compliance_monitoring · finance · workflow
CNCC deploys AI-powered document research for France's statutory auditors via Dust
France's statutory auditors relied on keyword search alone to navigate thousands of pages of standards and regulations, but keyword search could not interpret complex professional questions—only match exact terms.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Auditor submits natural question
Auditors ask natural language questions rather than constructing keyword queries.
Tools used
DustSidoniElasticsearchFrameMaker
Outcome
The pilot achieved an 85-87% satisfaction rate among testers from a rigorous profession, with external pilot demand doubling from 20 to 40 auditors, and internal staff experiencing faster meeting minutes generation.
What failed first
The Elasticsearch-based Sidoni database, despite two major evolutions, still could not interpret auditors' professional questions—only match keywords.
Results
Time savedminutes rather than hours
Volume85-87%
Cost replaced40
Grounding & classification
Source type: agency client case
32 fields verified against source quotes.
enterprise searchknowledge searchragsummarizationknowledge basemeeting recordingpolicy documentfailure mode describedhuman review describedmetric backednamed customerproduction runtime claimedsource backedtools describedvendor confirmedworkflow describedfinancial servicescustomer satisfactionemployee productivitytime savedagency client caseback office opscompliance monitoringlegal document reviewrag answering