Upload your facility's policies, plans, and reports in any language. CMSI AI Assessor evaluates all 48 sub-sections across the 24 Performance Areas of the Consolidated Standard, delivering a formal pre-audit with evidence, gaps, and recommendations mapped to the three CMSI performance levels.
Independent pre-audit tool. Not affiliated with the Consolidated Mining Standard Initiative, ICMM, World Gold Council, The Copper Mark, or Mining Association of Canada. The AI assessment is for pre-audit use only and does not constitute an external CMSI assurance engagement.
Embedded live on desktop. On mobile, tap the button below.
Chat with the AI, ask anything, get answers
This is an active conversational agent, not a static demo. Ask about any indicator, request explanations of results, explore the data, or simply type "How does this work?" to receive answers in real time.
Open CMSI AI Assessor in a new tab
Open CMSI AI Assessor
Best experienced in a dedicated tab on mobile.
A three-stage pipeline that mirrors the official CMSI Assurance Process.
Add as many documents as needed: PDF, DOCX, XLSX, PPTX (up to 50 MB each). Each upload is automatically summarized, tagged with key topics, and classified against the 48 sub-sections, indicating which ones the document provides substantive evidence for.
Name the facility, optionally mark sub-sections as Not Applicable, select the documents, and click Begin Assessment. The system evaluates all applicable sub-sections in batches of 6 concurrent runs, streaming findings live.
Printable editorial report complete with cover page, outcome banner, Claims Policy checklist, executive summary, and PA-by-PA deep dive with sub-section findings. Export as PDF using your browser's "Print to PDF".
The Consolidated Mining Standard organizes responsible mining performance into four Pillars, each containing six PAs covering distinct ESG topics.
Ethical Business Conduct
Corporate accountability, business integrity and anti-corruption, payment transparency, responsible supply chains, due diligence in conflict-affected and high-risk areas.
Worker & Social Engagement
Labor rights, occupational health and safety, security and human rights, stakeholder engagement, grievance mechanisms, Indigenous Peoples, and free, prior, and informed consent.
Social Performance
Community development and benefits, resettlement and land acquisition, cultural heritage, artisanal and small-scale mining, mine closure planning, decommissioning, and post-closure stewardship.
Environmental Responsibility
Tailings management, water management, biodiversity and ecosystems, climate change, hazardous materials, air emissions and noise, smelting and refining requirements.
Each sub-section receives one of six statuses. The level is derived deterministically from requirement-level determinations: the LLM evaluates requirement evidence, and the code derives the level. No subjective level guessing.
The facility demonstrates requirements across all three levels: full mastery of the sub-section.
One or more Leading Practice requirements not yet met. Solid compliance.
One or more Good Practice requirements not yet met. The minimum acceptable level.
Sole "alert" status. Renders in Oxblood. Blocks Performance Claim Eligibility.
Marked as a soft flag. Does not count toward formal level. Lists expected and missing requirements.
Not relevant to the operation (e.g., PA 23.2 Smelter at a site without a smelter). Rationale recorded.
For each Towards Good Practice / Good Practice / Leading Practice requirement defined in the standard, the LLM marks Met, Partially Met, Not Met, or Unaddressed, with a one-line rationale. The code then deterministically derives the achieved level. This matches the level of detail an Assurance Provider expects.
The CMSI Claims Policy specifies the conditions under which a facility can make a Performance Claim. CMSI AI Assessor reports which conditions pass and which block the claim, giving compliance teams full visibility into what is needed to advance.
Sum of sub-section points divided by the maximum possible (Leading Practice = 3 points, Good Practice = 2, Towards Good Practice = 1, Below TGP = 0). Insufficient Evidence and Not Applicable are excluded from the denominator.
Each PA score is the lowest level achieved across its applicable sub-sections. A single Below-TGP sub-section blocks the entire PA.
At least 80% of applicable PAs must achieve Good Practice or above. Rewards consistent performance beyond the minimum.
Each of the four Pillars must have at least four PAs at Good Practice. Prevents facilities from offsetting weaknesses in one Pillar with excellence in another.
The four meta-outcomes
Once all sub-sections are resolved, the system calculates one of four overall determinations.
All four Claims Policy criteria pass. The facility can proceed to external assurance in support of a Performance Claim.
All applicable PAs are at TGP or higher, but one or more Claims Policy thresholds have not been met. The dashboard highlights exactly which ones.
One or more PAs are Below TGP. The facility is not yet ready for external assurance and must address unmet TGP requirements.
Too many sub-sections have Insufficient Evidence (> 20% of applicable) to calculate a meaningful overall outcome. Upload additional documents.
No paraphrasing or filler. Verbatim citations from your documents attributed to their sources, with verifiable gaps citing specific requirements and one-to-one recommendations.
One of the six statuses above, plus 2-3 sentences in the auditor's voice explaining why this level was assigned to the sub-section.
Every standard TGP, GP, and LP requirement marked as Met / Partially Met / Not Met / Unaddressed, with a one-line rationale. This matches the level of detail an Assurance Provider expects.
