AI Intelligence

Ask your restaurant anything

Plain-language questions, cited answers computed from your own live data — never made up. Ask in the manager portal, over WhatsApp, through the API, or from AI tools like Claude Desktop connected straight to your restaurant.

Ask the business
What was our highest selling item in September?
Nasi Lemak Ayam — 1,842 sold (RM 23.9k). Next: Mee Goreng Mamak 1,204, Teh Tarik 1,187. Computed from your sales data · SQL shown on tap.
By outlet, please
Bangsar 1,061 · SS2 781. Same question, finer grain — one tap.

Everything included

Questions in plain language

"Best seller in September", "labour % by outlet last month", "top 10 wasted items" — asked the way you'd ask a person, answered with numbers.

Never a made-up number

Every figure in every answer comes from an executed, logged query over your own live data. If it can't be computed, the answer is an honest "I couldn't compute that" — never a guess.

A curated semantic layer

Answers draw only on governed reporting views — sales, labour, covers, inventory variance, loyalty — with business definitions baked in, so "net sales" always means net sales.

Guarded, read-only execution

Generated queries are parsed, restricted to read-only views, scoped to the outlets the asker may see, and time-limited — the engine can look, never touch.

Who, when, what happened

"Who last changed the taco recipe?" "When did Aina start planning the buka puasa event?" — answered from the platform's activity memory, citing the audit record.

Show-your-working answers

Each answer carries the key figures, a compact chart, and a "how this was computed" disclosure — the exact query and views used, one tap away.

Drill down in one tap

Any answer re-runs at finer grain — by outlet, by week, by daypart — so a headline number becomes a breakdown without retyping the question.

Ask from WhatsApp

Message your restaurant's number from the pasar or the school run — same engine, same security, answers in the chat you already live in.

Intelligence API

A clean ask endpoint returning structured answers, plus direct endpoints on the governed views — feed your own dashboards and spreadsheets from the same trusted layer.

Connect your own AI tools (MCP)

Point Claude Desktop or any MCP-capable client at your restaurant's own MCP endpoint and query your business inside your own workflow — token-authenticated, permission-scoped.

Every question logged

Question, query, execution stats and answer recorded per asker and channel, with monthly AI budgets applied — full accountability for every answer given.

PDPA-safe by default

Guest-level personal data stays out of the answer layer by default — aggregates only, with named-guest questions permission-gated and logged.

Questions, answered honestly

From question to cited number

Ask "what was our highest selling item in September?" — the engine writes a query against your governed sales views, validates it as read-only and scoped to your outlets, runs it, and answers with the figures, a mini chart, and the SQL collapsed underneath. Numbers you can defend, because you can see exactly where they came from.

1. Nasi Lemak Ayam1,842 · RM 23.9k
2. Mee Goreng Mamak1,204 · RM 13.2k
3. Teh Tarik1,187 · RM 4.7k
How this was computedView SQL · sales views

Numbers and memory, together

"Who last changed the taco recipe — and did its cost move after?" The memory side finds the change, the actor and the timestamp from the audit trail; the data side queries recipe costs around that date. One composed answer, both sources cited. It's the question every owner asks and no reporting tool can answer.

Changed byFarid · 14 Jul, 4:31 PM
Cost before → afterRM 4.10 → RM 3.85
SourcesAudit record + cost views

Your data, in your own AI tools

Connect Claude Desktop to your restaurant's MCP endpoint with a device-bound token and ask "labour % by outlet last month" mid-workflow — same governed pipeline, same outlet scoping, every call logged. Nothing is reachable without a valid token, and answers never exceed what that person is allowed to see.

Claude Desktop → your MCP endpointConnected
"Labour % by outlet last month"Bangsar 23.8% · SS2 26.4%
ScopeYour outlets · your permissions
Call logRecorded · channel: MCP

Run your restaurant on one platform

Be the first — join the waitlist and get onboarded first, on your own private server.