Improved response times and token usage

Open

#369 opened on Jul 22, 2026 0 comments 0 reactions 1 assignee View on GitHub

@akm-esco is already working on this.

Since Jul 22, 2026.

Assessment

This issue has not been assessed yet.

Description

product-area:search

Get faster responses at lower token cost, automatically. The agent routes specific tasks to faster, specialized models and removes extra LLM calls that inflate token usage, benefiting every Agent Builder user by default.

What the feature is
The agent optimizes model selection for specific tasks to enable faster responses at lower token cost. Architectural changes reduce and remove extra LLM calls that expand token usage, and route specific tasks like query generation to faster models with more specialized context.

Who
Who: Every Agent Builder user, with the improvements applied by default and no configuration required.

Why it matters
Responses get faster and token costs drop at the same time, for every user, without anyone having to opt in or tune anything.

Key user stories / use cases
high-volume agents, cost-sensitive deployments, latency-sensitive workflows.

Dominant language: No language data
Stars: 6
Forks: 1
PR merge metrics: No merged PRs in 30d

Contributor guide

No contributing guide indexed for this repository

First steps

Read the whole issue, then the project's contributing guide.
Comment on the issue to say you are picking it up — it saves two people doing the same work.
Fork the repository and make your change on a branch.
Open a pull request that references the issue number.

Improved response times and token usage

Assessment

Description

Contributor guide

First steps

More from elastic/roadmap

Get new issues in your inbox