Skip to content

Quick Start

Track your first AI interaction in under 5 minutes.

Prerequisites

Step 1: Install

pip install atheon-codex

npm install @atheon-inc/codex

Step 2: Initialise & Track (Backend)

Call init() once at startup, then track() after every LLM call. Both are non-blocking, so your API response time is unaffected.

import os
import atheon

# Call once at application startup
atheon.init(os.environ["ATHEON_API_KEY"])

# Inside your chat handler
user_query  = "How do I center a div?"
llm_output  = "You can use Flexbox..."

interaction_id, prompt_hash, fingerprint = atheon.track(
    provider="openai",
    model_name="gpt-4o",
    input=user_query,
    output=llm_output,
    tokens_input=14,
    tokens_output=32,
    finish_reason="stop",
)

# Return the payload to your frontend
return {
    "reply": llm_output,
    "interaction_id": str(interaction_id),
    "prompt_hash": prompt_hash,
    "fingerprint": fingerprint
}

import * as atheon from "@atheon-inc/codex";

// Call once at application startup. 
// This awaits the security handshake.
await atheon.init({ apiKey: process.env.ATHEON_API_KEY });

// Inside your chat handler
const userQuery = "How do I center a div?";
const llmOutput = "You can use Flexbox...";

const [interactionId, promptHash, fingerprint] = atheon.track({
    provider: "openai",
    modelName: "gpt-4o",
    input: userQuery,
    output: llmOutput,
    tokensInput: 14,
    tokensOutput: 32,
    finishReason: "stop",
});

// Return the payload to your frontend
return {
    reply: llmOutput,
    interaction_id: interactionId,
    prompt_hash: promptHash,
    fingerprint: fingerprint
};

Step 3: Render (Frontend)

Load the Atheon script. Wrap your prompt input in <atheon-input> and your LLM output in <atheon-output>, passing the backend attributes.

<script
  data-atheon-publisher-key="YOUR_PUBLISHER_KEY"
  src="https://js.atheon.ad/atheon.js"
  defer
></script>

<atheon-input>
  <textarea id="prompt-bar" placeholder="Ask a question..."></textarea>
  <button data-atheon-submit>Send</button>
</atheon-input>

<atheon-output id="chat-bubble">
  <div id="text-content"></div>
</atheon-output>

<script>
  const { reply, interaction_id, prompt_hash, fingerprint } = backendResponse;

  document.getElementById('text-content').innerText = reply;

  const bubble = document.getElementById('chat-bubble');
  bubble.setAttribute('interaction-id', interaction_id);
  bubble.setAttribute('prompt-hash', prompt_hash);
  bubble.setAttribute('fingerprint', fingerprint);
</script>

Step 4: Shut Down Gracefully

Call shutdown() when your process exits to flush any remaining queued events.

atheon.shutdown()

await atheon.shutdown();

That's it, your interaction is now tracked, fingerprinted, and visible in the Atheon Dashboard.

Next Steps