Bento Documentation

bento.track_ai is the manual path. Call it once per LLM site you want in Bento. Use it for SDKs without an integration (OpenAI, Anthropic, Bedrock, Vertex, anything else), or alongside an integration for custom events.

import bentolabs_sdk.analytics as bento

bento.track_ai(
    event="user_message",
    user_id="user_42",
    convo_id="conv_abc",
    model="gpt-4o",
    provider="openai",
    input="What's the capital of France?",
    output="Paris.",
)

Each call ships one span. It lands in the dashboard within seconds.

Arguments

str

required

Event name, shown as the row title.

str

Your stable user identifier. Pass-through string; no profile data is stored.

str

Conversation or session ID. Same value across turns links them in the timeline view.

str

Model identifier, e.g. gpt-4o or claude-3-5-sonnet-20241022. Required for cost and per-model breakdowns.

str

Provider key. One of openai, anthropic, google, aws_bedrock, azure_openai, cohere, mistral. Not auto-inferred from model name.

str | dict | list

Prompt or input. Strings pass through; dicts and lists are JSON-serialized.

str | dict | list

Model output. Same serialization rules as input.

dict

Custom dimensions. See Properties.

Returns the span ID as a 16-character hex string.

Pass all four

If you skip any of these, the dashboard column behind it stays empty for that call. The defaults you almost always want:

Argument	What you lose if you skip it
`user_id`	User filter and per-user breakdowns.
`convo_id`	Multi-turn conversations look like N independent rows.
`model`	Cost view and per-model breakdowns.
`provider`	Provider filter. Bento does not guess from the model name.

Bedrock model IDs like anthropic.claude-3-sonnet-20240229-v1:0 need provider="aws_bedrock", not "anthropic". The model ID is ambiguous on purpose; the provider tag breaks the tie.

Common shapes

A single LLM call

resp = client.chat.completions.create(model="gpt-4o", messages=messages)
reply = resp.choices[0].message.content

bento.track_ai(
    event="chat",
    user_id=user.id,
    convo_id=conv_id,
    model="gpt-4o",
    provider="openai",
    input=messages,
    output=reply,
)

Multi-turn conversation

Pass the same convo_id on every turn:

convo = "conv_2026-05-10_user42"

bento.track_ai(event="user_msg",      input="Hi",        convo_id=convo, user_id="u1", model="gpt-4o", provider="openai")
bento.track_ai(event="assistant_msg", output="Hello!",   convo_id=convo, user_id="u1", model="gpt-4o", provider="openai")
bento.track_ai(event="user_msg",      input="And then?", convo_id=convo, user_id="u1", model="gpt-4o", provider="openai")

Structured chat messages

Dicts and lists are JSON-serialized:

bento.track_ai(
    event="chat",
    input=[
        {"role": "system", "content": "You are helpful."},
        {"role": "user", "content": "Hi"},
    ],
    output={"role": "assistant", "content": "Hello!"},
    user_id="u1",
    convo_id="conv_abc",
    model="gpt-4o",
    provider="openai",
)

Streaming

Call track_ai once after the stream finishes. Accumulate the output, then emit one event:

chunks = []
for chunk in client.chat.completions.create(model="gpt-4o", messages=messages, stream=True):
    chunks.append(chunk.choices[0].delta.content or "")
full = "".join(chunks)

bento.track_ai(
    event="streamed_chat",
    user_id=user.id, convo_id=conv_id,
    model="gpt-4o", provider="openai",
    input=messages, output=full,
)

Parenting

bento.track_ai calls are root spans by default. They detach from any caller’s OTel context, so calling track_ai inside a FastAPI or Django request doesn’t pull the LLM event into that trace. Inside a bento.begin(...) block, track_ai calls become children of the trajectory instead, so the whole multi-step turn renders as one trace.

Integrations

Drop the per-call wrapping for Google ADK.

Properties

Tag events with arbitrary custom dimensions.

Trajectories

Group multi-step work into one trace.

Attributes mapping

How each argument lands in the dashboard.

Get started

Integrations

Manual tracking

Advanced

Tracking events

Arguments

Pass all four

Common shapes

A single LLM call

Multi-turn conversation

Structured chat messages

Streaming

Parenting

See also

Integrations

Properties

Trajectories

Attributes mapping

​Arguments

​Pass all four

​Common shapes

​A single LLM call

​Multi-turn conversation

​Structured chat messages

​Streaming

​Parenting

​See also

Integrations

Properties

Trajectories

Attributes mapping

Arguments

Pass all four

Common shapes

A single LLM call

Multi-turn conversation

Structured chat messages

Streaming

Parenting

See also