Sanaf AI
Start free
Developer Tools

Langfuse, worked by an AI employee

Not another app for your team to learn, and not a set of rules for you to build. You hire an AI employee, you give it access to your Langfuse account, and you ask it for things in Slack or Teams the way you would ask anyone else on the team. There is nothing to map and nothing to maintain.

  • Developer Tools
  • Connects with a key
  • 13 ready-made tools
  • Asked in Slack or Teams
At work

An illustration of how the conversation reads, not a transcript from a client account.

What Langfuse is

Open source LLM engineering platform. Traces, evals, prompt management and metrics to debug and improve your LLM application.

You paste in a key from your own Langfuse account. It is kept encrypted, and you can withdraw it from inside Langfuse whenever you like.

How a run works

One message in, the work done in Langfuse.

  1. 01

    You ask

    You message your AI employee in the chat your team already has open, in one sentence, in your own words.

  2. 02

    It works out the step

    It decides what the job needs in Langfuse. You do not pick anything from a menu or wire anything together.

  3. 03

    It does the work

    Signed in to your own Langfuse account, inside the access you granted it, doing the thing you asked for.

  4. 04

    It reports back

    It tells you what it did, in the same thread. If it could not do something, it says so rather than guessing.

13 tools it already has

What it can do in Langfuse

These are the ready-made tools your AI employee already has in Langfuse. It is not limited to them, but it never has to be taught these.

  • Create ScoreAttach an evaluation score to exactly one Langfuse trace, session, or dataset run, optionally narrowing a trace score to an observation.
  • Get Annotation QueueRetrieve one Langfuse annotation queue by its ID.
  • Get PromptRetrieve a Langfuse text or chat prompt by name, deployment label, or exact version, with optional dependency resolution.
  • List Annotation QueuesList annotation queues configured for human evaluation in the connected Langfuse project.
  • List Dataset ItemsList dataset items, optionally scoped to a dataset, source trace or observation, or historical dataset version.
  • List Dataset Run ItemsList run items for a specific Langfuse dataset and run name.
  • List DatasetsList datasets available to the connected Langfuse project.
  • List ExperimentsList Langfuse experiments active in a required time range, optionally including metadata and directly attached scores.
  • List ModelsList Langfuse-managed and project-custom model pricing definitions used for usage and cost calculation.
  • List ObservationsSearch Langfuse observations such as generations, spans, events, agents, and tool calls, selecting only the field groups needed.
  • List ScoresSearch numeric, boolean, categorical, text, and correction scores with subject and annotation context.
  • Query MetricsRun an aggregate Langfuse metrics query over observations or numeric, boolean, or categorical scores.
  • Upsert LLM ConnectionCreate or update a Langfuse LLM provider connection by provider name.
Access, and who is in charge of it

You stay the boss of your Langfuse account.

Nothing connects until you approve it. You grant access one app at a time, you can take it back the same way, and everything your AI employee does in there is written down where you can see it.

How we handle your data
  • It signs in to your own Langfuse account. You are not moving anything into ours.
  • You grant access one app at a time, and you can take it back the same way.
  • Everything it does in Langfuse is written down, with what it did and when.
  • Anything you tell it to check with you first, it checks with you first.
Other apps in the same corner of the business

It works in Langfuse and the rest of your software in the same job

A real job rarely stays in one place. Reading a message in one app, checking a record in another and writing the result in a third is one request to your AI employee, not three.

See every app

Questions people ask about Langfuse

Can an AI employee really work inside Langfuse?
Yes. It signs in to your own Langfuse account and works in it the way a new hire would, from the chat your team already has open. Nobody installs anything, and nobody learns a new screen.
Do I have to move anything out of Langfuse?
No. Nothing moves and nothing is replaced. Your records stay in Langfuse, your team carries on in the same screens they used yesterday, and your AI employee works alongside them in there.
How does it get into my Langfuse account?
You paste in a key from your own Langfuse account. It is kept encrypted, and you can withdraw it from inside Langfuse whenever you like. You approve it before anything connects, and you can take the access back the same way you gave it.
What can it actually do in Langfuse?
It has 13 ready-made tools in Langfuse today, among them Create Score, Get Annotation Queue and Get Prompt. The full list is on this page. It is not limited to those, but it never has to be taught them.
Can it use Langfuse and the rest of my software in the same job?
Yes, and that is usually the point. Reading a message in one app, checking a record in Langfuse and writing the result somewhere else is one request to your AI employee, not three separate ones you stitch together.
Who decides what it is allowed to do in Langfuse?
You do. You grant access one app at a time and can withdraw it at any time, anything you ask it to check with you first it checks with you first, and everything it does in Langfuse is written down with what it did and when.