Submit policies, plans, procedures, and reports from your operation in any language. TSM.AI evaluates the submission against all 31 indicators across the 9 TSM protocols of the Mining Association of Canada, producing verdicts on the C/B/A/AA/AAA scale (or Yes/No for the two binary protocols), with verbatim evidence, gaps, and actionable recommendations.
Independent pre-audit tool. Not affiliated with the Mining Association of Canada (MAC) or the TSM program. Determinations are advisory and do not constitute a verified TSM self-assessment or external verification.
Embedded live on desktop. On mobile, tap the button below.
Chat with the AI, ask anything, get answers
This is a real conversational agent, not a static demo. Ask about any indicator, request explanations of results, drill down into data, or simply type "How does this work?", and it responds in real time.
Open TSM.AI in a new tab
Open TSM.AI
Best experienced in a dedicated tab on mobile.
Three-step pipeline that faithfully mirrors the level-by-level TSM methodology.
Add as many documents as needed: PDF, DOCX, XLSX, PPTX (up to 50 MB each). Upon upload, text is extracted, a 1–2 sentence summary is generated, 3–8 topic tags are assigned, and the document is classified against the 31 indicators (returning indicator codes ranked by relevance).
Name the operation (default: "North Pine Mining"), choose which documents to include (default: all ready), select the output language for AI-generated text, and click Begin Assessment. The system processes 31 indicators in batches of 6 concurrent evaluations, streaming verdicts as they resolve.
Printable editorial report featuring a hero cover photo, protocol-by-protocol deep dive, verbatim evidence, gaps, and recommendations. Export using the browser's "Print to PDF". Server-side PDF generation is on the roadmap.
The TSM framework covers the entire operational footprint of a Canadian-style mining company, from Indigenous & Community Relationships to Tailings, Water, Biodiversity, and Climate Change.
Five protocols on social license
- ICR Indigenous & Community Relationships 4 ind.
- CMD Crisis Management & Communications 3 ind.
- SHS Safety & Health 5 ind.
- PRD Preventing Child & Forced Labour 2 ind.
- EDI Equitable, Diverse & Inclusive Workplaces 3 ind.
Four protocols on stewardship
- TMG Tailings Management 5 ind.
- WAT Water Stewardship 3 ind.
- BIO Biodiversity Conservation Management 3 ind.
- CCH Climate Change 3 ind. · binary
Energy & GHG Emissions and Climate Change are scored Yes/No for the protocol's binary indicators.
For each indicator, the evaluator receives the verbatim criteria text at each level and determines which level the operator most plausibly achieves given the evidence. Level A is the stated goal of TSM.
Below the entry threshold for expected indicator practice.
Procedures exist, but are not formalized at the management system level.
Documented management system aligned with TSM expectations.
System integrated into operations and periodically reviewed.
Demonstrated excellence; leadership within the protocol domain.
Two protocols use a binary verdict instead of a level: Energy Use & GHG Emissions and Climate Change. For these, TSM.AI returns YES or NO against the criteria text, with the same rigor of evidence attribution.
If no document in the assessment set was tagged as relevant to an indicator, TSM.AI automatically records INSUFFICIENT_EVIDENCE without calling the LLM. The rationale explains what types of documents would be required; the gaps array lists expected, missing requirements. It is not a failure, but an absence.
TSM does not produce a binary outcome. The roll-up captures the operation's TSM-readiness posture across all 31 indicators.
TSM-readiness roll-up
Each indicator at Level A or above (or YES) counts as at-goal. Indicators below A (or NO) count as below-goal. Insufficient Evidence is reported separately and does not count as below-goal.
Illustrative demo figures. Computed once when the assessment completes and stored on the assessment record.
No paraphrasing or filler. Verbatim citations from your documents, attributed to the source, with verifiable gaps citing specific criteria language and one-to-one recommendations.
One of C / B / A / AA / AAA (or YES / NO for binary protocols), plus 2–3 sentences citing the specific criteria language that supports or fails to support each higher level.
Verbatim quotes from your documents supporting the verdict, without paraphrasing. Each tagged with the source document name.
Specific missing requirements extracted from the criteria text, not generic observations. Cites the exact indicator language that was not met.
Concrete actions mapped one-to-one to gaps. Owner-friendly, scoped to a sprint or quarter, ready to enter your next TSM cycle.
