Developers

Add visibility without re-architecting your agent.

JeraViz is designed so that a few lines of instrumentation, or an OpenTelemetry exporter you may already run, produce a trace for every execution.

Read the quickstart preview Documentation

Integrate

Three ways in.

Python and TypeScript SDKs Launch scope
Decorators and context managers create spans for agents, model requests and tool calls. Batching and retries run in the background and never raise into your code.
OpenTelemetry (OTLP/HTTP) Launch scope
Already instrumented with OpenTelemetry? Point your exporter at JeraViz and map model and tool attributes. Conventions for generative AI are still evolving; the docs will state which version is supported.
Framework adapters Planned
Adapters for popular agent frameworks are planned after the first release. None are claimed today.

# Illustrative: not a published SDK
import jeraviz

jeraviz.init(
    api_key="YOUR_API_KEY",
    project="support-copilot",
    environment="staging",
)

@jeraviz.agent("refund-agent")
def handle_refund(ticket):
    # Each tool call becomes a span with arguments, result, duration and errors.
    with jeraviz.tool("payments_api.create_refund", args={"order_id": ticket.order_id}) as call:
        result = payments.create_refund(ticket.order_id)
        call.set_result(result)
    return result

Illustrative example. The JeraViz SDK is in development; names and signatures may change. Not a published package.

Developer toolkit

Everything around the SDK.

SDK integration
Python and TypeScript SDKs with decorators, context managers and automatic batching.
Launch scope
API access
REST API and OpenTelemetry (OTLP/HTTP) ingestion for anything you can instrument.
Launch scope
Documentation
Concepts, quickstart and reference. Starter docs are on this site now.
Launch scope
API keys
Keys scoped to a project and environment; shown once, stored hashed, revocable.
Launch scope
Project management
Projects and environments separate applications and stages such as staging and production.
Launch scope
Integration examples
Worked examples for common agent shapes. Framework adapters follow the first release.
Planned
Developer onboarding
A guided first run that ends with your first trace, plus a sample-data mode.
Launch scope

Onboarding

Designed to end at your first trace.

The planned first-run flow, from sign-up to a trace you can open. A sample-data mode lets you explore before you integrate; sample data is always labelled and never mixed with real telemetry.

01Create an account
02Create a workspace
03Create your first project
04Choose an integration method
05Generate an API key
06Install the SDK
07Send a sample execution
08Open your first trace
09Explore the dashboard

How an execution flows

1. Connect your AI application
Add the SDK (or point an OpenTelemetry exporter at JeraViz) and a project API key. No change to your agent architecture.
2. Capture execution events
Model requests, tool calls and handoffs are recorded as spans and sent in the background, so instrumentation does not block your agent.
3. Inspect traces and behavior
Open any execution to see the timeline, inputs, outputs, errors, tokens and estimated cost for each step.
4. Improve performance and reliability
Find the slow or failing step, fix it, and watch the trend change. Evaluations to lock in gains are on the roadmap.

Privacy controls

Full: Stores prompts, responses, tool arguments and results (subject to size limits and redaction rules).
Metadata only: Stores timing, status, tokens and names, but no payload text. Recommended for sensitive workloads.
Hashed payloads: Stores a hash of each payload so identical inputs can be recognized without storing the text.

What is captured

Build agents with visibility. Operate them with confidence.

Understand what your agents do, identify what needs improvement and build more reliable AI systems with JeraViz.

Start Building with JeraViz Read the docs

JeraViz Trace is in development. Sign-up is not open yet; the early-access page explains where things stand.