AIC

Intelligence

Local intelligence, from requirement to report.

CORTEX connects intelligence requirements, retained evidence, analysis, reports, controlled release and feedback in one application. Run it on-premise, in your private cloud or in the public cloud, with local or approved remote AI assistance.

Local intelligence, from requirement to report.

CORTEX connects intelligence requirements, retained evidence, analysis, reports, controlled release and feedback in one application. Run it on-premise, in your private cloud or in the public cloud, with local or approved remote AI assistance.

1.

Agree the question

One representative production case, handling scope, users and required outputs.

2.

See the real workflow

Synthetic requirement to approved release — including the negative cases.

3.

Validate your deployment

Disconnected, restart, restore and upgrade tests against your own criteria.

One connected workspace

From the question asked to the product delivered, nothing is separated from its origin.

  • Requirements

  • /

  • Source authority

  • /

  • Retained evidence

  • /

  • Entity relationships

  • /

  • Structured analysis

  • /

  • Product revisions

  • /

  • Controlled release

  • /

  • Explicit receipt

  • /

  • Recorded feedback

  • /

Evidence, connected


Examine an assessment against the evidence actually used.

01

Original file

The acquired byte sequence, retained with its hash and acquisition context. Quarantine and processing state are real.

02

Retained extraction

A parser output derived from those exact bytes, retained separately so the original is never replaced.

03

Exact citation

A precise retained passage or data cell, with the version and integrity detail needed to find the same material later.

Reprocessing a source does not change an older citation. Amending a report does not reuse approval for different content.

Connected lifecycle

Direction, Collection, Analyse, Product and Feedback in one workspace. A requirement records the question, the decision it supports and the information gaps. Collection is bound to reviewed source authority. Nothing is stranded from the question that caused it.

Requirements carry owner, decision point and due date.

Tasking, attempts and results recorded against exact scope.

Retained revisions preserve context when the question changes.

Connected lifecycle

Direction, Collection, Analyse, Product and Feedback in one workspace. A requirement records the question, the decision it supports and the information gaps. Collection is bound to reviewed source authority. Nothing is stranded from the question that caused it.

Requirements carry owner, decision point and due date.

Tasking, attempts and results recorded against exact scope.

Retained revisions preserve context when the question changes.

Retained evidence

Original files are kept separately from extracted content, with hashes and acquisition context. A citation selects a precise retained passage or cell. Reprocessing a source does not change an older citation.

Original bytes retained with hash and provenance.

Extraction revisions kept alongside the original.

Citations resolve to the exact version actually used.

Retained evidence

Original files are kept separately from extracted content, with hashes and acquisition context. A citation selects a precise retained passage or cell. Reprocessing a source does not change an older citation.

Original bytes retained with hash and provenance.

Extraction revisions kept alongside the original.

Citations resolve to the exact version actually used.

Accountable release

A draft is not a release. Approval binds exact report content, handling restrictions and an eligible internal audience. Contributors cannot approve their own work, a download is not a receipt, and changing content or audience requires a new decision.

Independent approval, separate from authorship.

Genuine PDF, DOCX and structured JSON outputs.

Explicit acknowledgement of the exact package.

Accountable release

A draft is not a release. Approval binds exact report content, handling restrictions and an eligible internal audience. Contributors cannot approve their own work, a download is not a receipt, and changing content or audience requires a new decision.

Independent approval, separate from authorship.

Genuine PDF, DOCX and structured JSON outputs.

Explicit acknowledgement of the exact package.

Requirement

Active

Assess whether the synthetic disruption trend warrants further collection.

Decision point — 14 Mar

Owner — Planning cell

Revision — 3 retained

Direction

Collection

Analyse

Product

Feedback

01

02

03

Connected lifecycle

Direction, Collection, Analyse, Product and Feedback in one workspace. A requirement records the question, the decision it supports and the information gaps. Nothing is stranded from the question that caused it.

Requirements carry owner, decision point and due date.

Tasking, attempts and results recorded against exact scope.

Retained revisions preserve context when the question changes.

Deployment

On-premise, private cloud or public cloud.

CORTEX ships as a signed five-service node: ingress, web application, database, isolated parser and an optional local model. Run it on your own hardware, in your private cloud, or in an AIC-operated Microsoft Azure environment in the UK. Same application, same controls, whichever route you choose.

Disconnected

On-premise or air-gapped

Browser

Local CORTEX node

Application, storage and parser. Optional local model.

External capabilities are blocked before transport. An air-gapped profile ships with the node; physical isolation and disconnected acceptance are confirmed per installation.

Connected

Private or public cloud

Browser

Local CORTEX node

Application, storage and parser. Optional local model.

Approved feeds, map tiles and hosted model endpoints only, under your organisation’s policy. Hosted in Azure UK South with independent environments, or on cloud infrastructure you operate.

Secure by design


Authority is checked at every operation, never assumed from a role.

01

Fail-closed authority

Every content operation needs a current identity, an unexpired grant, workspace membership, a permitting role and the full handling scope, compartments and caveats included. Anything missing, malformed or expired fails closed.

