GuidesAI reliability

Validate a model’s output before using it

By the Banzai Labs teamUpdated on 2 min read

JSONSchema+ rulesAcceptederror sent backNothing enters the system without passing the check
The model output goes through a schema and rules; on failure, the error is sent back to it.

Three levels of checks

  1. 1FormatParsable JSON, fields present.
  2. 2Types and valuesNumber, date, value from a list.
  3. 3Business rulesThe product exists, the discount is capped.

With Zod

import { z } from 'zod';

const Order = z.object({
  productId: z.string(),
  quantity: z.number().int().min(1).max(50),
  shipping: z.enum(['standard', 'express']),
});

async function extract(text: string, retries = 2) {
  let prompt = text;
  for (let i = 0; i <= retries; i++) {
    const raw = await callModel(prompt);
    const r = Order.safeParse(raw);
    if (r.success && (await productExists(r.data.productId))) return r.data;
    prompt = `${text}\n\nThe previous answer was invalid: ${r.success ? 'unknown product' : r.error.message}`;
  }
  return null; // fallback: human review
}

What is often checked

Output Check
Amount Positive, capped, right currency
URL Domain on an allowlist
Recipient Existing contact, not an invented address
Category Value from a closed list
Published text Length, banned words, review if sensitive

The technique: reliable JSON from an LLM. The risks: AI hallucinations and prompt injection.

Frequently asked questions

Doesn’t a forced tool already guarantee the format?
It makes the right format very likely, and some modes guarantee the schema is respected. Business rules (a positive price, a future date, an ID that exists) still have to be checked in your code.
How many retries?
One or two are usually enough. Beyond that, the problem lies in the instructions or the input data: fall back and log the case.
What fallback should I plan?
A safe default value, a human review queue, or a clear message to the user. Never invalid data saved silently.

Read next

All guides