Quick start

Connect application events from JavaScript, Python, Go or Rust.

For setup and management entirely from a coding agent, see the headless workflow and SDK platform clients.

Copy this into your coding agent

Paste into Cursor, Codex, Claude Code, or another coding agent in your project.

Set up Bench in this repository using https://docs.usebench.ai/sdk/quickstart.
Inspect the app and use the installation command and setup key from my Bench SDK page.
Keep the key server-side, start with metadata-only capture, and label the environment.
Instrument one real app operation, send a synthetic request, and flush the events.
Confirm Bench received it. Show what changed and any steps I still need to complete.

Beta. Choose a language below for installation, tracing and real app tests.

Choose your language: JavaScript/TypeScript, Python, Go or Rust.

Set up with your coding agent

1. Open SDK in Bench

   Open SDK in the sidebar, or Production → Set up SDK inside a system. Choose your language. Bench prepares your account setup key automatically. SDK access is included on every plan.

2. Copy the agent prompt

   Under Set up using a coding agent, select Copy prompt. Paste it into Claude Code, Cursor, Codex, or another trusted coding agent in your application repository. The prompt includes your setup key, installation command and API endpoint. Your coding agent reads the repository, branch and deployment configuration from the open project. Use a trusted agent: that prompt contains a secret. Do not commit or share it. You can return to setup to copy the same account key. Revoke it from API keys if needed.

3. Verify an interaction

   The agent adds server-side instrumentation and sends a synthetic metadata-only trace. SDK setup shows Waiting for first event, then SDK events received once ingestion succeeds. Open AI systems, select the system, then Production.

The automatic setup key belongs to your account and has a zero evaluation cap. Creating it does not start a paid evaluation. For narrower access, create a key restricted to specific repositories in API keys. Manage or revoke keys there.

Set an explicit environment, such as staging or production, in the SDK options to distinguish received deployments. Connection status shows the last accepted event for a system/environment, not a live heartbeat or proof that every route has instrumentation. A silent application cannot be distinguished from an absent SDK using telemetry alone.

Choose your language

Language	Guide	Includes
TypeScript / JavaScript	TypeScript and JavaScript	Tracing, real app tests and scripted conversations
Python	Python	Sync and async tracing, real app tests and simulations
Go	Go	Context-aware tracing, real app tests and simulations
Rust	Rust	Async tracing, real app tests and simulations

Each guide includes a coding-agent prompt, a connection example and lifecycle instructions. Automatic framework adapters are coming soon.

What Bench recognizes

systemName names the agent or workflow. If omitted, the repository name is used. The first trace creates a system for that name, repository and branch. This identifies where events came from. You can add its intended business outcome on the system’s Understanding page. GitHub scans or uploaded prompts still provide the prompt definitions needed for prompt benchmarking. Systems connected only through the SDK can receive and display traces before those definitions are connected.

Wrap agents and tools using your language guide. Follow its context instructions to retain parent IDs. Use a real prompt component ID from Bench to connect a span to discovered criteria, or link it from Production. Do not invent component IDs.

Frameworks

Wrap your existing Node/server call for Vercel AI SDK, Mastra, OpenAI Agents, LangChain, LangGraph, Deep Agents or a custom workflow. Await the full invocation and instrument the tools whose behavior you want to inspect. This release does not automatically patch those libraries. It is not an OTLP collector, browser SDK or a guarantee of complete agent tracing. Use the separate Python, Go and Rust clients for those languages. More automatic framework adapters are coming soon.

For a reusable coding-agent guide, see skills/bench-sdk/SKILL.md inside the installed package. Follow production checks when ready to evaluate.

Find your activity

Open an AI system’s Production tab. Recent interactions appear after the SDK sends them. The Quickstart button opens this guide in a new tab; Set up SDK opens the in-app setup. Capturing metadata does not start an evaluation.

Use development, staging and production

Set BENCH_ENVIRONMENT in each deployment. Open Event environment in a system’s Production tab to select the events you want to inspect. A staging event confirms staging receipt; it does not mark production as connected. Older events without an environment appear under Not specified.

Environments share your Bench account, permissions and evaluation allowance. A label does not switch your application’s payment, email or database credentials. Use separate test credentials and fixture data when testing side effects. Learn more in environments.

If no event arrives

Check the endpoint and API key, confirm the instrumented code ran, and flush before a short-lived process exits. Look for SDK delivery errors in your server logs without printing credentials. A deployment with no recent requests may have no recent events even when the SDK is installed.

After confirming receipt, replace the synthetic callback with an existing app operation. For long-running servers, reuse the Bench instance and call shutdown() on shutdown. For serverless handlers, await flush() before the request lifecycle ends.

Trace identifiers

The SDKs generate trace and span IDs automatically. If you send events directly, use a nonzero 32-character lowercase hexadecimal trace ID and a nonzero 16-character lowercase hexadecimal span ID. Parent span IDs use the same format. Do not use emails, customer IDs or other personal information as identifiers. Invalid identifiers are rejected.