02GENERATIONS

Every prompt and completion

A generation is a single model call. Currai records the exact prompt you sent, the completion you got back, the model and its parameters, and how long it took — so you can replay any response and understand why the model said what it said.

Full input and output payloads, including system and tool messages.
Model name plus temperature, top_p, max_tokens and any custom parameters.
Latency and time-to-first-token captured for every call.
Attach your own evaluation scores as metadata to record output quality on each call.

↗See your generations

Capture a generation ✍️

gen = trace.generation(
    name="openai.chat.completions",
    model="gpt-4o-mini",
    model_parameters={"temperature": 0.2, "max_tokens": 512},
    input=messages,
)

reply = client.chat.completions.create(model="gpt-4o-mini", messages=messages)

gen.end(output=reply.choices[0].message.content)

Use every prompt and completion in production

Capture inputs, outputs, model and parameters for every LLM call. Currai keeps this information connected to the conversation, user, session, and supporting trace so product and engineering teams can investigate the same evidence.

Start with one production workflow, verify the captured data, and use the resulting evidence to find recurring friction, debug failures, and measure whether each release improves the agent experience.

Follow the Currai getting-started guide to connect a real agent, then review the AI agent monitoring playbook for a practical production workflow.

↗Get Started