canonical: https://jentic.com/apis/smith.langchain.com/smith-langchain

# Smith Langchain LangSmith

The LangSmith API is used to programmatically create and manage LangSmith resources. Host https://api.smith.langchain.com Authentication To authenticate with the LangSmith API, set the `X-Api-Key` header to a valid [LangSmith API key](https://docs.langchain.com/langsmith/create-account-api-key#create-an-api-key). The API exposes 440 endpoints secured with apiKey, bearer authentication.

## For AI agents

Programmatically get audit logs, get tracing project prebuilt dashboard. Covers 440 operations with apiKey, bearer authentication.

## Scope

Does not handle payments, crm, or developer tools - use for communications only.

## Capabilities

- Get Audit Logs
- Read Tracer Session
- Update Tracer Session
- Delete Tracer Session
- Create Tracer Session

## Use cases

### Communications Operations

Use the LangSmith to perform communications operations programmatically. The API provides 440 endpoints covering core functionality including get audit logs, get tracing project prebuilt dashboard, read tracer session.

Example prompt: Call GET `/api/v1/audit-logs` to get audit logs

### Automated Ace Management

Automate ace operations by combining multiple LangSmith endpoints. Agents can get tracing project prebuilt dashboard and then read tracer session in a single workflow.

Example prompt: Call POST `/api/v1/sessions/{session_id}/dashboard` to get tracing project prebuilt dashboard, then verify the result

### AI Agent Integration via Jentic

AI agents discover and call LangSmith endpoints through Jentic without managing credentials directly. An agent searches for the required operation by intent, receives the matching endpoint schema, and executes the call with Jentic-managed authentication. This eliminates the need to read API documentation or handle apiKey, bearer tokens manually.

Example prompt: Search Jentic for 'get audit logs', load the operation schema, and execute with Jentic-managed credentials

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| GET | `/api/v1/audit-logs` | Get Audit Logs |
| POST | `/api/v1/sessions/{session_id}/dashboard` | Get Tracing Project Prebuilt Dashboard |
| GET | `/api/v1/sessions/{session_id}` | Read Tracer Session |
| PATCH | `/api/v1/sessions/{session_id}` | Update Tracer Session |
| DELETE | `/api/v1/sessions/{session_id}` | Delete Tracer Session |
| POST | `/api/v1/sessions` | Create Tracer Session |
| GET | `/api/v1/sessions` | Read Tracer Sessions |
| DELETE | `/api/v1/sessions` | Delete Tracer Sessions |

## Key resources

- **Ace** — Operations for ace
- **Agent Builder** — Operations for agent builder
- **Annotation Queues** — Operations for annotation queues
- **Api Key** — Operations for api key
- **Audit Logs** — Operations for audit logs

## Why Jentic

- **Setup:** Wiring LangSmith by hand means sending its X-API-Key or bearer token plus tenant and organization id headers against api.smith.langchain.com and managing retries yourself. Through Jentic you install once, import LangSmith from the API Directory, store the credential once, and your agent calls it.
- **Permission scoping:** LangSmith puts the session id in the URL path (`/api/v1/sessions/{session_id}`), so a rule can pin your agent to one session: it can read that session and its dashboard. You choose the operations it may call, so deleting a session is not included unless you add it.
- **Credential handling:** Your LangSmith credential is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
- **Discovery method:** Agents search Jentic by intent such as 'read a tracing session' or 'get audit logs', and Jentic returns the matching LangSmith operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

## Related APIs

- **Twilio** — Alternative communications API
- **Sendgrid** — Alternative communications API
- **Pusher** — Complementary communications API

## FAQ

### What authentication does the LangSmith use?

The LangSmith uses apiKey, bearer authentication. Through Jentic, these credentials are stored encrypted in your Jentic One instance and injected at execution time, so raw secrets never enter the agent context.

### Can I get audit logs with the LangSmith?

Yes. Use the GET `/api/v1/audit-logs` endpoint. The API returns structured JSON responses that agents can parse and act on directly.

### What are the rate limits for the LangSmith?

Rate limits are not specified in the OpenAPI spec. Check the vendor documentation for current limits. Through Jentic, rate limiting is handled automatically with retry logic built into the execution layer.

### How do I get audit logs through Jentic?

Install the Jentic SDK with pip install jentic, authenticate through Jentic One, the self-hosted execution layer, then search for 'get audit logs'. Jentic returns the matching LangSmith operation with its input schema. Load the schema and execute the call - credentials are injected automatically.

### How many endpoints does the LangSmith have?

The LangSmith exposes 440 endpoints covering ace, agent builder, annotation queues operations.

### Can I limit what my agent is allowed to do with the LangSmith API?

Yes. Because you run Jentic One yourself, your own rules decide which LangSmith operations and which credential the agent may use. Since the session id sits in the URL path (`/api/v1/sessions/{session_id}`), you can pin the agent to a single session so it only reads that session and its dashboard. Deleting a session or listing all sessions is excluded unless you explicitly grant those operations.