Context everywhere
One business memory. Every AI you choose.
One understanding of the business — its relationships, history, decisions, and evidence — delivered through the Percidian Gateway to the commercial assistants, internal agents, embedded applications, and automated workflows your policy approves, without rebuilding integrations, permissions, or memory for each one. The model can change; the memory does not.
The Gateway
What an approved destination receives — and what an unapproved one does not.
Approve a destination and it receives the governed context for the request — identity, permissions, and evidence intact. An unapproved destination receives no context, no summary, and no metadata.
Destination policy
4 of 5 approved
One policy; every request to an approved destination inherits it.
- Commercial assistantThe tool people already open
Receives · governed context for the request
- Identity
- Permissions
- Destination policy
- Provenance
- Internal agentRuns the work for a person and a task
Receives · governed context for the request
- Identity
- Permissions
- Destination policy
- Provenance
- Embedded applicationAn AI feature inside your software
Receives · governed context for the request
- Identity
- Permissions
- Destination policy
- Provenance
- Automated workflowLong-running, unattended
Receives · governed context for the request
- Identity
- Permissions
- Destination policy
- Provenance
- New AI toolNot yet reviewed
Receives nothing — no context, no summary, no metadata.
4 approved destinations receive governed context, scoped to the requester. 1 not approved receives nothing.
Change the AI, keep the understanding
Your institutional knowledge should not be trapped inside an assistant.
Models improve. Applications change. Teams adopt different tools for different work. Percidian keeps the organization’s understanding independent of the model or interface consuming it — so a new assistant, agent, or model endpoint inherits what the business already knows instead of starting from nothing.
- One institutional memory across AI products
- Consistent business definitions and domain meaning
- Shared source connections and evidence
- Common permission enforcement
- Portable context across model changes
Context shaped for the request
This user. This task. This moment. This approved destination.
Percidian does not send a static company dump to every model. It assembles the relevant authorized view of the business for the request.
Who is asking
Identity, group, role, delegation, and source access.
What work is being performed
Matter, transaction, client, workflow, objective, and purpose.
What matters now
Current relationships, history, decisions, changes, and evidence.
Where context may go
The approved AI system, application, agent, or model endpoint receiving it.
Four outcomes
The same understanding, whichever AI does the work.
Consistency
Every approved AI system uses the same business vocabulary, relationships, current state, and evidence.
Control
Context leaves Percidian with identity, permissions, destination policy, and provenance intact.
Choice
Use the model and application suited to each job without fragmenting the knowledge beneath them.
Efficiency
Reuse understood context instead of repeating source processing and retrieval inside every AI product.
One governed path
Approve once. Every experience built on it inherits the standard.
One place to decide which destinations may receive enterprise context; every new assistant, agent, or application inherits the same identity, permission, and evidence rules.
How each access decision is made: Permissions & governance. Delivery interfaces: Developers. The product: Percidian Gateway.
Percidian Gateway
One destination policy, one delivery path — identity, permissions, and evidence travel with the request.
- Commercial assistants
- Internal agents
- Embedded applications
- Automated workflows
- APIs and MCP
Bring your business into every AI decision
Give every approved AI system the context to do its best work.
Connect the knowledge your organization already has. Preserve what it learns. Apply the permissions it already trusts. Make that understanding available wherever people and agents work.