Monitor your agents at runtime

Install the Flint AI SDK to capture live traces of your agents in production. Within minutes, see what your agents actually do — prompts, responses, models called, and guardrail events.

Requirements: Python 3.10 or laterSupported with flintai_sdk.wrap(): OpenAI, Anthropic, LangChain (ChatOpenAI, ChatAnthropic, ChatGoogleGenerativeAI), Google GenAIGoogle ADK: Use ADKGuardrailsPlugin instead of wrap() — see SDK Usage guide

Install the SDK in your agent's environment

On your local machine or wherever your agent code runs:

pip install flintai-sdk-py

Optional: Install with provider extras

If you need specific provider dependencies:

pip install "flintai-sdk-py[openai]"     # OpenAI
pip install "flintai-sdk-py[anthropic]"  # Anthropic
pip install "flintai-sdk-py[genai]"      # Google GenAI
pip install "flintai-sdk-py[adk]"        # Google ADK
pip install "flintai-sdk-py[all]"        # All providers

Log into Flint AI Platform and register your agent for monitoring:

Navigate to Agents and select Add agents
Choose Monitor & protect agents > Install SDK
Enter a name for your agent (for example, “Customer Support Bot”)
Select your agent to open its Sessions tab

The setup page shows the values you need:

Gateway URL - Shown in the code snippet on the Sessions tab
API key - Use an existing Flint AI API token, or create one now if you don’t yet have one. Tokens are managed in Settings → API Keys.

Copy your token immediately when created — it will only be shown once.

Wrap your LLM client in your agent code

Import flintai_sdk and wrap your existing LLM client.

Using environment variables: Instead of hardcoding credentials, set FLINTAI_GATEWAY_URL and FLINTAI_API_KEY as environment variables, then call flintai_sdk.wrap(client) without parameters.

OpenAI
Anthropic
LangChain
Google GenAI

import openai
import flintai_sdk

client = openai.OpenAI(api_key="your-openai-api-key")
client = flintai_sdk.wrap(
    client,
    gateway_url="https://your-gateway-url",
    api_key="your-flintai-api-key",
)

response = client.chat.completions.create(
    model="gpt-4",
    messages=[{"role": "user", "content": "Hello"}],
)

import anthropic
import flintai_sdk

client = anthropic.Anthropic(api_key="your-anthropic-api-key")
client = flintai_sdk.wrap(
    client,
    gateway_url="https://your-gateway-url",
    api_key="your-flintai-api-key",
)

message = client.messages.create(
    model="claude-sonnet-4-20250514",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello"}],
)

from langchain_openai import ChatOpenAI
import flintai_sdk

llm = ChatOpenAI(model="gpt-4", api_key="your-openai-api-key")
llm = flintai_sdk.wrap(
    llm,
    gateway_url="https://your-gateway-url",
    api_key="your-flintai-api-key",
)

response = llm.invoke("Hello")

import google.genai
import flintai_sdk

client = google.genai.Client(api_key="your-gemini-api-key")
client = flintai_sdk.wrap(
    client,
    gateway_url="https://your-gateway-url",
    api_key="your-flintai-api-key",
    llm_api_key="your-gemini-api-key",  # Required for Google GenAI
)

response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents="Hello",
)

Google ADK: Use ADKGuardrailsPlugin instead of wrap() — see the SDK Usage guide for details.

Run your agent

Run your agent as you normally would. The SDK captures each LLM interaction automatically.

View your traces

Back in Flint AI Platform, navigate to Agents and select your agent, then open the Sessions tab.Within moments, you’ll see:

Sessions - Individual agent runs
Traces - Every LLM call with prompts, responses, model info, and latency
Guardrail events - Any policy actions (if configured)

Add runtime protection: Pass policy_id="your-policy-id" to flintai_sdk.wrap() to enforce guardrails. Policies apply input/output detectors that can block, redact, or alert on unsafe content before it reaches users. Learn more →

Overview

Getting Started

Rules Reference

Resources

Monitor your agents at runtime

Next steps

SDK Configuration

SDK Usage

​Next steps

SDK Configuration

SDK Usage

Next steps