> ## Documentation Index
> Fetch the complete documentation index at: https://docs.openserv.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Improve prompt reliability with Kronos

> Audit and repair SERV's generated reasoning prompt before inference.

<Frame>
  <img src="https://mintcdn.com/openserv/wCXyJJTiOX6drWSJ/images/tutorials/kronos.webp?fit=max&auto=format&n=wCXyJJTiOX6drWSJ&q=85&s=4019913a26ae57ecb65fb9a3c9d6141e" alt="A reasoning prompt passing through a Kronos audit checkpoint and repair loop" width="1536" height="1024" data-path="images/tutorials/kronos.webp" />
</Frame>

Kronos audits the reasoning prompt SERV generates from your system prompt. If the audit finds a semantic problem, SERV repairs the generated prompt and checks it again before sending the request to the model.

## Enable Kronos

Add `-serv-kronos` to a supported base model ID. The suffix is a model feature, not an application tool, so you do not add a function definition or implement a handler for it.

```js theme={null}
const response = await client.chat.completions.create({
  model: "gpt-5.4-mini-serv-kronos",
  messages: [
    {
      role: "system",
      content: "Approve refunds only when the order is eligible and the customer provides the order ID.",
    },
    { role: "user", content: "Can I get a refund for order 1842?" },
  ],
});
```

SERV removes the feature suffix before routing to the upstream provider. Use a real base model from the [model catalog](../models), then append `-serv-kronos` exactly once.

## When to use Kronos

Use Kronos for system prompts with procedural rules, multiple conditions, or consequences that must remain consistent. It is especially useful when a small ambiguity in the instructions could change the model's decision.

Kronos does not replace application authorization, tool-argument validation, or testing. Keep those checks in your application.

## Cost and behavior

Kronos adds audit work and may add repair work to the SERV prompt-generation phase. This increases cost and latency when that work runs. Prompt caching can reuse the audited result for matching requests; the upstream model still runs for every request. See [Monitor usage and billing](./usage-and-billing).

You can combine Kronos with Multipath by using `-serv-kronos-multipath`. See [Use Multipath for branching instructions](./multipath).