AI-assisted internal-audit fieldwork
A procedure you can follow from evidence to review.
The illustrative workflow connects the audit procedure to the sources, result and human decision. A Test defines what to do; a Run records one execution.
Book a demoIllustrations explain the product model. Confirm your procedure, formats and review requirements during evaluation.
Documents → Tests → Runs → Review → Findings → Working Papers
Documents establish the source set. Tests hold the Audit Test Recipe, including Extract, Reconcile and Checks. A Run records inputs, Recipe version, execution details and outcomes.
Review resolves uncertainty and records decisions. Findings group related confirmed exceptions. Working Papers collect the procedure, evidence references and sign-offs.
Illustrative Run snapshot · DEMO-RUN-018
180 of 190 eligible records completed.
One check per record · Q1 FY27. Completion does not resolve human review.
- Received
- 200
- Eligible
- 190
- Execution completed
- 180
- Excluded
- 10
- Awaiting evidence
- 6
- Processing failures
- 4
- Pass157
- Fail17
- Insufficient evidence6
- Needs human review6
- Not applicable0
- Processing error4
Outcomes total 190 eligible records; excluded records are separate. Missing evidence is reported separately unless the configured completeness procedure explicitly defines its absence as a failure.
Recipe v3 · Inputs v1 · illustrative engine demo-1 / model fixture-1. Completed Run history is immutable. A new Recipe version creates new work; it does not rewrite this snapshot.
Draft / review incomplete · Finding: Not raised · 0 confirmed exceptions.
Engagement work and reusable knowledge.
Overview summarises an engagement's scope, population and open review work. The workspace holds Test Library templates and Knowledge Hub sources; Copilot assists across this context.
A snapshot is distinct from a conclusion.
In the product model, completed Run history is immutable. New inputs or Recipe versions create new work. Run Integrity: Verified means the recorded inputs and versions remain unchanged; it does not mean the audit passed.
Reperformance needs pinned inputs, versions and retained model outputs where relevant. A fresh unpinned model call is not a guarantee of identical results.
AI assists. Code compares. People approve.
AI extraction and suggested mappings need evidence review. Deterministic comparisons apply the configured arithmetic. Recipe approval, exception decisions and final conclusions stay with people.
Keep answers tied to sources.
Knowledge Hub supplies versioned sources. Copilot drafts Recipes and explains results with citations; people approve the procedure and conclusion.
Explore Knowledge Hub and Copilot ↗Does this example confirm current availability?
The example explains the product model with synthetic data. Confirm the procedure, formats and review behaviour you need in an evaluation; a labelled illustration does not replace product evidence.
Your next procedure
Start with the work you need to review.
Discuss the sources, rules and output your team needs. Please keep confidential audit evidence out of the enquiry form.