01
Permission-aware retrieval
Entitlements carried from the source system through indexing and into the answer, so results respect the access rights a user already has.
Retrieval that a security review can actually approve.
An enterprise RAG platform answers from your own documents and records rather than from a general model. Pexon builds retrieval that carries your permission model end to end, grounds every answer in a citable source, and gates each release behind an eval harness so quality does not drift after launch.
The starting point
The demo showed everyone everything.
Retrieval prototypes almost always index a folder and ignore entitlements. That is fine for a demo and disqualifying for production — no security team will issue credentials to a system that cannot express who may see what.
What we build
What the platform includes
02
Grounding and citation
Every answer points at the record it came from, which is what makes it checkable rather than merely plausible.
03
Eval harness
A test set built before the feature, run before each release, so regressions surface in CI instead of in front of a user.
What changes
- People find the existing answer instead of recreating it.
- Answers can be checked against the source, so trust is earned rather than assumed.
- Quality regressions are caught by the harness rather than reported by users.
Where it differs from search
An answer with a source is not the search you already have
Conventional enterprise search returns documents and leaves the reading to you. Retrieval returns an answer and the record it came from — and it can combine several sources into one answer, but only within what the asking user is entitled to see. That last clause is the entire difference between a demo and a deployable system.
The permission model has to travel with the context through retrieval, which means the platform reads entitlements from the source systems at query time rather than snapshotting them. It is the hardest part of the build and the one most platforms do not do — which is why the security review is the gate the platform is designed for.
One corpus, end to end.
We take a single document set all the way through — extraction, masking, indexing, entitlements, evaluation — before adding a second. That is the thread that proves the pattern for everything after it.
Platform questions
How is this different from the search we already have?
Conventional search returns documents and leaves the reading to you. This returns an answer with the record it came from, and it can combine several sources — but only within what the asking user is entitled to see.
What does the eval harness actually test?
A fixed question set with known-good answers, scored on groundedness and correctness. It runs before every release, which is the only reliable way to notice that a model or prompt change made things worse.
Next step
Not a sales call. An architecture call.
Thirty minutes with the architect who would actually run the engagement.