-
No. 12Nov 2026
- Assays and lab data
- Mass balance and reconciliation
- Agents, tools and skills
- Language models
- Tailings and water
Can a local AI assistant tell which size fraction carries the most copper?
Given a published tailings table and Python, two local models named the fraction carrying the most of the reported copper in all 20 attempts. None said that the 8.2 % of the sample missing from the table might hold copper too.
-
No. 11Nov 2026
- Assays and lab data
- Laboratory and assay
- Reading drawings and documents
- Language models
- Documents and drawings
Can a local model put the right assay into the right database field?
With each field's method, unit and statistic spelled out, a local model got 83 of 84 fields right in each of three passes over seven certificates, against 55 for rules written from one certificate; its one miss made a gold standard's standard deviation (SD) three times too tight.
-
No. 01Oct 2026
Recovery moved by two percentage points. Did the circuit actually improve?
With the plant unchanged, a reported tailings assay of 0.08 instead of 0.10 % Cu lifts two-product recovery by 1.92 points. What to check before crediting a gain.