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.

Instrument a project with LLM Observability v1.0.0

Use this resource to instrument an AI backend with Datadog LLM Observability

New

  • 449 downloads
  • 169 likes
  • 160 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install instrument-llm-observability

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 detects the runtime, the LLM framework and existing instrumentation, then adds the SDK initialisation with the right parameters and the dependency in the deployment manifest. It also checks session ID plumbing and fixes any gaps it finds.

Mostly picked by

Updated November 2, 2026

Card for the “Instrument a project with LLM Observability” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • SKILL.md: analysis, routing and project verification
  • references/llmobs-python.md: instrumenting a Python project
  • references/llmobs-nodejs.md: instrumenting a Node.js project

Good fit for

  • Your AI agent loses track of user sessions
  • You want to see an LLM's calls and steps in Datadog

Not for

    Tags

    • LLM
    • observability
    • AI agents
    • Datadog

    About

    You say

    “Add LLM Observability to our Python backend that calls a support agent.”

    Card for the “Instrument a project with LLM Observability” skill

    Skill published by datadog-labs under the MIT 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 instrument an AI backend with Datadog LLM Observability
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/common-credentials.md1.9 KB
    • references/common-verify-report.md2.5 KB
    • references/llmobs-nodejs.md18.4 KB
    • references/llmobs-python.md16.9 KB
    • SKILL.md11.6 KB

    Origin and licence

    Listed unmodified

    Author
    datadog-labs
    Source
    github.com/datadog-labs/agent-skills/tree/ef022309cc6b6296e7574589ac332699b1c9a092/dd-instrument-llmo
    Licence
    MIT

    Notice

    « dd-instrument-llmo » (datadog-labs, MIT) 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.