Spans must be inserted before decision points due to DecisionPoint.parentSpanId FK referencing Span.id. Switched from nested Prisma create to interactive transaction with topological span ordering. Also adds real MoonshotAI LLM test script.
AgentLens Examples
Example scripts demonstrating the AgentLens SDK for tracing and observing AI agent behavior.
Setup
pip install vectry-agentlens
Examples
| Script | Description |
|---|---|
basic_agent.py |
Simplest usage — init, trace, log decisions, shutdown |
openai_agent.py |
OpenAI integration — wrap the client for automatic LLM call tracing |
multi_agent.py |
Nested traces — planner delegates to researcher, writer, and editor sub-agents |
customer_support_agent.py |
Realistic support workflow — classification, routing, escalation, error handling |
seed_demo_traces.py |
Seeds the live dashboard with 11 realistic traces via direct HTTP POST (no SDK) |
Running
Each SDK example follows the same pattern:
# Set your API key and endpoint
export AGENTLENS_API_KEY="your-key"
# Run any example
python examples/basic_agent.py
For the OpenAI example, you also need:
pip install openai
export OPENAI_API_KEY="sk-..."
Seed Script
The seed script sends pre-built traces directly to the API — no SDK or OpenAI key needed:
python examples/seed_demo_traces.py
This populates the dashboard with varied traces (COMPLETED, ERROR, RUNNING) across multiple agent types.