Safety Incident Agent
The Safety Incident Agent turns shift reports, incident logs, photos and witness statements into structured SHEQ records. It classifies each incident, tags likely root causes, checks what must be reported under the MHSA or OHS Act, and looks across sites for hazards that keep recurring, so your safety team acts before the next incident.
Ideal forSHEQ teams
The difference
From 2-3 hours per incident to 10-15 minutes
Your safety team spends its time on investigations and prevention, not on capturing reports.
Done by hand
2-3 hours per incident
With the Vanine agent
10-15 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.
Complete records, every shift
Incidents are captured in full from the shift report itself, so nothing is lost between the control room and the SHEQ system.
Reportable incidents never missed
The agent checks each incident against MHSA and OHS Act reporting rules and flags the ones that must go to the DMRE or Department of Labour.
Patterns seen across sites
Near misses and minor incidents that recur across shifts and sites are grouped and flagged, which is where serious incidents usually start.
Capabilities
Every incident captured properly, and the hazards that keep coming back found early.
Built for SHEQ managers, safety officers, mine managers and operations teams at South African mines, plants and industrial sites.
Incident capture
Reads shift reports, logs, photos and statements, and creates a structured incident record with who, what, where and when.
Root-cause tagging
Suggests likely root causes and contributing factors using your chosen method, such as ICAM or 5 Whys.
Trend alerts
Groups similar incidents and near misses across shifts and sites, and alerts SHEQ when a hazard keeps recurring.
Regulatory reporting checks
Checks each incident against MHSA and OHS Act reporting requirements and drafts the notification where one is needed.
Corrective action tracking
Proposes corrective actions with owners and dates, and follows up on the ones that are overdue.
Audit-ready records
Keeps a complete, cited record of every incident and investigation for inspectors and ISO 45001 audits.
How it works
From your systems to a result you sign off
Your SHEQ manager approves every classification, investigation finding and regulatory notification.
Connect the places your incident records already live.
Shift reports, control room logs, photos and witness statements from SharePoint, email or your SHEQ system. Already use something else? We connect that too.
- OpenAI Frontier
- Your own AI platform or models
- Microsoft 365 (Teams, SharePoint, Outlook, Excel)
- SHEQ systems such as IsoMetrix, Enablon and SAP EHS
- Shift reports, control room logs and WhatsApp photos
- Power BI safety dashboards
Runs at the end of every shift, or on request in Teams, using the models your organisation approves.
Structured incident records in your SHEQ system, with trend alerts and a Power BI safety dashboard.
Step by step
- 01
A shift ends and its reports and logs are filed.
- 02
The agent reads them and creates a record for each incident.
- 03
It classifies each incident and tags likely root causes.
- 04
It checks which incidents must be reported to the regulator.
- 05
It compares incidents across sites and flags recurring hazards.
- 06
Your SHEQ manager reviews and assigns the corrective actions.
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.
"Capture the incidents from last night’s shift"
- site
- Shaft 2
- shift
- Night, 28 Sep
On a model you host yourself
Run the agent on open-weight models in your data centre or private cloud. Your incident records 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 incident records stay yours.
The agent runs inside your tenancy, reads only what each task needs, and never trains on your incident records. Every step is logged so your auditors can see exactly what it touched.
Built for regulated work.
+YOUR INCIDENT RECORDS 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
