Enterprise knowledge assistants and RAG — US
An enterprise assistant should help a user find an answer they are allowed to see and understand the evidence behind it. Retrieving a relevant-looking paragraph is not enough when documents conflict or access permissions differ between teams.
FI Digital designs knowledge assistants around approved sources, permission-aware retrieval and evaluation.
The goal is a useful answer with an understandable limitation when the evidence is missing, outdated or restricted.
What the engagement covers
Identify authoritative documents and records, owners and update rules.
Design indexing and access checks so the application respects the intended user boundary.
Connect the response to relevant source material and make uncertainty visible.
Test missing answers, conflicting versions and permission changes. Define ongoing source and model review.
FI DIGITAL / WORKFLOW
Enterprise knowledge assistants and RAG
- Source boundary
- Retrieval and permissions
- Review and authorise
- Evaluation and maintenance
- Resolve with the owner
A practical example
An illustrative employee asks about a policy that has been superseded. The assistant should use the approved current version or explain the gap, not combine old and new instructions into a confident answer.
Questions that shape the scope
Use these questions to identify the first decision and the information needed to make it.
- Which source is authoritative?
- How are permissions checked?
- What happens when evidence conflicts?
- How are outdated documents removed?
Scope the US workflow and its dependencies
Identify the US business process, contracting entity and system owners before using a global template. Multi-state or multi-entity requirements, supported provider accounts and working-hour coverage should be explicit where they affect delivery. The project should have a named acceptance owner and an agreed support arrangement; no local office or round-the-clock coverage is implied.
From assessment to an accepted result
Agree the user, workflow, expected outcome and acceptance owner. Identify the important unknowns early.
Set out records, interfaces, permissions and dependencies. Make failure recovery part of the design.
Review usable work against representative scenarios. Keep decisions and scope changes visible.
Confirm acceptance, rollback, account ownership, documentation and the support arrangement.
Control cost around the work that matters
AI-assisted development, reusable components and supported connectors can reduce parts of the build effort. They do not remove the need to agree requirements, resolve conflicts between systems, review permissions or accept the business result. Keep the first release bounded and compare proposals against the same interfaces, tests, handover and support responsibilities. Ask which recurring provider charges and maintenance tasks remain after launch. Senior coordination is most useful where it resolves a concrete dependency or decision; it should be visible in the scope. The aim is a maintainable working outcome at an understood total cost, not additional complexity for its own sake.
What your team should receive at handover
The handover should cover the working application or integration, relevant source and configuration access, deployment instructions and the accepted test evidence. Document the important dependencies and the actions that require an authorized owner. A useful release record explains what is included, what remains outside scope and how the team can recover from an ordinary failure. These materials support maintainability; they do not replace a separately agreed support arrangement.
Scope and responsibilities
The scope, acceptance criteria, third-party dependencies and operating responsibilities are agreed for the engagement. No partner tier, certification, guaranteed saving or fixed delivery period is implied.
Frequently asked questions
Does RAG stop hallucinations?
No. Retrieval can improve grounding, but the system can still select irrelevant material, misunderstand it or produce an unsupported answer. Evaluation should test those failures and define the expected response when evidence is insufficient. The user needs a usable way to inspect the source and escalate a question that the assistant cannot answer reliably.
Can it respect our existing document permissions?
That is a design and testing requirement, not an automatic consequence of connecting a document store. Review identity mapping, indexed content, retrieval filters and downstream access. Test users with different rights and changes to those rights, including revoked access, before treating the assistant as a safe route to internal information.
Can the project start with a smaller first release?
Yes, if the first release covers a useful end-to-end workflow rather than disconnected screens. Agree the user, outcome, acceptance checks and operational owner. Keep later features visible without placing them all in the initial scope. The first release should test the important assumptions and leave a maintainable foundation for the next decision.
How are cost and delivery time estimated?
The estimate follows the agreed workflow, interfaces, data, permissions and operating requirements. Discovery should expose uncertain dependencies before they become hidden commitments. Break the work into reviewable milestones and state assumptions, exclusions and third-party costs. A fixed number of weeks or a low starting price is not a reliable substitute for a defined delivery scope.
Can you integrate with our existing systems?
Integration depends on the systems’ available interfaces, access rights, limits and commercial terms. Review the actual records and actions required before choosing a connector or custom interface. Define identifiers, retry behaviour, duplicate prevention and reconciliation. The proposal should distinguish supported actions from capabilities that still require discovery or permission from another system owner.
Who owns the software and accounts?
Ownership, licensing and access should be explicit in the agreement. Distinguish custom code from existing product components, third-party services and open-source dependencies. Agree where repositories, cloud accounts, credentials and documentation will be controlled, and what is handed over. Do not assume that commissioning a project automatically transfers every underlying software right or provider account.
How do you test before launch?
Test the business workflow, user permissions, ordinary failures and recovery, using representative scenarios agreed with the people who will operate the result. Include data quality and integration behaviour where relevant. Record acceptance and unresolved issues before release, with a rollback or fallback appropriate to the change. A demonstration of the happy path is only one part of readiness.
Is ongoing maintenance included?
The proposal should distinguish delivery, warranty or defect correction, and ongoing operational support. Dependencies, usage and business requirements can change after launch, so assign ownership for updates and monitoring. Support hours, response targets and service levels require a specific agreement. They should not be assumed from a general description of development or platform operations services.