Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

Analyzing LLM app latency, cost and quality v1.0.0

Use this resource to analyze latency, cost and quality of LLM apps from ingested data

New

  • 466 downloads
  • 158 likes
  • 232 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install llm-application-observability-analysis

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent checks which data sources exist in Elastic (APM or OTLP traces, integrations), then answers only from them about performance, tokens, quality and agent orchestration. You get figures based on data actually ingested.

Mostly picked by

Updated November 2, 2026

Card for the “Analyzing LLM app latency, cost and quality” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
Apache-2.0

Similar resources

View all

What you get

  • SKILL.md: available data, process and output discipline
  • references/esql-recipes.md: ES|QL queries for LLM metrics
  • references/genai-fields.md: reference GenAI fields

Good fit for

  • Your token spend is rising without explanation
  • An agent calls tools in an order you don't understand

Not for

    Tags

    • llm
    • observability
    • tokens
    • cost

    About

    You say

    “Which model used the most tokens this week, and did its latency rise?”

    Card for the “Analyzing LLM app latency, cost and quality” skill

    Skill published by elastic under the Apache-2.0 license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to analyze latency, cost and quality of LLM apps from ingested data
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE11.3 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/esql-recipes.md8.6 KB
    • references/genai-fields.md6.7 KB
    • references/integrations.md4.7 KB
    • SKILL.md19.5 KB

    Origin and licence

    Listed unmodified

    Author
    elastic
    Source
    github.com/elastic/agent-skills/tree/cdcc551b6c3f254793a2fd6a179ff924f0bfbfb8/skills/observability/llm-obs
    Licence
    Apache-2.0

    Notice

    « observability-llm-obs » (elastic, Apache-2.0) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.