amazon-bedrock

Amazon Web Services launched Policy Engine and Lambda interceptors for Bedrock AgentCore gateway, enabling enterprises to control which tools AI agents can access and validate requests dynamically. The Policy Engine uses Cedar declarative policy language for deterministic access decisions, while Lambda interceptors run custom code before or after each tool call for validation, token exchange, and response filtering.

Amazon Web Services introduced dataset management in Bedrock AgentCore, enabling developers to build versioned test suites with immutable baselines for agent evaluation. The feature supports predefined scenarios with ground truth assertions and user simulation scenarios where LLM-backed actors conduct multi-turn conversations.

AWS has deployed Amazon Bedrock AgentCore to orchestrate more than 20 specialized AI agents across its global sales organization through a unified interface called Field Advisor. The system has processed over 120,000 prompts since launch, delivering a 41% latency reduction compared to previous infrastructure and saving large-scale sales reps up to 2 hours per week on CRM tasks.

Amazon Bedrock now supports programmatic tool calling (PTC), a technique that allows LLMs to generate Python code for multi-step tool orchestration rather than making sequential API calls. AWS offers three implementation paths: self-hosted Docker sandboxes on ECS, managed execution via Amazon Bedrock AgentCore Code Interpreter, and Anthropic SDK-compatible proxy integration.

AWS published a technical guide for prompting Amazon Nova 2 Lite for content moderation without fine-tuning. The approach uses the MLCommons AILuminate Assessment Standard's 12-category hazard taxonomy and includes XML/JSON structured prompts and few-shot learning examples for high-throughput moderation pipelines.

Popsa, a photo book service operating in 50+ countries, generated over 5.5 million AI-powered titles in 2025 using Amazon Nova models. The company achieved 73% positive user feedback with Nova Pro while reducing costs and latency compared to Claude 3 Haiku.

Amazon Bedrock has formalized its model lifecycle management with three states—Active, Legacy, and End-of-Life—guaranteeing at least 12 months of availability after launch and 6 months in Legacy status before deprecation. For models with EOL dates after February 1, 2026, a new extended access phase provides an additional 3+ months of access during Legacy state, giving customers more time to migrate applications.

Amazon Bedrock now supports Reinforcement Fine-Tuning (RFT) for customizing Amazon Nova and open source models using reward signals instead of labeled datasets. AWS reports up to 66% accuracy improvements over base models with reduced customization complexity. The approach works best for tasks with verifiable correctness (code, math) or subjective evaluation (moderation, summarization).

Amazon has published a technical guide for building real-time conversational podcasts using Amazon Nova 2 Sonic, its speech understanding and generation model. The solution demonstrates streaming audio generation, multi-turn dialogue between AI hosts, and stage-aware content filtering through a web interface.

Amazon has released a serverless architecture solution using Bedrock Guardrails that dynamically selects safety policies based on user age, role, and industry. The solution enforces five specialized guardrails—including COPPA-compliant child protection and healthcare-specific policies—at inference time to prevent prompt injection attacks and ensure context-appropriate responses.

Amazon Bedrock has introduced three distinct video analysis workflows that leverage multimodal foundation models to extract insights from video content at scale. The approaches—frame-based, shot-based, and multimodal embedding—are designed for different use cases and cost-performance trade-offs, with open-source reference implementations available on GitHub.

Amazon Bedrock now enables reinforcement fine-tuning (RFT) across multiple model families including Amazon Nova, open-weight models like OpenAI's GPT-OSS 20B, and Qwen 3 32B. The service automates the end-to-end customization workflow using GRPO optimization, allowing models to learn from feedback on multiple responses rather than static training datasets, with support for OpenAI-compatible APIs.

Amazon Web Services has integrated Claude's tool use (function calling) capability into Bedrock, enabling serverless document processing for custom entity recognition. The solution uses Claude 3.5 Sonnet to extract structured data like names, dates, and addresses from driver's licenses and other documents without traditional model training.

NVIDIA Nemotron 3 Super, a hybrid Mixture of Experts model with 120B parameters and 12B active parameters, is now available as a fully managed model on Amazon Bedrock. The model supports up to 256K token context length and claims 5x higher throughput efficiency over the previous Nemotron Super and 2x higher accuracy on reasoning tasks.

Amazon Nova 2 Lite expands context window to 1 million tokens, introduces extended thinking with developer controls, and adds native tool use and web grounding. AWS claims Nova 2 Lite surpasses Nova 1 Pro on multi-step reasoning while costing 7x less and running up to 5x faster.

Amazon Bedrock now offers NVIDIA's Nemotron 3 Nano as a fully managed serverless model, expanding its Nemotron portfolio alongside previously available Nemotron 2 Nano 9B and Nemotron 2 Nano VL 12B variants. The addition enables developers to deploy NVIDIA's smallest inference-optimized model without managing infrastructure.

Amazon Bedrock now enables access to Anthropic Claude models in India with global cross-region inference support. The service allows developers to build generative AI applications with Claude variants across AWS regions.