Integrations / Guardrail connector

Argent with Amazon Bedrock Guardrails

Keep the guardrail you built in Amazon Bedrock. Argent calls its ApplyGuardrail API on the prompts and replies that cross the gateway, from any client and any model, and enforces the verdict under one Argent policy.

AWS logo
01 / INTEGRATIONS / GUARDRAIL CONNECTOR

What Argent does with Bedrock Guardrails

Your guardrail, applied to all AI traffic, not only to Bedrock models.

AWS's ApplyGuardrail API checks any text against a guardrail you have already configured, without calling a foundation model (AWS, Use the ApplyGuardrail API). Argent uses that API, so the same guardrail can judge traffic to every provider your people and agents use.

  • Prompts and replies. Prompts are checked as guardrail input and replies as guardrail output.
  • Bedrock's decision is the block. Whenever your guardrail intervenes, for any filter or topic you set in Bedrock, Argent treats it as a hard block.
  • Scores for the record. Content filter confidence is turned into a score: none 0, low 0.33, medium 0.66, high 1.0, so observe mode and the signed record show how close each call was.
  • Replies too. With the egress lane on, replies are checked as well. A classifier flags, it cannot cut out words, so under the default reply setting a flagged reply goes through unchanged with a note on the signed record; under block, the whole reply is replaced with a safe error.
02 / INTEGRATIONS / GUARDRAIL CONNECTOR

How its filters map

Bedrock's content filters map onto Argent's own categories. The filters are described in the AWS docs.

Bedrock content filterArgent category
Prompt attackprompt_injection and jailbreak
Hatehate
Insultstoxicity
Misconducttoxicity
Sexualsexual
Violenceviolence

A filter with no Argent category is left out of coverage. If two filters feed the same category, the higher score counts.

03 / INTEGRATIONS / GUARDRAIL CONNECTOR

How it connects

Argent calls AWS. Nothing in AWS calls Argent.

APIApplyGuardrail through the AWS SDK for Go, signed with AWS Signature Version 4
Which guardrailThe guardrail id or ARN and its version, such as DRAFT or 1, plus its AWS region
CredentialAn IAM access key and secret key, with an optional session token, stored as one JSON secret in your vault
EndpointThe regional default, or an endpoint override you set
Time limit1.5 seconds per check by default, adjustable up to 30 seconds
TestA harmless ApplyGuardrail call that proves the guardrail is reachable and the credential is accepted
04 / INTEGRATIONS / GUARDRAIL CONNECTOR

What you configure

Connect it once, then point the tenant's classifier policy at it.

  1. Have a guardrail in Bedrock. Note its id or ARN, version and region.
  2. Make a credential. An IAM access key allowed to call ApplyGuardrail on that guardrail.
  3. Store it in your vault as JSON with access_key_id, secret_access_key and, if used, session_token: HashiCorp Vault or OpenBao, AWS Secrets Manager, CyberArk Conjur or Infisical. Argent keeps only the reference, and never puts the key in its config, a log or an error.
  4. Add the connector. On the Integrations page, under Guardrails, choose Amazon Bedrock Guardrails, enter the guardrail, version, region and secret reference, then Connect and Test.
  5. Use it in the policy. In the tenant's classifier policy, choose your guardrail as the scoring backend, pick this connector and enable the categories you want enforced.
  6. Watch first. In observe mode, verdicts are scored and recorded without blocking. Switch to block when the record looks right.
05 / INTEGRATIONS / GUARDRAIL CONNECTOR

When Bedrock cannot answer

A guardrail that cannot answer is never read as a pass.

  • Could not measure is not clean. If the guardrail times out, cannot be reached, rejects Argent's credential or sends back an answer Argent cannot read, the check counts as not measured. What happens next is the policy's on-timeout setting: deny, or allow with a note on the signed record.
  • No silent fallback. A tenant that hands the decision to its own guardrail is resolved to that guardrail only. Argent never quietly scores it with a different engine instead.
  • Every enabled category must be covered. If the policy turns on a category the vendor did not evaluate, that category fails closed. It is never scored as zero.
  • One policy language. Policies name categories from Argent's closed set of eleven: prompt_injection, jailbreak, toxicity, hate, sexual, violence, pii, secrets, off_topic, gibberish and code. A policy write that names anything else is refused.
  • Credentials stay references. A token or key lives in your vault. Argent stores only the reference and resolves it when it connects, and a reference it cannot resolve stops the connection.
  • Connectors are an administrator's job. The Integrations page is gated by console role, like every console route.
  • A rejected key is not a pass. An AWS access-denied, expired-token or bad-signature answer is read as not authorized, never as clean.
06 / INTEGRATIONS / GUARDRAIL CONNECTOR

Where this fits

Pages that go deeper.