Quickstart

New to Trodo? Trodo is an observability platform for AI agents. Every agent execution becomes a trace — a structured record of timing, inputs, outputs, LLM calls, and tool invocations — so you can understand exactly what your agent did and where it went wrong. Learn more about the concepts →

Agentic setup

Install the Trodo AI skill to let your coding agent integrate Trodo automatically. It detects your framework, picks the right integration path, and knows the common pitfalls.

Ask your coding agent
Manual installation

Point your agent at the skill repository and ask it to add tracing:

Install the Trodo AI skill from github.com/trodoai/skills
and use it to add tracing to this application.

The skill works with Cursor, Claude Code, Windsurf, and any other assistant that can read files in your repo or fetch from GitHub.

Clone the repository and copy the skill into your project:

git clone https://github.com/trodoai/skills.git
cp -r skills/trodo-tracing .cursor/rules/trodo-tracing

Then prompt your agent:

Use the Trodo AI skill in .cursor/rules/trodo-tracing
to add tracing to this application.

The agent will install the SDK, wire up trodo.init(), wrap your agent entry point with wrapAgent, and tell you which env var to set.

Manual setup

Prefer to do it by hand? Three steps.

1. Install

Node.js
Python

npm install trodo-node

pip install trodo-python

Grab your site ID from app.trodo.ai → Settings → Sites and set it as TRODO_SITE_ID in your environment.

2. Initialise once at boot

Call init at your app entry point, before any provider client (OpenAI, Anthropic, LangChain, etc.) is imported. That’s how auto-instrumentation attaches itself to their SDKs.

Node.js
Python

import trodo from 'trodo-node';
trodo.init({ siteId: process.env.TRODO_SITE_ID });

import os, trodo
trodo.init(site_id=os.environ["TRODO_SITE_ID"])

3. Wrap your agent

wrapAgent records everything inside the callback as one run. LLM calls, tool calls, retrieval — all captured as child spans with zero extra code.

Node.js
Python

import trodo, { wrapAgent } from 'trodo-node';
import { openai } from '@ai-sdk/openai';
import { generateText } from 'ai';

trodo.init({ siteId: process.env.TRODO_SITE_ID });

const supportBot = (userId: string, threadId: string, question: string) =>
  wrapAgent('support-bot', async (run) => {
    run.setInput({ question });
    const result = await generateText({ model: openai('gpt-4o'), prompt: question });
    run.setOutput({ answer: result.text });
    return result.text;
  }, { distinctId: userId, conversationId: threadId });

const { result, runId } = await supportBot('user-42', 'thread-abc', 'What is the capital of France?');

import os, trodo
from openai import OpenAI

trodo.init(site_id=os.environ["TRODO_SITE_ID"])
client = OpenAI()

def support_bot(user_id: str, thread_id: str, question: str) -> str:
    with trodo.wrap_agent("support-bot", distinct_id=user_id, conversation_id=thread_id) as run:
        run.set_input({"question": question})
        resp = client.chat.completions.create(
            model="gpt-4o",
            messages=[{"role": "user", "content": question}],
        )
        answer = resp.choices[0].message.content
        run.set_output({"answer": answer})
        return answer

answer = support_bot("user-42", "thread-abc", "What is the capital of France?")

See your trace in Trodo

Open the Trodo dashboard and navigate to Agent Analytics → Runs. Your run appears within a few seconds — click it to see timing, input, output, and every child span from provider instrumentation.

Next steps

Concepts — runs, spans, kinds, propagation.
Tracing → wrapAgent — every option on the run.
Integrations — per-framework setup and auto-capture tables.
Recipes — copy-paste examples for common app shapes.

GETTING STARTED

TRACING

INTEGRATIONS

Agentic setup

Manual setup

1. Install

2. Initialise once at boot

3. Wrap your agent

See your trace in Trodo

Next steps

GETTING STARTED

TRACING

INTEGRATIONS

Documentation Index

​Agentic setup

​Manual setup

​1. Install

​2. Initialise once at boot

​3. Wrap your agent

​See your trace in Trodo

​Next steps

Agentic setup

Manual setup

1. Install

2. Initialise once at boot

3. Wrap your agent

See your trace in Trodo

Next steps