Can it work on our raw database?

Technically yes, usefully no. Pointed at raw tables it will produce plausible numbers that disagree with your reports. The semantic layer is the difference between a demo and a system people trust.

Does it replace our BI platform?

No. It sits beside it and answers the ad-hoc questions that currently arrive as a request to the BI team.

Logistics & Mobility · Ask your data

Supply-chain questions answered on the spot

Ask a question in Arabic or English and get the number, with the query behind it.

Book the Data Foundation Assessment

Questions answered without an analystQuery accuracy against certified metricsTime from question to answerReporting backlog

The problem

What this fixes

On-time performance, cost per drop and carrier comparison questions all require an analyst, so weekly reviews argue about definitions.

A natural-language layer over a governed semantic model: the question is translated into a query against certified metrics, the answer shows the SQL and the source, and permissions follow the user. The governance work is the product, without a semantic layer, natural-language analytics produces confident, inconsistent numbers.

Logistics & Mobility

On-time and in-full

One definition across operations, commercial and the customer report.

Logistics & Mobility

Cost to serve

By lane, customer and vehicle type, answered directly.

Logistics & Mobility

Carrier performance

Comparable metrics for the negotiation, not the anecdote.

Logistics & Mobility

Exceptions in plain language

Ask what went wrong yesterday and get the query behind the answer.

In this sector

Where it earns its place

Delivery

How we build it

Foundation check

Before any build

We inspect the systems, the data behind them and the quality of the records this capability will depend on, then write down what has to be fixed before anything is built.

Narrow first release

First release

One workflow, one team, real traffic, measured against the baseline we captured before we started.

Controls and evaluation

Runs in parallel

Guardrails, approval gates, evaluation sets, logging and the evidence pack your auditor and your regulator will ask for.

Scale and hand over

After sign-off

Additional workflows, sites or languages, then runbooks and training so your team can operate it without us.

Data foundation

What has to be right first

A modelled warehouse or lakehouse, not raw source tables.
Certified metric definitions with named owners.
Row- and column-level security already enforced.
A bilingual business glossary.

Controls

Guardrails and KPIs

Every action is logged and replayable

Inputs, retrieved context, model version, output and the human decision are written to an immutable log, so an auditor can reconstruct any single interaction months later.

Data stays where your regulator requires

In-country, in-region or on-premise deployment, with the model portfolio right-sized to the workload instead of routing everything to a frontier endpoint abroad.

Accuracy is monitored, not assumed

A held-out evaluation set runs on every model or prompt change, with drift alerts and a documented rollback path when quality moves.

A human owns every consequential decision

Agents draft, route and execute reversible steps. Anything that moves money, changes a record of consequence or affects a person's rights stops at a named human approver with the reasoning attached.