Skip to main content

​
Welcome to Foil

Foil is an observability platform purpose-built for AI applications. Get complete visibility into your LLM calls, agent workflows, and AI pipelines with distributed tracing, real-time alerting, and actionable analytics.

​
Why Foil?

Building AI applications is hard. Debugging them is harder. Foil gives you the tools to understand what your AI is doing, why it’s failing, and how to make it better.

Distributed Tracing

Track every LLM call, tool execution, and agent step with full context and parent-child relationships.

Real-time Alerting

Get notified instantly when your AI hallucinates, gets stuck, or produces low-quality outputs.

Cost Analytics

Monitor token usage, latency, and costs across all your models and agents.

Custom Signals

Track user feedback, quality scores, and custom metrics tied to your traces.

​
How It Works

1

Install the SDK

Add the Foil SDK to your project with npm or pip.
npm install @foil-ai/sdk
2

Instrument Your Code

Wrap your AI calls with Foil’s tracer to capture every interaction.
const tracer = createFoilTracer({
  apiKey: 'your-api-key',
  agentName: 'my-agent'
});

await tracer.trace(async (ctx) => {
  // Your AI logic here
});
3

View in Dashboard

See your traces, metrics, and alerts in the Foil dashboard.

​
Features

​
Traces & Spans

Every AI interaction is captured as a trace containing multiple spans. Spans represent individual operations like LLM calls, tool executions, or retrieval steps. Foil automatically tracks:
  • Input and output content
  • Token usage (prompt, completion, total)
  • Latency and time-to-first-token
  • Errors and status codes
  • Custom metadata

​
Intelligent Alerting

Foil uses LLM analysis to detect issues that traditional monitoring misses:
  • Hallucination Detection - Identifies fabricated facts in outputs
  • Quality Analysis - Catches off-topic or incomplete responses
  • Loop Detection - Alerts when agents get stuck repeating themselves
  • Content Safety - Flags inappropriate or unsafe content

​
Signals & Feedback

Capture user feedback and custom metrics directly tied to your traces:
  • Thumbs up/down ratings
  • Star ratings
  • Sentiment analysis
  • Goal completion tracking
  • Custom metrics

Quickstart

Get up and running in 5 minutes

JavaScript SDK

Full-featured SDK with tracing support

Python SDK

Lightweight SDK for Python apps

API Reference

Complete REST API documentation