Cisco Launches ACE For Machine Data

Cisco introduces ACE (Analytics Context Engineering), a framework that constructs hybrid data views and a virtual filesystem to transform nested JSON/AST machine payloads for LLM consumption. ACE stores full-fidelity data in an external datastore, generates columnar and row-oriented views, and reports reductions in token usage (from 5,025 to 2,350) with improved answer accuracy in troubleshooting tests.
Key Points
- 1Transforms nested JSON into complementary columnar and row-oriented hybrid views for LLM consumption
- 2Reduces prompt size and inference cost by preserving full-fidelity datastore while optimizing LLM context
- 3Enables faster, more accurate troubleshooting workflows; cut tokens from 5,025 to 2,350 in tests
Scoring Rationale
Official Cisco engineering innovation delivers measurable token and accuracy gains, but scope currently focuses on observability-specific workflows.
Sources
Public references used for this report.
Practice interview problems based on real data
1,625 SQL & Python problems across 15 industry datasets — the exact type of data you work with.
Try 250 free problems