Atla

Integrate `Atla` with Kern for real-time monitoring, automated evaluation, and performance analytics of your AI agents.

Atla is an advanced observability platform designed specifically for AI agent monitoring and evaluation. This integration provides comprehensive insights into agent performance, automated quality assessment, and detailed analytics for production AI systems.

Prerequisites

API Key: Obtain your API key from the Atla dashboard

Install the Atla Insights SDK with Kern support:

1uv pip install "atla-insights"

Configuration

Configure your API key as an environment variable:

1export ATLA_API_KEY="your_api_key_from_atla_dashboard"

Example

1from os import getenv
2from kern.agent import Agent
3from kern.models.openai import OpenAIResponses
4from kern.tools.hackernews import HackerNewsTools
5from atla_insights import configure, instrument_agno
6
7# Step 1: Configure Atla
8configure(token=getenv("ATLA_API_KEY"))
9
10# Step 2: Create your Kern agent
11agent = Agent(
12    name="Market Analysis Agent",
13    model=OpenAIResponses(id="gpt-5.2"),
14    tools=[HackerNewsTools()],
15    instructions="Provide professional market analysis with data-driven insights.",
16    debug_mode=True,
17)
18
19# Step 3: Instrument and execute
20with instrument_agno("openai"):
21    response = agent.run("Retrieve the latest news about the stock market.")
22    print(response.content)

Now go to the Atla dashboard and view the traces created by your agent. You can visualize the execution flow, monitor performance, and debug issues directly from the Atla dashboard.