Audit Working Paper Agent
The Audit Working Paper Agent turns the client's trial balance and PBC documents into lead schedules, preliminary and final analytical review, sample selections and test working papers in a CaseWare-ready format, aligned to the International Standards on Auditing as adopted by IRBA. It tracks audit queries to the client and drafts management letter points from the findings for the engagement manager to review.
Ideal forAudit managers
The difference
From 12-16 hours per audit file to 3-4 hours
Your audit teams put their hours into testing, judgement and client conversations, and busy season becomes more manageable.
Done by hand
12-16 hours per audit file
With the Vanine agent
3-4 hours
Time returned to your team
75%
Indicative figures. We measure your own baseline in the first fortnight so the numbers you see are yours.
Less time on mechanical file work
Trainees spend weeks building lead schedules, ticking schedules and query lists. The agent prepares that structure so your team starts testing on day one.
Consistent, inspection-ready files
IRBA inspections focus on documentation quality. Every working paper follows the same structure, links to the source and records how samples were selected.
Faster close-out with clients
Open queries and PBC gaps are tracked in one list per client, so fewer audits run late waiting for documents.
Capabilities
Audit files that are built before your team arrives on site.
Built for audit managers, seniors, trainee accountants and partners at IRBA-registered audit firms in South Africa.
Lead schedules
Maps the client's trial balance to your firm's lead schedule structure and reconciles opening balances to the prior-year signed AFS.
Analytical review
Prepares planning and final analytical procedures with expectations, thresholds linked to your materiality and explanations still required from management.
Sample selection
Selects samples from ledgers and listings using the method and sample sizes your methodology sets, and documents the selection for the file.
Test working papers
Builds test of detail and control working papers with the attributes to test, the source documents received and the results recorded by the team.
Audit query and PBC tracking
Maintains the PBC list and query register per client, drafts follow-ups and shows what remains outstanding at a glance.
Management letter drafting
Drafts management letter points from recorded findings, with observation, risk and recommendation, for the engagement manager to edit.
How it works
From your systems to a result you sign off
The engagement team performs and reviews the testing, the engagement manager reviews the file, and the registered auditor forms and signs the audit opinion.
Connect the places your audit evidence already live.
Trial balances and ledger exports from the client's ERP, PBC documents from SharePoint or your client portal, and prior-year files exported from CaseWare. Already use something else? We connect that too.
- OpenAI Frontier
- Your own AI platform or models
- Microsoft 365 (Teams, SharePoint, Outlook, Excel)
- Copilot Studio
- CaseWare Working Papers
- Draftworx
- SAP, Sage, Syspro, Dynamics 365, Xero
- Client PBC portals and SharePoint document libraries
Runs on request in Teams or OpenAI Frontier during planning and fieldwork, using the models your firm approves.
Lead schedules, analytical review, sample selections, test templates, query lists and draft management letter points in CaseWare-ready format.
Step by step
- 01
The audit is planned and the client's trial balance and PBC documents arrive.
- 02
The agent builds lead schedules and the planning analytical review.
- 03
It selects samples and prepares test working papers and query lists.
- 04
Your team performs the testing and records results; the agent drafts management letter points.
- 05
The engagement manager and partner review the file and the registered auditor signs the opinion.
Deployment
Runs inside the tools your team already uses
The same agent and the same cited output, delivered three ways: through the AI assistant you have rolled out, on a model you host yourself, or inside your own software.
In the frontier assistant you already pay for
We publish the agent as an MCP server. Add it as a connector and your team calls it from the chat they use every day, with no new tool to learn.
"Build the lead schedules"
- client
- Retail group
- section
- Revenue and receivables
On a model you host yourself
Run the agent on open-weight models in your data centre or private cloud. Your audit evidence never leave your network, which keeps POPIA and data residency straightforward.
- Llama
- Mistral
- Ollama
- or any OpenAI-compatible endpoint
Inside your own software
Trigger a run from your own workflows, and push the finished output into your ERP, GRC or reporting systems. We build the integration with your team.
- REST API
- Webhooks
- Batch jobs
- Embeddable review panel
Governed the same way, every route
Whichever way your team reaches the agent, identity, permissions and audit stay with your existing controls.
- Single sign-on through Entra ID, Okta or Google Workspace
- Reads only the documents each user is already allowed to open
- Every tool call written to an audit log you can export
How we deliver it
One agent, three ways to hold it
Start where your team already works, then take it as far into your systems as the value justifies.
DATA SECURITY & PRIVACY
Your audit evidence stay yours.
The agent runs inside your tenancy, reads only what each task needs, and never trains on your audit evidence. Every step is logged so your auditors can see exactly what it touched.
Built for regulated work.
+YOUR AUDIT EVIDENCE NEVER LEAVE YOUR ENVIRONMENT
More agents
More agents we build for South African enterprises
Each one is built on the same foundation: your documents, your rules, and your people signing off.
Precision AI for Institutional Workflows
