---
title: "recommendAgentPolicy"
description: "Recommend a least-privilege policy from recorded traffic"
canonical: "https://pgbeam.com/docs/ts-sdk/policies/recommendAgentPolicy"
last-updated: "2026-10-24T21:15:09.000Z"
---

# recommendAgentPolicy

> Recommend a least-privilege policy from recorded traffic

URL: https://pgbeam.com/docs/ts-sdk/policies/recommendAgentPolicy

{/* Auto-generated from OpenAPI. Do not edit. Run `pnpm generate:sdk-docs` to regenerate. */}

Derives the tightest policy that would still pass every statement this agent credential has legitimately run, using its recorded audit history over a lookback window (default 30 days). The candidate's table allowlist is the union of relations actually referenced, its statement-kind allow set is the observed set, it downgrades to read-only when no writes were seen, and its max_rows ceiling comes from an observed high-percentile row count. The candidate is proven safe by replaying it through the data plane's own policy engine against the same history: a good recommendation has replay.summary.newly_blocked == 0. This endpoint is advisory only. It reads the audit log, never connects to the upstream database, and never creates, updates, or mutates any policy or credential; the operator loads the candidate into the editor and saves it themselves.

## Usage

```typescript
const result = await api.policies.recommendAgentPolicy({
    pathParams: { project_id: "prj_xxx", agent_id: "agt_xxx" },
    body: {
      ,
    },
  });
```

## Parameters

| Parameter             | Type     | Required | Description                                                                                                                    |
| --------------------- | -------- | -------- | ------------------------------------------------------------------------------------------------------------------------------ |
| pathParams.project_id | `string` | Yes      | Unique project identifier (prefixed, e.g. prj_xxx).                                                                            |
| pathParams.agent_id   | `string` | Yes      | Unique agent credential identifier (prefixed, e.g. agt_xxx).                                                                   |
| body.lookback_days    | `number` | No       | How many days of recorded audit history to analyze.                                                                            |
| body.limit            | `number` | No       | Maximum number of distinct query shapes to analyze and replay, newest first. Traffic is deduplicated by normalized query hash. |

## Response

`Promise<PolicyRecommendation>`: the recommended candidate policy and its replay proof.

## Example

```typescript
import { PgBeamClient } from "pgbeam";

const client = new PgBeamClient({
  token: "pbu_...",
  baseUrl: "https://api.pgbeam.com",
});

const result = await client.api.policies.recommendAgentPolicy({
  pathParams: { project_id: "prj_xxx", agent_id: "agt_xxx" },
  body: {
      ,
    },
});
```

## Errors

| Status | Description                                                                                                                                                                                                                                                                                           |
| ------ | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| 400    | The request was rejected. `code` is `INVALID_INPUT`, and `errors` names the offending fields when the failure was a validation one.                                                                                                                                                                   |
| 401    | Missing or invalid authentication. `code` is `UNAUTHORIZED`.                                                                                                                                                                                                                                          |
| 403    | The caller is authenticated but not allowed to perform this operation. `code` is `FORBIDDEN` when the caller's role is insufficient, and `PLAN_LIMIT_REACHED` when the organization's plan is what stands in the way. The two are answered differently, so branch on the code rather than the status. |
| 404    | The resource does not exist, or the caller is not entitled to know that it does. `code` is `NOT_FOUND`.                                                                                                                                                                                               |
| 413    | The request body exceeds the 2 MB limit. `code` is `PAYLOAD_TOO_LARGE`.                                                                                                                                                                                                                               |
| 415    | The request body is not JSON, or carries a body without declaring a Content-Type. `code` is `UNSUPPORTED_MEDIA_TYPE`.                                                                                                                                                                                 |
| 429    | Rate limited. `code` is `RATE_LIMITED`.                                                                                                                                                                                                                                                               |
| 500    | The request failed for a reason on our side. `code` is `INTERNAL_ERROR`. Quote `request_id` when reporting it.                                                                                                                                                                                        |