Quickstart | Respan Docs

Set up Respan

Sign up — Create an account at platform.respan.ai
Create an API key — Generate one on the API keys page
Add credits or a provider key — Add credits on the Credits page or connect your own provider key on the Integrations page

Use AI

Add the Docs MCP to your AI coding tool to get help building with Respan. No API key needed.

1 {
2   "mcpServers": {
3     "respan-docs": {
4       "url": "https://docs.respan.ai/mcp"
5     }
6   }
7 }

1. Set up your account

2. Set up tracing

Pick the method that matches your stack.

Respan tracing SDK

OpenAI Agents SDK

Anthropic Agents SDK

Vercel AI SDK

Others

Add @workflow and @task decorators to your code. LLM calls are auto-captured.

1 # pip install respan-tracing
2 from openai import OpenAI
3 from respan_tracing.decorators import workflow, task
4 from respan_tracing.main import RespanTelemetry
5 
6 k_tl = RespanTelemetry()
7 client = OpenAI()
8 
9 @task(name="joke_creation")
10 def create_joke():
11     completion = client.chat.completions.create(
12         model="gpt-4o-mini",
13         messages=[{"role": "user", "content": "Tell me a joke about AI"}],
14     )
15     return completion.choices[0].message.content
16 
17 @workflow(name="joke_workflow")
18 def joke_workflow():
19     return create_joke()
20 
21 result = joke_workflow()
22 print(result)

For advanced features (class-based workflows, override span I/O), see Tracing SDK.

3. See your first trace

Open the Traces page in the Respan dashboard. You should see your trace appear within a few seconds.

What’s next

Enrich your spans with customer_identifier, metadata, and thread_identifier.
Set up the gateway to route LLM traffic through one API with fallbacks, retries, and caching.