Unit Trust Product Agent
The agent drafts unit trust fund documents and Minimum Disclosure Documents by combining performance data, approved regulatory wording and your investment narrative. It handles multiple fund classes, presents performance to ASISA standards and keeps a full audit trail, so your product team can focus on strategy and distribution.
Ideal forProduct teams
The difference
From 3-4 weeks to 15-30 minutes
Your product team can launch and maintain more fund classes and spend its time on strategy and distribution rather than document assembly.
Done by hand
3-4 weeks
With the Vanine agent
15-30 minutes
Time returned to your team
90%
Indicative figures. We measure your own baseline in the first fortnight so the numbers you see are yours.
Repetitive, regulated and monthly
MDDs, TER and TC updates and ASISA classification checks recur across every fund class, every month. The agent removes the assembly work while keeping the disclosures consistent.
Approved wording, every time
Risk warnings and regulatory statements come from your library of approved CISCA, FSCA and FAIS wording, which reduces the chance of a non-compliant disclosure.
A defensible record
Source data, template versions and compliance sign-offs are logged for each document, giving you a clear trail if the FSCA asks.
Capabilities
Compliant MDDs and fund documents drafted in minutes, every month.
Built for product and fund governance teams at CIS management companies, asset managers, LISP product teams and compliance officers.
Fund document drafting
Creates first drafts of new portfolio documentation, including supplemental deed schedules, investment policy wording, fee structures and risk disclosures, ready for review before submission to the FSCA.
Regulatory language library
Uses your library of approved CISCA, FSCA and FAIS disclosure wording so every risk warning and regulatory statement is vetted and consistent.
Minimum disclosure document creation
Generates MDDs and fact sheets with performance, portfolio characteristics, TER and TC figures and fund highlights, formatted to your brand and FSCA requirements.
Multi-class support
Handles portfolios with several fund classes, producing separate fee, performance and distribution details for each class.
Performance and classification data
Pulls performance from your systems, presents it to ASISA standards with the correct category, benchmark and disclaimers, and flags Regulation 28 compliance statements for retirement-compliant funds.
Version control and audit trail
Records the source data, template versions and compliance sign-offs used in each document, creating a defensible audit trail for FSCA review.
How it works
From your systems to a result you sign off
On a monthly schedule for MDDs and fact sheets, or on request in Teams or OpenAI Frontier for new fund documentation.
Connect the places your fund documents already live.
Performance and portfolio data from your systems and fund administrator, plus approved wording and templates held in SharePoint. Already use something else? We connect that too.
- OpenAI Frontier
- Your own AI platform or models
- Microsoft 365 (Teams, SharePoint, Word, Excel)
- Copilot Studio
- Performance and portfolio systems
- Fund administrator data (Maitland, Apex, Prescient)
- Your brand and document templates
On a monthly schedule for MDDs and fact sheets, or on request in Teams or OpenAI Frontier for new fund documentation.
Draft MDDs and fund documents are saved to SharePoint for compliance sign-off. Any FSCA submission is made by your authorised team.
Step by step
- 01
Month-end data is available or a new fund or class is being launched.
- 02
The agent pulls performance, TER and TC and portfolio data for each class.
- 03
It drafts MDDs or fund documents using approved wording and your templates.
- 04
It checks classification, benchmarks, disclaimers and Regulation 28 statements.
- 05
Compliance reviews and signs off, and your team publishes or submits to the FSCA.
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.
"Draft the September MDDs for the Balanced Fund"
- fund
- Balanced Fund
- month
- Sep-2026
On a model you host yourself
Run the agent on open-weight models in your data centre or private cloud. Your fund 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 fund documents stay yours.
The agent runs inside your tenancy, reads only what each task needs, and never trains on your fund documents. Every step is logged so your auditors can see exactly what it touched.
Built for regulated work.
+YOUR FUND 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
