Skip to content
POST/api/v1/compliance/policy-to-code

Convert policy text to enforcement code

Given a compliance control id (`controlId`) — one of `eu-ai-act.art-15`, `soc2.cc6.1`, `hipaa.164.308a1`, `owasp-llm.01-prompt-injection` — returns a pre-authored guardrail template: a natural-language check, a firewall rule body, Python and TypeScript SDK snippets, a reference URL, and a `confidence` label of `high`/`medium`/`low`. Deterministic static lookup, no LLM call. An unknown or omitted `controlId` falls back to a `confidence: "low"`, `enabled: false` template whose match value is derived from the supplied `policyText`; `policyText` has no effect when a known `controlId` matches. `availableControls` lists the recognised ids. No test cases are returned. Generated rules require human review before deploy.

Authentication

Send Authorization: Bearer YOUR_API_KEY on every request. Generate API keys at /dashboard/settings/api-keys.

Request body required

Example

{
  "controlId": "string",
  "policyText": "string"
}
Schema
{
  "application/json": {
    "schema": {
      "type": "object",
      "properties": {
        "controlId": {
          "type": "string",
          "maxLength": 500
        },
        "policyText": {
          "type": "string",
          "maxLength": 50000
        }
      },
      "additionalProperties": false
    }
  }
}

Response

200 example

{
  "success": true
}

All status codes

200Generated rule.
400(no description)
401(no description)
403Forbidden — insufficient role for this operation.
429(no description)
500Internal Server Error — an unhandled error was converted to the standard error envelope (INTERNAL_ERROR).

Code samples

cURL

curl -X POST \
  https://evalguard.ai/api/v1/compliance/policy-to-code \
  -H "Authorization: Bearer $EVALGUARD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "controlId": "string", "policyText": "string" }'

TypeScript

// The TypeScript SDK (@evalguard/sdk) exposes TYPED methods — runEval,
// getEval, runSecurityScan, checkFirewall, … — not a generic request().
// For an arbitrary endpoint, call it directly:

const res = await fetch("https://evalguard.ai/api/v1/compliance/policy-to-code", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.EVALGUARD_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "controlId": "string",
    "policyText": "string"
  }),
});
console.log(res.status, await res.json());

Python

# The Python SDK (pip install evalguardai) exposes TYPED methods on
# EvalGuardClient — run_eval, get_eval, … — not a generic request().
# For an arbitrary endpoint, call it directly:

import os
import requests

headers = {"Authorization": f"Bearer {os.environ['EVALGUARD_API_KEY']}"}
headers["Content-Type"] = "application/json"

response = requests.request(
    "POST",
    "https://evalguard.ai/api/v1/compliance/policy-to-code",
    headers=headers,
    json={
    "controlId": "string",
    "policyText": "string"
},
)
print(response.status_code, response.json())

Go

package main

import (
	"context"
	"fmt"
	"net/http"
	"os"
	"strings"
)

func main() {
	body := strings.NewReader(`{"controlId":"string","policyText":"string"}`)
	req, _ := http.NewRequestWithContext(context.Background(), "POST", "https://evalguard.ai/api/v1/compliance/policy-to-code", body)
	req.Header.Set("Authorization", "Bearer "+os.Getenv("EVALGUARD_API_KEY"))
	req.Header.Set("Content-Type", "application/json")
	resp, err := http.DefaultClient.Do(req)
	if err != nil { panic(err) }
	defer resp.Body.Close()
	fmt.Println(resp.Status)
}

Errors

400401403429500

Other Compliance endpoints