When you open the app, it comes pre-populated with a fictional Canadian operation named North Pine Mining, a plausible library of corporate documents, and a precomputed assessment with all 31 indicators resolved.
The operation
North Pine Mining, a fictional operation in the Canadian boreal forest, used to showcase the real-world structure across the 9 TSM protocols and the Indigenous & community context.
Plausible library
Indigenous engagement framework, community investment policy, crisis management plan, OHSMS, EDI strategy, child and forced labor due diligence, tailings management standard, water management plan, biodiversity action plan, climate strategy, and GHG inventory.
Precomputed assessment
All 31 indicators resolved. A mix of A and AA in well-evidenced areas, transitional B in half-implemented areas, some C signaling immediate action, plus YES/NO on binary climate indicators.
Inspect the existing assessment, then upload your own documents and run a new assessment against the live LLM pipeline. New documents and assessments persist across sessions and remain visible to anyone opening the app.
Track the assessment running indicator by indicator. Then read the editorial report featuring a hero cover photo and protocol-by-protocol deep dive.
Assessment dashboard
Three columns: left rail with the list of indicators grouped by protocol (each row showing its tier badge, code, and name).
Center detail panel displaying findings for the selected indicator as an editorial article.
Right-hand coverage matrix showing which documents support which indicators.
Live progress: the frontend polls every 3 seconds while the assessment runs; ~6 indicators move from skeleton to resolved per minute.
Formal report
Editorial typography with hero cover photography and page-break controls.
Protocol-by-protocol deep dive with verbatim evidence, gaps, and recommendations.
Print to PDF via browser. Server-side PDF generation is on the roadmap.
Disclaimer stating that determinations are advisory and do not constitute a verified TSM self-assessment or external verification.
No. TSM.ai is an independent pre-audit tool built by Data Riders. It is not affiliated with the Mining Association of Canada (MAC) or the TSM program. Reports include a clear disclaimer.
All 31 indicators across the 9 TSM protocols: Indigenous & Community Relationships, Crisis Management & Communications, Safety & Health, Preventing Child & Forced Labour, Equitable Diverse & Inclusive Workplaces, Tailings Management, Water Stewardship, Biodiversity Conservation, and Climate Change. The C/B/A/AA/AAA scale applies to seven protocols; Yes/No applies to the two binary protocols.
Documents can be submitted in any language. The interface is available in English and Portuguese. LLM-generated rationale, gaps, and recommendations adapt to the output language selected by the user. Additional UI languages are on the roadmap.
For each indicator, the evaluator receives the code/name/purpose, the verbatim criteria text for each level, and the full text of each document tagged as relevant during ingestion (truncated to 15,000 characters each). The model selects the level the operator most plausibly achieves given the evidence, citing the specific criteria language that supports or fails to support each higher level.
There is no single pass/fail in TSM. The roll-up reports four metrics: at-goal count (indicators at A or higher, or Yes), below-goal count (indicators below A, or No), insufficient-evidence count, and overall TSM-readiness percentage (at-goal / 31). Computed once when the assessment completes and stored.
A C verdict means the evidence shows the operator is below the entry threshold. Insufficient Evidence means no document in the assessment set was tagged as relevant to that indicator; it is an absence of evidence, not evidence of failure. The rationale explains what types of documents would be required and recommends documents to produce.
No. TSM.ai runs in demo mode by design: no authentication, single shared workspace. Documents and assessments persist across sessions and remain visible to anyone opening the app. Authentication and multi-tenancy are on the roadmap.
No. TSM.ai is a pre-audit tool that identifies gaps and surfaces evidence before a TSM self-assessment or external verification. Determinations are advisory and do not constitute a verified TSM self-assessment or external verification.
PDF, DOCX, XLSX, and PPTX, up to 50 MB each. Upon upload, the document is auto-summarized, tagged with topics, and classified against the 31 indicators. Full text is preserved for the indicator assessment stage (which truncates at 15,000 characters per document).
No procurement. No login. Open the assessor, inspect the North Pine Mining demo case, and upload your own documents for a fresh assessment against the live pipeline.
TSM.ai is an independent pre-audit tool built by Data Riders. Not affiliated with the Mining Association of Canada (MAC) or the TSM program.