02

Isolated processing

Uploaded files are treated as untrusted. Extraction runs in a separate non-root container with a read-only filesystem, capped memory and CPU, a hard deadline, and no access to database credentials or application keys.

03

Signed and recoverable

Release bundles are signed. Backups are encrypted without staging plaintext, carry a signed manifest, and restore into fresh storage only after signature, hash and image identity checks pass.

Handling labels run from OFFICIAL to TOP SECRET. Versions, actors, timestamps, reasons and integrity hashes are retained for every documented change.

AI, on your terms


Run a pinned local model on the node, or an approved endpoint you control.

01

Local model

A pinned, digest-verified model runs on your own hardware. No automatic download, no substitute model, no cloud fallback. Generation works in both Online and Offline modes.

02

Approved remote model

In Online mode, connect an OpenAI-compatible endpoint you have approved, with protected credentials and a handling ceiling. Tools, retrieval, remote storage and retries are switched off for this workflow.

03

Provenance you can inspect

Each assisted draft records the provider and model, prompt version, source and requirement versions, hashes and the first-draft fingerprint. The analyst reviews and edits before anything is saved.

Model assistance prepares an editable first draft from a bounded, authorised dataset. Review, approval and release stay with people.

Claim discipline

We publish what we can demonstrate. Not what sounds impressive.

Every statement on this page maps to a named, dated piece of project evidence with a stated boundary. Here is the line we hold, and the wording we refuse.

What we will say

Connects requirements, retained evidence, analysis, products and feedback.

Supports local operation without requiring cloud AI.

Retains exact revisions, citations and audit history.

Requires independent approval for exact release content and audience.

Records explicit acknowledgement of a package by a named recipient.

What we will not say

“The only complete intelligence platform.”

“No data can ever leave any deployment.”

“Tamper-proof legal chain of custody.”

“Accredited for any classification level.”

“Automatically produces verified intelligence from any source.”

Operational release acceptance is tracked separately for every deployment. Ask us which gates are still open — we will show you the list.


Recorded evidence, not marketing numbers.

1,646

Tests passed in the current unified pipeline run

105

Browser scenario executions across three configurations

121

Deployment contract checks, recorded separately

Zero

Browser errors or external requests in Offline runs

Each figure is attributed to named, dated evidence with a stated boundary. Totals from earlier baselines overlap and are not added together. Operational release acceptance — including the signed offline node, recovery, upgrade and image assurance — is assessed separately for each deployment.

The questions that decide it.

Direct answers, including where the honest answer is “not yet”.

How is this different from a document repository?

A repository stores files. CORTEX keeps the requirement, the source-use authority, the exact evidence, the analytical judgement, the independent release decision and the recipient's response connected to one another. You can re-open an assessment years later and see the version of the material it was actually based on.

Where can CORTEX run?

On your own hardware, in your private cloud, or in an AIC-operated Microsoft Azure environment in the UK. It is the same signed five-service node in every case. On-premise and private cloud installations can run an Offline policy, including an air-gapped profile, so nothing leaves the site. Public cloud runs Online with only the feeds, map gateways and model endpoints your organisation has approved.

Is it ready for our operational network?

The connected application is implemented and supported by recorded application, database, browser and document-generation checks. Operational release acceptance is tracked separately, including the signed offline node, recovery, upgrade and image assurance. We will tell you precisely which gates are open before you commit to anything.

How does the AI work, and where does our data go?

Model assistance prepares an editable first draft from one bounded, authorised dataset, and the analyst reviews it before anything is saved. You can run a pinned local model on the node, which never calls out, or connect an OpenAI-compatible endpoint you have approved, with protected credentials and a handling ceiling. Offline policy rejects hosted generation altogether. Every draft records the model, prompt version, source versions and hashes.

How is this different from a document repository?

A repository stores files. CORTEX keeps the requirement, the source-use authority, the exact evidence, the analytical judgement, the independent release decision and the recipient's response connected to one another. You can re-open an assessment years later and see the version of the material it was actually based on.

Where can CORTEX run?

On your own hardware, in your private cloud, or in an AIC-operated Microsoft Azure environment in the UK. It is the same signed five-service node in every case. On-premise and private cloud installations can run an Offline policy, including an air-gapped profile, so nothing leaves the site. Public cloud runs Online with only the feeds, map gateways and model endpoints your organisation has approved.

Is it ready for our operational network?

The connected application is implemented and supported by recorded application, database, browser and document-generation checks. Operational release acceptance is tracked separately, including the signed offline node, recovery, upgrade and image assurance. We will tell you precisely which gates are open before you commit to anything.

How does the AI work, and where does our data go?

Model assistance prepares an editable first draft from one bounded, authorised dataset, and the analyst reviews it before anything is saved. You can run a pinned local model on the node, which never calls out, or connect an OpenAI-compatible endpoint you have approved, with protected credentials and a handling ceiling. Offline policy rejects hosted generation altogether. Every draft records the model, prompt version, source versions and hashes.