Equity Research Agent
The agent reads results announcements, presentations and call transcripts, extracts revised guidance and flags material changes in management commentary. It delivers structured summaries and model-ready data so you publish faster and widen your JSE coverage without adding analysts.
Ideal forSell-side research teams
The difference
From 2-3 hours per call to 5-10 minutes
Your analysts spend results season forming views and talking to clients rather than transcribing calls and updating spreadsheets.
Done by hand
2-3 hours per call
With the Vanine agent
5-10 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.
Results season compresses everything
Many JSE companies report in the same weeks, and every call takes hours to digest. The agent handles the extraction so your analysts keep pace across their whole coverage list.
No more manual data entry
Guidance and KPIs arrive in a structured format ready for your Excel models, which removes retyping and the errors that come with it.
Every number is traceable
Each extracted figure cites the exact management statement behind it, so you can defend your estimates to clients and your research committee.
Capabilities
Turn every results call into model-ready guidance before the market digests it.
Built for sell-side analysts at SA brokers, buy-side analysts at asset managers and independent research houses.
Automated guidance extraction
Extracts forward-looking guidance on revenue, EBITDA, margins, capex and segment metrics from presentations and transcripts, with precise citations to management statements.
Management commentary analysis
Summarises themes from prepared remarks and Q&A, flagging tone shifts, new strategic initiatives and changes in competitive positioning versus prior periods.
Period-on-period comparison
Compares current guidance and commentary with prior interim, full-year and operational updates in your knowledge base, showing revisions and how the narrative has evolved.
KPI and metric tracking
Extracts company-specific metrics such as HEPS, trading density, active clients or like-for-like sales and tracks them over time to spot inflection points.
Risk factor identification
Flags new risks raised by management, including regulatory change, electricity and logistics constraints, rand volatility and macroeconomic uncertainty.
Structured output for models
Delivers guidance and metrics in a structured format ready for your Excel models and research systems.
How it works
From your systems to a result you sign off
Ask it in Teams or OpenAI Frontier after a call, or schedule it to run as each company in your coverage reports.
Connect the places your research models already live.
Results announcements on SENS, results presentations, call transcripts, and your prior notes and models in SharePoint. Already use something else? We connect that too.
- OpenAI Frontier
- Your own AI platform or models
- Microsoft 365 (Teams, SharePoint, Excel)
- Copilot Studio
- JSE SENS results announcements
- IRESS, Bloomberg, LSEG (within your data licence)
- Your research knowledge base and financial models
Ask it in Teams or OpenAI Frontier after a call, or schedule it to run as each company in your coverage reports.
Summaries go to your research workspace and structured guidance and KPIs land in Excel, ready for the analyst to review before updating the model.
Step by step
- 01
A covered company releases results or holds its results call.
- 02
The agent reads the announcement, presentation and transcript.
- 03
It extracts guidance and KPIs and compares them with prior periods.
- 04
It drafts a structured summary with flagged changes and risks.
- 05
Your analyst reviews the output and updates the model and research note.
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.
"What guidance did management give?"
- company
- JSE retailer
- period
- H1 FY2027
On a model you host yourself
Run the agent on open-weight models in your data centre or private cloud. Your research models 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 research models stay yours.
The agent runs inside your tenancy, reads only what each task needs, and never trains on your research models. Every step is logged so your auditors can see exactly what it touched.
Built for regulated work.
+YOUR RESEARCH MODELS 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
