Mining Technical Report Review Agent

The Mining Technical Report Review Agent reads Competent Person's Reports, Competent Valuator's Reports and mineral asset valuations and checks them against the SAMREC and SAMVAL Codes, their Table 1 checklists and Section 12 of the JSE Listings Requirements. It finds missing disclosures, inconsistent resource and reserve figures and unsupported valuation inputs, and cites each finding to the clause and the page, so reviewers start from a complete compliance view instead of a blank checklist.

Ideal forMining corporate finance teams

The difference

From 3-5 days per report review to 2-3 hours

Your team clears technical reports for transactions and listings faster, with every gap found before the JSE does.

Done by hand

3-5 days per report review

With the Vanine agent

2-3 hours

Time returned to your team

85%

Indicative figures. We measure your own baseline in the first fortnight so the numbers you see are yours.

Fewer queries from the JSE

Missing Table 1 items and Section 12 disclosures are found before submission, not in the regulator's review.

Reviewers spend time on the judgement calls

The clause-by-clause checking is done, so senior people focus on geology, assumptions and value.

Consistent figures across the document set

Resources, reserves and valuation inputs are checked against each other across the CPR, the valuation and the circular.

Capabilities

Every Competent Person's Report and valuation checked against SAMREC, SAMVAL and the JSE rules, clause by clause.

Built for mining corporate finance advisers, sponsors, competent persons and valuators working on South African and JSE-listed mineral assets.

SAMREC table 1 check

Tests the report against every Table 1 item that applies to the project's stage and commodity.

SAMVAL valuation review

Checks the valuation approaches, inputs and disclosures against the SAMVAL Code and its Table 1.

JSE section 12 check

Confirms the disclosures the JSE requires of mineral companies are present and consistent.

Resource and reserve consistency

Compares tonnages, grades and classifications across the CPR, valuation and other transaction documents.

Competent person check

Confirms the competent person's qualifications, independence and sign-off are disclosed.

Cited to the clause

Links every finding to the code clause and the page of the report it relates to.

How it works

From your systems to a result you sign off

Your reviewer confirms every finding before it goes to the competent person or the JSE.

TeamsExcelWordSharePointOutlook
Any system you use
Connects

Connect the places your technical reports already live.

Competent Person's Reports, valuation reports, models and circulars from your data room or shared drives. Already use something else? We connect that too.

  • OpenAI Frontier
  • Your own AI platform or models
  • Microsoft 365
  • Virtual data rooms (Intralinks, Datasite, Ansarada)
  • SAMREC, SAMVAL and JSE Listings Requirements reference library
  • Word review templates and Excel valuation models
Works in

Runs when a new draft lands in the data room, or on request in Teams, using the models your organisation approves.

SAMREC table 1 check
SAMVAL valuation review
JSE section 12 check
Resource and reserve consistency
Competent person check
Cited to the clause
Delivers to

A compliance review in your Word template, with a findings register in Excel, saved to the transaction folder.

Step by step

  1. 01

    A draft CPR or valuation lands in the data room.

  2. 02

    The agent reads the report and the supporting documents.

  3. 03

    It checks the report against SAMREC or SAMVAL and Table 1.

  4. 04

    It checks the disclosures against Section 12 of the JSE Listings Requirements.

  5. 05

    It compares figures across documents and drafts the findings register.

  6. 06

    Your reviewer confirms the findings and sends them to the author.

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.

Model Context Protocol

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.

Adopting frontier AI across your teams
Called from ClaudeMCP connected

"Check the CPR against SAMREC Table 1"

Toolmining_technical_report_review.check_samrec
report
CPR, manganese project
listing
JSE Main Board
Returned6 items incompleteEvery finding linked to its source document
Self-hosted

On a model you host yourself

Run the agent on open-weight models in your data centre or private cloud. Your technical reports never leave your network, which keeps POPIA and data residency straightforward.

  • Llama
  • Mistral
  • Ollama
  • or any OpenAI-compatible endpoint
Sovereign AI on your infrastructure
Bespoke systems

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
Custom integrations from our software factory
Governance

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 your data is handled

DATA SECURITY & PRIVACY

Your technical reports stay yours.

The agent runs inside your tenancy, reads only what each task needs, and never trains on your technical reports. Every step is logged so your auditors can see exactly what it touched.

Built for regulated work.

+
WHAT THE AGENT KEEPSONLY THE OUTPUTENCRYPTED AT REST0 BIT AES0% DELETABLE0 TRAINING RUNS

YOUR TECHNICAL REPORTS NEVER LEAVE YOUR ENVIRONMENT

Precision AI for Institutional Workflows

Build once.Deploy across teams.Improve over time.