon in the dashboard, then activate.
Also alert me if more than 8 people queue at the kiosk.
draft_rule
Drafted a second rule: • Zone: Tobacco kiosk (CAM-12) • Type: crowd density • Threshold: 8 people • Severity: nudge to floor team
A morning with Alex

30 questions mapped. 16 answered today.

This is the kind of conversation a store manager has with Alex before the doors open. Every reply is a real tool call against your tenant, never a guess. The two at the end are mapped and on the roadmap.

AAlex · A typical morning · IllustrativeLive
Morning Alex — anything happen overnight?
search_eventsLive today
Morning! Quiet one. After-Hours Guard stayed armed all night and nothing tripped across the cameras. The only movement was the 4am goods-in, and that driver's on your whitelist so it didn't raise an alert. Everything was back online before you opened up.
Anything I should deal with first?
get_business_intelligenceLive today
Two things, really. There's a watchlist match from yesterday still waiting on your review, and yesterday's late-afternoon rush ran a bit thin on staff against your usual. Want me to pull either one up?
Is that match someone we've banned?
get_individual_profileLive today
Yes, they're on your estate watchlist, with prior matches at two other stores in the group. I've put the profile and the full history on screen so you can see the chain for yourself.
OK. Confirm the 21:18 concealment as a theft.
update_event_statusLive today
Done, marked as confirmed and logged to the audit trail. I've bundled the clip, the face and the confidence score together. Want me to draft the police report while we're here?
Yes please, draft it.
draft_reportLive today
Drafted. It's got the face image, the clip, and the earlier events tied to that person. Have a read before you send it, nothing goes out until you forward it yourself.
Can you set up a PPE alert for the stockroom?
draft_ruleLive today
Sure. I've drafted a rule for the stockroom on CAM-09 to flag anyone without hi-vis and a hairnet. Take a look at the zone I've drawn in the dashboard and switch it on if it looks right.
How are we doing on false alarms this week?
get_security_analyticsLive today
Trending the right way, fewer than last week, and accuracy's holding steady. I can break it down store by store if that helps.
Which store's had the most theft this month?
cross_store_compareShipping Q3
Mapped and on the roadmap. Alex doesn't answer this one yet.
Are any cameras offline right now?
get_camera_healthRoadmap
Mapped and on the roadmap. Alex doesn't answer this one yet.

16 of 30 mapped questions are answered today. The rest are on a published roadmap, and the full matrix lives in your tenant.

How Alex works

Tool-calling. Not text generation.

Alex doesn't generate answers from a model. Alex calls real platform APIs that you can audit. The model interprets your question, picks the right tool, runs it, and narrates the result. The data is always real.

INTERPRET

LLM picks the tool

Your question is parsed against Alex's tool catalogue (search_events, get_individual_profile, get_business_intelligence, …). The model picks the right one.

EXECUTE

RBAC server-side

The tool runs against the same APIs your dashboard uses. Permissions enforced server-side, a Store Manager can't query another store via prompt injection.

LOG

Every action audited

Every Alex action that touches data writes to the append-only audit log, same chain of custody as a manager clicking a button in the UI.

MODEL

Anthropic Claude

Sub-processor disclosed on the trust centre. Disabled per-tenant on request.

TOOLS

Real platform APIs

Same endpoints as the dashboard. No mock data, no LLM-generated facts.

GUARDRAIL

Confirmation UX

Action-taking calls (status changes, police-report approval, rule toggles) require an inline confirmation step. Never auto-executed.

BACKOFF

Graceful failure

If a tool errors or returns nothing, Alex narrates the failure cleanly rather than inventing an answer.

GDPR & Alex

An LLM in a surveillance product needs a different bar.

Alex is held to the same GDPR commitments as the rest of QuantumEye, and a few extra ones that come with using a model.

01

No PII in the prompt context window

Face vectors, ethnicity codes, and raw video never enter the LLM's context. Alex sees structured tool results, not embeddings.

02

Human-in-the-loop for any write action

Every action-taking Alex call requires an inline confirmation. Status updates, police-report approval, rule toggles, all gated. New rules are drafted by Alex and activated by a human in the dashboard.

03

Sub-processor disclosed

The model provider is on our sub-processor list. Tenants can disable Alex entirely if their DPA forbids it.

04

Same audit chain

An Alex-initiated action is indistinguishable in the audit log from a UI-initiated one, and equally provable.

See Alex run against your real estate.

We can stand up a sandboxed Alex instance against an anonymised copy of your data, so the questions you actually ask are the questions you'll see answered on the demo call.