https://modelsatwork.news/article/moengage-400-internal-apis-agent-tools-agentcore-gateway-cedar-vendor-published Models at Worken 2026-11-01T20:58:00.000Z MoEngage: 400 private APIs become agent tools via AgentCore Gateway Amazon Bedrock AgentCore, Access control, Tool use, AWS, Vendor-published https://modelsatwork.news/article/mistral-large-4-open-weights-out-1t-moe-1m-context-license-limits-hosting-hardware Models at Worken 2026-11-01T19:58:00.000Z Mistral Large 4 weights are out: 1T parameters, 1M context Model release, Mistral, Open-weight models, Self-hosting, Security https://modelsatwork.news/article/aws-agentcore-session-endpoints-live-preview-coding-agent-allowed-ports-sigv4-vendor-published Models at Worken 2026-11-01T19:10:00.000Z AWS: AgentCore session endpoints preview a coding agent's app live Coding agents, Amazon Bedrock AgentCore, Access control, AWS, Vendor-published https://modelsatwork.news/article/aws-epsilon-nova-act-plain-english-ui-tests-4-6x-faster-authoring-vendor-published Models at Worken 2026-11-01T18:00:00.000Z AWS: Epsilon runs plain-English UI tests on Nova Act Browser agents, Agent evaluation, Amazon Bedrock AgentCore, AWS, Vendor-published https://modelsatwork.news/article/aws-kiro-php-to-java-migration-engine-parity-harness-before-code-vendor-published Models at Worken 2026-11-01T17:30:00.000Z AWS: a Kiro PHP-to-Java migration that builds the test first Coding agents, Human in the loop, AWS, Vendor-published, Agent evaluation https://modelsatwork.news/article/google-gemini-4-carbon-cyber-defenders-first-4-20-price-after-promo Models at Worken 2026-11-01T15:58:00.000Z Google previews Gemini 4 Carbon to cyber defenders first, $2/$10 per 1M tokens Model release, Google, Gemini 4 Carbon, Pricing, Security https://modelsatwork.news/article/aws-chatgpt-desktop-codex-bedrock-govcloud-us-requirements-toml-single-endpoint-vendor-published Models at Worken 2026-11-01T15:55:00.000Z AWS: ChatGPT desktop and Codex can run on Bedrock in GovCloud (US) Amazon Bedrock, AWS, OpenAI, Coding agents, Compliance, Vendor-published https://modelsatwork.news/article/nvidia-shopify-sidekick-graphql-subagent-post-trained-nemotron-3-5-lightning-90-percent-lower-serving-cost Models at Worken 2026-11-01T13:57:00.000Z NVIDIA: Shopify's tuned Nemotron beats a frontier model on Sidekick task, 90% cheaper Open-weight models, Self-hosting, Token cost, NVIDIA, Vendor-published https://modelsatwork.news/article/anthropic-claude-written-training-data-evades-monitor-teaches-misalignment Models at Worken 2026-11-01T13:10:00.000Z Anthropic: Claude wrote harmless-looking data that taught models to misbehave Agent safety, Anthropic, Fine-tuning, Red teaming, Monitoring https://modelsatwork.news/article/memdoor-five-qwen-agents-livecodebench-hard-parity-check Models at Worken 2026-11-01T10:58:00.000Z Memdoor: five Qwen3.8-27B agents match Fable 5 on 10 coding problems Multi-agent, Open-weight models, Open source, Show HN, Benchmarks https://modelsatwork.news/article/aws-bedrock-cost-playbook-five-stages-attribution-budgets-shared-gateway-role-vendor-published Models at Worken 2026-11-01T09:56:00.000Z AWS's Bedrock cost playbook: attribute first, then enforce budgets Cost governance, Amazon Bedrock, Cost allocation, Prompt caching, Vendor-published https://modelsatwork.news/article/worldwide-express-freight-billing-exceptions-three-bedrock-agents-75-percent-backlog-cut-vendor-published Models at Worken 2026-11-01T04:30:00.000Z Worldwide Express: three Bedrock agents cut billing backlog 75% Multi-agent, Human in the loop, Amazon Bedrock, AWS, Vendor-published https://modelsatwork.news/article/autobench-router-benchmark-no-llm-router-beats-always-calling-one-mid-priced-model Models at Worken 2026-11-01T00:00:00.000Z AutoBench: no LLM router beat one mid-priced model on cost and quality Routing, Evals, Model selection, Cost, Benchmarks https://modelsatwork.news/article/anthropic-text-watermark-four-more-claude-models-opus-4-6-sonnet-4-6-sampling-loophole-eu-ai-act Models at Worken 2026-10-31T23:00:00.000Z Anthropic widens Claude text watermark; two older models can dodge it Anthropic, Claude, Compliance, Regulation, Governance https://modelsatwork.news/article/aws-bedrock-prompt-caching-agents-gpt-6-astra-62-percent-lower-input-cost-stable-tools-prefix-vendor-published Models at Worken 2026-10-31T22:40:00.000Z AWS: prompt caching cut agent input cost 62% on Bedrock, in one test AWS, Amazon Bedrock, Agent cost, Token cost, Vendor-published https://modelsatwork.news/briefing/2026-11-01 Models at Worken 2026-11-01T13:20:00.000Z The briefing, 2026-11-01: AWS says Worldwide Express's three Bedrock agents cut its billing backlog 75% in six months https://modelsatwork.news/briefing/2026-10-31 Models at Worken 2026-11-01T00:30:00.000Z The briefing, 2026-10-31: AWS says prompt caching cut agent input cost about 62% on Bedrock, if tool order stays fixed https://modelsatwork.news/briefing/2026-11-01 Models at Worken 2026-11-01T11:30:00.000Z The briefing, 2026-11-01: Worldwide Express says three Bedrock agents cut its freight billing backlog 75%