How a compliance team stops treating AI drafts as a leap of faith
A financial services compliance function rolls out generative drafting for case narratives and regulatory responses. KnowledgeHub grounds every draft in cited, versioned sources, so reviewers check evidence instead of guessing where a sentence came from.
A citation on every sentence.
Where did this sentence come from?
The pilot works. Drafting time drops. Then it stalls in the same place every generative AI project in a regulated function stalls: someone asks where a sentence came from, and there isn't a good answer.
A generated paragraph might be accurate. It might also be a fluent restatement of last year's policy, or a source that was superseded two ontology releases ago. Without a way to tell the difference, every draft needs the same manual check a human-written one would, which erases the time saved in the first place.
Legal and compliance don't block generative AI because they doubt what it can write. They block it because "trust me" isn't a standard a regulator will accept, and neither should it be.
The fix isn't a better prompt. It's a retrieval layer underneath the generation that the output can't outrun.
KnowledgeHub sits between the request and the model. Before anything is generated, the relevant passages are retrieved from a versioned corpus — policy documents, prior case files, regulatory guidance — each one tagged with its source, ingestion date, and the ontology release that classified it.
Agents are given bounded tasks: retrieve, summarise, draft a specific section. They assemble a response with every claim linked to its source passage. Nothing reaches a reviewer without its citations attached, and nothing leaves the reviewer's desk without a human approval.
Cited, sentence by sentence
Every generated sentence points to the exact passage, document version and ontology release behind it.
Narrow, auditable tasks
Agents retrieve, summarise and draft. They never give the final sign-off.
Reproducible drafts
Prompt and model versions are logged with the ontology, so a draft from March and one from June can each be reproduced.
A regulatory inquiry, drafted with its sources
A response is due
A regulatory inquiry lands on the reviewer's desk.
Instead of a blank page, the reviewer requests a first draft.
The sources come first
Before anything is generated, the relevant passages are retrieved.
Internal policy, the guidance the inquiry responds to, and how a similar inquiry was handled eighteen months ago. Each is tagged with its source, date and ontology release.
Read with the evidence, not blind
Three claims are flagged as weakly supported, where the passage is a partial match.
The reviewer checks those three, tightens the wording and approves the rest as drafted.
The same answer, again
What leaves the desk carries its full citation chain.
Which passage, which document version, which ontology release. The same query against the same version returns the same answer six months later.
Faster, because it's defensible
- A draft that cites its sources is the fastest to approve.
- Reviewers check evidence instead of reconstructing the reasoning.
- Legal can see what governed generation means in practice.
- Rollout expanded beyond the pilot team.
- Sector
- Financial services
- Region
- Denmark / Nordics
- Org scale
- 1k–10k relevant seats
- Personas
- Compliance officers, legal reviewers, AI governance leads, IT security
- Products
- KnowledgeHub · Case workspace · Agents
- Compliance
- GDPR-aligned processing · ISO 27001 posture · full prompt and version logging
More from Financial institutions
Easy to start. Safe to stop.
The pilot runs at a fixed price: we map the workflow, deploy it in your environment and prove it on your own cases. Then you decide.
Fixed price · Fixed timeframe
- 01
Map the workflow
Two weeks with your people where we document what happens today, including the parts nobody wrote down.
- 02
Deploy in your environment
Inside your tenancy, on your data residency terms, with no exports and nothing leaving through the side door.
- 03
Prove it under audit
Controlled evaluation against your own cases with compliance and the process owner signing off before go-live.
- 04
Run in production
We stay on with retraining, reporting and ongoing oversight for as long as the workflow runs.
Fixed price, Fixed timeframe. 8–12 weeks pilot: Continue (Expand once you know it works) / Stop.