Discovery Review Agent
The Discovery Review Agent reviews large document sets for relevance and privilege for discovery under Rule 35 of the Uniform Rules of Court. It tags each document by issue, identifies potentially privileged material, and prepares the schedules for the discovery affidavit so the attorney can review and finalise them.
Ideal forLitigation attorneys
The difference
From 40-60 hours per 1,000 documents to 8-12 hours
Discovery deadlines become manageable, and senior attorneys spend their time on the key documents and privilege calls.
Done by hand
40-60 hours per 1,000 documents
With the Vanine agent
8-12 hours
Time returned to your team
80%
Indicative figures. We measure your own baseline in the first fortnight so the numbers you see are yours.
Manageable document volumes
Email-heavy disputes can involve tens of thousands of documents. The agent does the first-pass review so your team focuses on the documents that matter.
Privilege protected
Inadvertently discovering privileged documents is hard to undo. The agent flags legal advice, litigation privilege and without prejudice material for attorney review.
Consistent, defensible review
Every document is assessed against the same issues and criteria, with reasons recorded, so your discovery process is consistent and explainable.
Capabilities
Get through Rule 35 discovery faster, with privilege protected.
Built for litigation attorneys, candidate attorneys, paralegals and in-house dispute teams handling document-heavy matters in South African courts and arbitrations.
Relevance review
Assesses each document against the issues defined by the pleadings and records a short reason for its relevance classification.
Privilege identification
Flags documents that may attract legal advice privilege, litigation privilege or without prejudice protection, for attorney decision.
Issue tagging
Tags documents by issue, custodian and date, so the team can build witness files and focus on the key documents quickly.
Duplicate and thread handling
Groups duplicate documents and email threads so reviewers see each conversation once.
Discovery affidavit schedules
Prepares the schedules of documents for the Rule 35 discovery affidavit, separating documents in possession, privileged documents and documents no longer held.
Personal information flags
Highlights personal information of third parties so the team can consider POPIA and confidentiality measures before documents are produced.
How it works
From your systems to a result you sign off
The attorney decides on relevance and privilege, finalises the schedules, and the client deposes to the discovery affidavit.
Connect the places your discovery documents already live.
Client document collections from SharePoint, Outlook mailboxes, Purview eDiscovery exports and your document management system. Already use something else? We connect that too.
- OpenAI Frontier
- Your own AI platform or models
- Microsoft 365 (Teams, SharePoint, Outlook, Excel)
- Copilot Studio
- Microsoft Purview eDiscovery exports
- iManage and NetDocuments
- Court Online and CaseLines
Runs as a batch review on a schedule or on request in Teams or OpenAI Frontier, using the models your organisation approves.
A tagged review set in Excel, a privilege log and draft discovery affidavit schedules in Word.
Step by step
- 01
The attorney defines the issues and loads the document collection.
- 02
The agent removes duplicates and groups email threads.
- 03
It reviews each document for relevance and privilege and tags it by issue.
- 04
It prepares the privilege log and discovery affidavit schedules.
- 05
The attorney reviews the classifications and privilege calls.
- 06
The client deposes to the affidavit and the attorney serves it.
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.
"Remove duplicates and group email threads"
- rule
- Uniform Rule 35
- custodians
- 9 mailboxes
On a model you host yourself
Run the agent on open-weight models in your data centre or private cloud. Your discovery documents 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 discovery documents stay yours.
The agent runs inside your tenancy, reads only what each task needs, and never trains on your discovery documents. Every step is logged so your auditors can see exactly what it touched.
Built for regulated work.
+YOUR DISCOVERY DOCUMENTS 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
