This case study demonstrates the material cost, time, and risk reduction achieved by avoiding a “direct-to-RSMF” workflow for chat data and instead applying search, filtering, and contextual expansion prior to RSMF formulation using StreemView. By operating on native chat messages first — rather than prematurely committing data into static 24-hour RSMFs — the legal team produced a dramatically smaller, more relevance-dense review population.
The outcome: a 97% reduction in review volume, a 96% reduction in review cost, and substantial downstream efficiencies that would not have been achievable in a traditional workflow.
Background and Challenge
Modern chat data (Slack, Teams, text messages, and similar platforms) is fundamentally conversational — not document-centric. Traditional workflows that promote all collected chat data directly into 24-hour RSMF files before any search or filtering treat a message feed the same way they treat a static document. The result is a massive, context-bloated review population where each search hit drags in an entire calendar day’s messages — most of them irrelevant.
This matters more when the data volume is large.
