사전 계산된 컨텍스트로 더욱 빠르고 저렴하게 지원 조사 수행

Precomputed context cut input tokens by 58% and latency by 40% in Elastic’s support agent, making support investigations more efficient by reducing repeated retrieval. When a support engineer is assigned a case, the questions can sound straightforward: What happened, what evidence supports the root cause, and what should happen next? The answers may be spread across a case record, a long conversation feed, linked engineering issues and comments, knowledge articles, and related cases. Precomputed context gathers and organizes evidence from those related records before the agent receives a question.

The agent can then begin with the case relationships already identified, rather than reconstructing them during each response. In our evaluation, this approach resulted in lower input token use and latency, without a statistically significant reduction in factuality. Before adding precomputed context, the Support team at Elastic used an agent for case investigation, root cause analysis (RCA), triage, and related work. To answer a question, the agent had to discover relevant indices, inspect schemas, issue several queries, reconcile conflicting updates, and assemble a response.

Questions ranged from narrow state lookups to multisource investigations: What is the current status and priority of support case 1234567? After client ABC’s cluster migrated certificates, it returned Secure Sockets Layer (SSL) handshake and certificate_unknown errors. What caused the failure, and how should it be fixed? Which knowledge base articles are relevant? Client ABC’s cluster stopped processing indexing requests and returned 'rejected execution of primary operation' errors. What was the root cause, and how was service restored?

The next question about the same case or about a related case often required much of the same orientation and synthesis work. That repetition consumed input tokens and added latency. It also increased the chance of invalid queries or wrong source selection. Earlier work on precomputed context provided a starting point. It described extracting useful context ahead of time and storing it as structured Knowledge Indicators (KIs). Then it explained how an agent retrieves those compact records before scanning raw documents.