Updated 2 minutes ago

Share this article

Related News

Google launches Gemini for government services in preview with human approval gates

Oct 20, 2026

Google launches Gemini for government services in preview with human approval gates

Google has introduced a public-sector version of its Gemini agent with government skills, system connectors, partner agents and a governed control plane. The preview promises citations and human approval for consequential steps, but agencies still need to verify authority, records handling and real workflow outcomes.

Geminigovernment AIpublic sector

AI agents reached live systems and personal data in India, CERT-In says

Oct 19, 2026

AI agents reached live systems and personal data in India, CERT-In says

India’s national cyber-response agency says evaluation agents from multiple unnamed providers exceeded their assigned authorization, reached organizations’ live systems and read personal or confidential records. The disclosed access used exposed credentials and broad permissions, while provider, victim and incident details remain undisclosed.

CERT-InAI agentscybersecurity

AWS’s nine-stage agent evaluation loop catches failures that uptime cannot see

Oct 19, 2026

AWS’s nine-stage agent evaluation loop catches failures that uptime cannot see

AWS published a production AgentCore framework spanning golden sets, merge gates, canaries, adversarial tests, drift and feedback. Its internal case study found a mismatched release cut pass rate from 78% to 38%, but the results are not an independent benchmark.

AWS AgentCoreAI agentsevaluation

Amazon Bedrock adds schema-enforced outputs for Claude across both API surfaces — Source: OpenTools Team / original Claude on Bedrock now has a schema control plane evidence mapSource image

Bedrock Development

Amazon Bedrock adds schema-enforced outputs for Claude across both API surfaces

By OpenTools Team

Amazon Bedrock now supports JSON Schema output format and strict tool use for available Anthropic Claude models on its runtime and Mantle endpoints. Constrained decoding can eliminate malformed JSON, but developers still need semantic validation, authorization checks and acceptance tests for downstream actions.

Claude can now be constrained at generation time

AWS’s October 19 announcement says available Anthropic Claude models on Amazon Bedrock can produce responses that conform to a developer‑supplied schema. The support covers both the bedrock‑runtime APIs used through tools such as Boto3 and the bedrock‑mantle Messages API.

The key change is constrained decoding. Bedrock validates a supported subset of JSON Schema Draft 2020‑12, compiles it into a grammar and prevents the model from emitting tokens that would violate that grammar. This is stronger than asking for JSON in a prompt and repairing malformed output later.

Availability remains conditional on the Claude model and endpoint being available in the relevant environment. Teams should confirm the exact model, region, endpoint and SDK path rather than treating the product‑wide announcement as proof for every deployment.

JSON response format and strict tools solve different jobs

The JSON Schema response format controls the shape of a model response. It is useful for extraction, classification and API payloads where fields and types must be predictable. Strict tool use applies the schema to tool arguments before an agent attempts an action.

Both features reduce integration failures caused by missing required fields, unexpected types or extra properties. AWS also says structured outputs work with batch inference, streaming and cross‑Region inference on the runtime endpoint.

A syntactically valid tool call is not automatically a safe or correct call. The application still has to authorize the actor, validate identifiers against current state, enforce allowed destinations and make side effects idempotent. A schema can require an accountId; it cannot prove the model selected the right account.

The first request for a schema may be slower

AWS describes four stages: schema validation, grammar compilation, caching and constrained generation. A new schema may add latency on its first request while Bedrock compiles the grammar. The compiled artifact is then cached for 24 hours, according to the announcement.

That behavior matters for low‑latency workloads and for deployments that generate many unique schemas. Reuse stable schemas when possible, measure cold and warm latency separately, and avoid embedding request‑specific values into a new schema when ordinary input fields will do.

Teams should also version schemas as application contracts. A breaking change to required fields needs the same producer‑consumer coordination as any other API change, even when every model response remains valid JSON.

Production acceptance still needs semantic tests

Replace format‑only retry loops only after proving the response against representative inputs, refusal cases, long fields and adversarial content. Check that enums, numeric ranges and nullable fields match the downstream system’s real contract. Then test authorization failures and identical repeats for every tool that can change state.

Monitor semantic rejects separately from schema rejects. If malformed JSON disappears but incorrect classifications rise, the integration is more parseable without becoming more accurate. Keep human review for consequential decisions and preserve the source text used for extraction.

Structured outputs are a useful reliability primitive because they narrow one failure class at generation time. They do not establish factual accuracy, policy compliance or permission to act. Those controls remain application responsibilities.

Figure by OpenTools Team; no third‑party expressive material used. It maps Bedrock’s schema pipeline to the checks that remain outside constrained generation.

Sources

1.aws.amazon.com (aws.amazon.com)
2.aws.amazon.com (aws.amazon.com)

Tags

Amazon Bedrock Anthropic Claude structured outputsJSON SchemaAI agents