-
No. 15Nov 2026
- Documents and drawings
- Knowledge retrieval and reporting
- Security and data privacy
- On-premises and edge hardware
- Evaluation and benchmarks
Which local model finds the whole answer in a mine’s reports?
Five public records on Cadia's molybdenum plant, 576 pages, searched in SAG-Wiki with no connection beyond the workstation. The first five passages held the answer in 48 of 49 single-fact searches, but both the feed route and the plant's first filtered concentrate, from two records, in only 6 of 21. Every search returned passages for a shift figure the records do not hold.
-
No. 14Nov 2026
- Documents and drawings
- Knowledge retrieval and reporting
- Language models
- Security and data privacy
- On-premises and edge hardware
How does SAG2 find cited answers in a mine’s records, offline?
SAG2, run in SAG-Wiki with the search sealed from any network, searched six public mining records for eight plant and safety questions, and a model on the same workstation answered each from the passages returned, citing them. Six of the seven searches with target pages returned those pages; 38 of 41 statements that cite a passage were fully supported by it, counting the record title sent with each.
-
No. 11Nov 2026
- Documents and drawings
- Laboratory and assay
- Reading drawings and documents
- Language models
- Assays and lab data
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. 08Nov 2026
- Documents and drawings
- Reading drawings and documents
- Agents, tools and skills
- Vision models
- Evaluation and benchmarks
Does a written skill help a local LLM read a whole plant flowsheet?
On each of two plant drawings, Qwen 3.8 Flash Next found more streams in all three attempts with a flowsheet-reading skill than in any attempt without it, and drew fewer wrong lines, in about twice the time. The 27B model gained on one drawing of two in each of two runs, not the same one, and in its rerun took about fifteen times as long with the skill as without.
-
No. 06Nov 2026
- Documents and drawings
- Reading drawings and documents
- Vision models
- Evaluation and benchmarks
- On-premises and edge hardware
Can a local LLM read a mineral processing plant flowsheet?
Two local models, four flowsheets. Both read the simple drawings. On a whole plant neither got every line right; the one that zoomed in piece by piece recovered more of the loops.