# Faster, cheaper support investigations with precomputed context

DevFeed: [Faster, cheaper support investigations with precomputed context](<https://devfeed.tech/articles/faster-cheaper-support-investigations-with-precomputed-context-78882.md>)

Original publisher: [Read original article](<https://www.elastic.co/search-labs/blog/reduce-token-usage-precomputed-context>)

Author: Abhimanyu Anand

Published: 2026-08-11T00:00:00Z

Content type: article

Language: en

Sources: [Elasticsearch Labs](<https://devfeed.tech/sources/elasticsearch-labs.md>)

Topics: [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [context window](<https://devfeed.tech/topics/context-window.md>)

Tags: [agent-builder](<https://devfeed.tech/tags/agent-builder.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [cache](<https://devfeed.tech/tags/cache.md>), [client](<https://devfeed.tech/tags/client.md>), [development](<https://devfeed.tech/tags/development.md>), [discovery](<https://devfeed.tech/tags/discovery.md>), [documentation](<https://devfeed.tech/tags/documentation.md>), [latency](<https://devfeed.tech/tags/latency.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [tokens](<https://devfeed.tech/tags/tokens.md>)

## AI overview

Elastic describes using precomputed case-level context in a support agent to reduce repeated retrieval and cross-source synthesis. In a small evaluation, the approach lowered observed input-token use and latency without a statistically significant reduction in factuality; the article treats the results as directional and notes that live case fields still require verification.

## Source excerpt

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.