Amazon Bedrock adds structured outputs for all Claude models: JSON Schema output and strict tool use
Constrained decoding enforces the schema during generation, so calling Claude on Bedrock no longer needs custom parsing and retries.
// Key points
- Structured outputs work for all Anthropic Claude models on both the bedrock-runtime and bedrock-mantle endpoints, where the model is available.
- Two mechanisms: JSON Schema output format controls the response structure, and strict tool use validates tool parameters against schemas.
- It works with batch inference, with cross-Region inference on bedrock-runtime, and can stream structured responses as typed events.
- Responses contain only the fields the schema defines, which cuts output tokens and can lower cost for high-volume workloads.
Builder's takeTeams on Bedrock can finally delete the retry-on-parse-failure glue. File metadata extraction in AI Cloud Drive is exactly this case; I'll tighten the schema to required fields only, then compare output tokens and failure rate. Constrained decoding guarantees format, not correctness, so keep sampling the results.
// Background · from #Anthropic
Full timeline →- Oct 21 Inference hooks leave beta for Claude Enterprise: governed prompts wait for the organization's own AI security server
- Oct 19 Anthropic publishes its own employment data: by August, interactive AI agent hours outnumbered employees six to one, and junior technical hiring shrank as a share
- Oct 19 Anthropic sets up a Public Benefit Fund with 5% of its shares, subject to stockholder approval, plus 2% more for every 50% rise in value above a baseline