Products

Ask anything. Trust the answer.

One brain, limitless ways to use it. Kadura Meridian is our flagship platform: the standard way into the brain, and part of every deployment. The connector brings the same brain into Claude and ChatGPT. On the same brain we build tooling shaped to your operation alone, and whatever else your world needs.

Part one

Meridian.

The same in every deployment, working from day one. Six capabilities over one model, so an answer, a report, a dashboard and an agent all draw on the same evidence and reach the same figure.

Ask.

Put any question to the brain and get a direct answer, with the source and confidence attached. When it does not know, it says so and states what it would need.

Example record

Which site held the most stock of this component last week?

Site 2: 18,400 units

07 · The evidence

Why you should believe it.

The six answer what Meridian can do for you. Three more answer why you should believe it, and they ship with every deployment.

ExploreWalk the entity graph directly, rather than through a question.

GapsWhat the brain knows it does not know, ranked by how much it matters.

AuditEvery run, every cost, every action, across Meridian and any tooling built on your brain.

On the record

Part two · The connector

The same brain, inside Claude and ChatGPT.

Your people already use Claude or ChatGPT. The connector lets them put questions to the brain from there: records, figures, documents and the knowledge graph, answered by the same tools and the same checks as Ask. It is built on the Model Context Protocol, the open standard both apps use for connectors.

How it connectsOne web address, pasted into Claude or ChatGPT. People sign in with their normal Kadura account and their usual authenticator code. No new password, no API key, no shared token. One consent screen, the first time only.

What it answersTotals, counts, rankings and breakdowns from your records. Your own defined measures, computed from the definition you set. Documents searched by meaning, with citations. How things connect in the graph. A complete listing as an Excel file when you need one.

It reads, never writesNothing reached through the connector can change or delete your data. The one exception is Excel export, which writes a new file into your own storage.

The same permissions, exactlyThe connector is not a second door with its own rules. What a person can see in Meridian is exactly what they can see through Claude or ChatGPT, and nothing more. Every request runs as that person, under their own role, their own permissions and their own document clearance. If a set of data is closed to them in Meridian, it stays closed here, and a document above their clearance is never returned.

Under your administratorsWhich apps may connect, which roles may use it, and an off switch that takes effect within a minute. A person's access can be withdrawn on their next request. Every request is logged: who, which tool, which app, when. Never the question itself.

Agents, tooAny agent can be connected on its own, carrying its instructions, its private files and its skills into Claude from the first message. One sign-in covers all of them, and disconnecting one leaves the rest untouched.

What travels with every figure

The filters applied, how many rows it rests on, whether one row dominates, whether the list is partial, and a check verdict: corroborated, self-consistent, contested, single-source, or settled by a person. The honesty rules are handed to the app at the moment it uses a tool.

Where it stops

Answers go to the AI app your people use, under that provider’s terms, and your administrators decide which apps are allowed. Kadura supplies the data, the rules and the checks. Claude or ChatGPT writes the final sentence.

Live in production with both Claude and ChatGPT. They are the defaults, not the limit. If your people work in any other AI application that supports connectors, we will build one for it, and it comes under the same permissions and the same administrator controls.

Optional in every deployment, in our cloud or on your own server. Switching it on is configuration, not a project.

Where the standard ends.

Meridian and the connector are the same in every deployment. Some work is best done through something built to fit your operation and the way your people work, and that is what tooling is for.

Part three · Tooling

Built for your operation alone.

The differenceMeridian gives every business the same six capabilities, and that covers most of what a business needs to ask. Some work is best done through something built for it: a screen shaped to the way the yard team works, a calculator sales runs on every quote, a console that writes back into the systems you already have. That is what tooling is for.

What gets builtTooling built to fit your operation and the way your people work, on the same brain: whatever a team needs to do its job well, in the form that suits the job. A credit cockpit for the finance team. A shipment console for the yard. A production board for the factory floor. A pricing calculator for sales. Proof of range rather than a catalogue: if it can read from the brain, it can be built on it.

Today

We build them with you: shaped to the job, reconciled exactly against the data underneath.

Describe a tool in plain language and get a real one back, built over your brain and governed the same way.

The safety model bounds what a tool can reach, not what it can express. Every call runs under the viewing person’s own clearance, and the tool never holds a credential.

The brain is the foundation. What stands on it is up to you.

See what a brain of your business would look like.

Tell us about your business Why you can trust a number