Direct verbatim quotes from your submitted documents supporting the verdict. Each is attributed to the source document and the requirement it evidences. No paraphrasing.
Actionable items from standard requirements that are missing or underdeveloped in the documentation. Cited to specific requirement IDs (e.g., "GP requirement 1.4.3"), not generic observations.
One-to-one mapping with identified gaps wherever possible. Concrete, scoped, and owner-friendly actions for the next assurance cycle.
Track the assessment running subsection by subsection. Then review the editorial report with Foolscap-on-Slate typography.
Assessment dashboard
Outcome banner at the top with Foolscap styling, contained Oxblood seal for Performance Claim Eligible; Slate-bordered banners for other states.
Claims Policy checklist showing which of the four conditions passed or blocked the claim.
Pillar / PA / Subsection rail with all 48 subsections grouped by Pillar → PA → subsection, each with a verdict bar.
Detail panel displaying the full findings for the selected subsection.
Coverage panel with a documents-by-subsection matrix, citation thumbnails, and radar chart across the four Pillars.
Formal report
Editorial typography with Foolscap-on-Slate styling for a printable, high-craft feel.
Cover page with outcome banner and overall determination.
Executive summary with Claims Policy checklist for leadership and assurance teams.
PA-by-PA deep dive with findings by subsection (level achieved, determinations by requirement, citations, gaps, recommendations).
Print as PDF via browser. Server-side PDF generation is on the roadmap.
When you open the app, it comes prepopulated with a fictional mining unit, including a corporate library, a full assessment with all 48 subsections resolved, and a realistic mix of levels across the four Pillars.
Unit
A fictional mining unit to demonstrate the real-world structure: governance, social, and environmental scope, plus an optional smelter site.
Corporate library
Code of conduct, anti-bribery, human rights, community engagement, indigenous peoples, tailings management, water management, biodiversity, climate, mine closure, supplier code, OHS, and grievance mechanism.
Precomputed assessment
All 48 subsections resolved across the four Pillars. Balanced mix of Leading Practice highlights, mainstream Good Practice, and a handful of Towards Good Practice gaps to address.
Inspect the existing assessment, then upload your own documents and run a fresh assessment against the live LLM pipeline.
No. CMSI AI Assessor is an independent pre-audit tool built by Data Riders. It is not affiliated with the Consolidated Mining Standard Initiative, ICMM, World Gold Council, The Copper Mark, or Mining Association of Canada. Reports include a clear disclaimer.
All 48 subsections across the 24 Performance Areas of the CMSI Consolidated Standard, distributed across four Pillars: Ethical Business Conduct (PAs 1–5), Worker & Social Engagement (PAs 6–11), Social Performance (PAs 12–17), and Environmental Responsibility (PAs 18–24). Each subsection is evaluated using the official three-level ladder.
Documents can be submitted in any language. Findings are written in the language of the submitted documents (with an optional user override). The interface is in English; full UI internationalization is on the roadmap.
The LLM evaluates each individual requirement (TGP, GP, LP) as Met, Partially Met, Not Met, or Not Addressed. The achieved level is then derived deterministically by code: all TGP met → at least Towards Good Practice; all TGP + GP → Good Practice; all three levels → Leading Practice; any TGP not met → Below TGP. The LLM evaluates evidence by requirement; level derivation is code, not LLM.
When all applicable subsections resolve, the system computes the overall outcome against four CMSI Claims Policy thresholds: aggregate score ≥ 80%, all applicable PAs at TGP or higher, ≥ 80% of PAs at Good Practice or higher, and at least 4 PAs per Pillar at Good Practice or higher. The four meta-outcomes are Performance Claim Eligible, Continual Improvement Required, Below Standard, or Indeterminate.
Users can mark subsections as Not Applicable when they are not relevant to the operation (e.g., PA 23.2 Smelter at a site without a smelter). NA subsections are excluded from both the numerator and denominator of the aggregate score. The justification is recorded for transparency.
No. CMSI AI Assessor runs in demo mode by design: no authentication, single shared workspace. Documents and assessments persist across sessions.
No. CMSI AI Assessor is a pre-audit tool that identifies gaps and surfaces evidence ahead of a formal assessment by an Assurance Provider. The final report includes a disclaimer stating that the AI assessment is for pre-audit use only and does not constitute a formal CMSI external assurance engagement.
PDF, DOCX, XLSX, and PPTX, up to 50 MB each. Upon upload, full text is extracted, a 1–2 sentence summary is generated, key topics are tagged, and the document is classified against the 48 subsections, indicating which ones it provides substantive evidence for.
No procurement. No login. Open the assessor, inspect the demo case, and then upload your own documents for a fresh assessment against the live pipeline.
CMSI AI Assessor is an independent pre-audit tool built by Data Riders. Not affiliated with the Consolidated Mining Standard Initiative, ICMM, World Gold Council, The Copper Mark, or Mining Association of Canada.
