AI Agent News from Official Blogs and Changelogs · page 2
-
How LoanPro built an agentic AI loan servicing assistant with Amazon Bedrock AgentCore
LoanPro built a multi-agent AI assistant on Amazon Bedrock to give loan servicing agents borrower context and recommendations, reducing call times by up to 15 percent.
-
Responsible AI for agentic AI: A phased roadmap for platform and application teams
AWS published a three-phase roadmap for embedding responsible AI governance in agentic AI platforms and applications.
-
GPT-6.2 Astra and Sol now available on AI Gateway
OpenAI's GPT-6.2 Astra and Sol models are now available via Vercel's AI Gateway, with improved document generation and computer use capabilities.
-
Build memory-aware AI agents with Agentic Retrieve on Amazon Bedrock Managed Knowledge Base
Amazon Bedrock Managed Knowledge Base adds memory capabilities to store conversations and extract facts, enabling multi-user agents with private per-user memory and document access.
-
Taxonomy of multi-agent design patterns, anti-patterns, and lessons from manufacturing
AWS published a taxonomy of multi-agent design patterns and anti-patterns with a framework for deciding when multiple agents are needed and how to build cost-efficient systems.
-
GitHub Copilot weekly releases — November 9
GitHub Copilot adds support for GitHub Enterprise Server repositories in the Copilot app and improves agent session visibility in VS Code.
-
GitHub Copilot models deprecated on November 16, 2026
GitHub deprecated certain models across Copilot Chat, inline edits, ask and agent modes, and code completions.
-
Control where GitHub Copilot customizations come from
Enterprise administrators can now require GitHub Copilot customizations to come from plugins or managed settings instead of standalone configurations.
-
VS Code retires the Local harness in February 2027
VS Code 1.146 deprecates the Local harness, the older software coordinating model, context, and tools for GitHub Copilot agent sessions in the editor, with retirement planned for February 2027.
-
How MoEngage built agentic customer engagement on Amazon Bedrock AgentCore
MoEngage built Merlin AI, a set of agents on Amazon Bedrock AgentCore that enable marketing teams to manage campaigns through conversation, using MCP tools to access platform APIs with data isolation.
-
Introducing explicit prompt caching with open-weight models on Amazon Bedrock
Amazon Bedrock now supports prompt caching for open-weight models, reducing input costs and latency by reusing long context across requests. The post demonstrates caching with the Chat Completions API and an OpenCode coding agent.
-
AI made integrations the vendor’s problem
Report discusses how MCP adoption across vendors has shifted integration responsibilities from users to vendors in AI agent development tools.
-
AI Gateway now supports Private Inference
AI Gateway now supports Private Inference, allowing fine-tuned and self-hosted models to run through unified authentication, SDKs, and observability.
-
Advancing computer-use agents for healthcare teams
OpenAI discusses advances in computer-use agents for healthcare teams.
-
Agents are users, so your software needs evals
Vercel argues that agents are now software users, and developers building agents or agent-compatible software should use evals to measure agent performance across discovery, selection, and access.
-
Qwen4-Max now available on AI Gateway
Alibaba's Qwen4-Max reasoning model is now available on Vercel's AI Gateway, featuring native vision, 1M-token context, and support for professional tools including Blender and game engines.
-
Route coding agent requests to the right model on Amazon Bedrock with NVIDIA NeMo Switchyard
AWS CDK deployment guide for LiteLLM with NVIDIA NeMo Switchyard routing plugin on Amazon Bedrock, measuring cost per solved task for coding agents.
-
Upcoming deprecation of selected GitHub Copilot models in December
GitHub will deprecate selected models across GitHub Copilot experiences including chat, edits, and agent modes on December 14, 2026.
-
Token Pass now includes $150 in tokens for $30/month
Vercel Token Pass now includes $150 of tokens per month (up from $80) for the same $30 per team per month. The credit applies to featured open-weight models served through AI Gateway , including…
-
GitHub Enterprise Server support in the GitHub Copilot app
GitHub Copilot app now supports GitHub Enterprise Server accounts, allowing users to work with remote repositories, issues, and pull requests.
-
Gemini 4 Hydrogen in GitHub Copilot
Google's Gemini 4 Hydrogen Flash model is now generally available in GitHub Copilot for coding, tool use, and multistep workflows.
-
Introducing ChatGPT Wallet
ChatGPT Wallet enables secure purchases for agents in ChatGPT Work, Codex, and dots with user approval and card protections.
-
New in n8n: Public API rate limits that keep every team on your instance running
n8n added public API rate limits per API key with 429 response headers and idempotency key support for safe retries.
-
Parallel Decisions now available on AI Gateway for free
Parallel Decisions Fast from Parallel is now available on AI Gateway and is free through November 23, 2026. It searches the live web to answer typed questions about companies, products, policies…
-
Build once, run on any agent: A practical guide to agent skills
GitHub published guidance on agent skills as reusable, reviewable code that can run across different agent platforms while keeping tools and permissions host-specific.
-
How Natera designed an agentic AI system for lab ops with Amazon Bedrock AgentCore
Natera built SWARM, an agentic AI system on Amazon Bedrock AgentCore for lab operations, achieving 130x faster first response and 96.2% automated coverage on support tickets.
-
Kimi K3.1 Pro is now available in Token Pass
Kimi K3.1 Pro, a model for coding and agentic workflows with vision and tool use, is now available in Vercel's Token Pass subscription at $30 per month for $80 in credits.
-
Optimizing cost per task and proving agent ROI on Amazon Bedrock
AWS post explains how to calculate true cost per task for agents on Bedrock and reduce it through caching, routing, and output constraints.
-
Building a self-service LLM gateway with Amazon Bedrock and LiteLLM
Guide to building an OpenAI-compatible LLM gateway using LiteLLM on AWS Fargate with Amazon Bedrock foundation models, including cost controls and quota management.
-
Run agents securely and efficiently with the next generation AgentCore runtime
Amazon Bedrock's next-generation AgentCore runtime now offers hardware-isolated sessions, faster starts, more compute capacity, and usage-based billing for running multi-step AI agent workloads.
-
Migrate to Amazon Bedrock Managed Knowledge Base with your coding agent
AWS published a migration guide for moving customer-managed Amazon Bedrock knowledge bases to Managed Knowledge Base, with a coding agent automating discovery, creation, and validation steps.
-
Build composable, interoperable multi-agent systems with A2A on AWS
AWS demonstrates a multi-agent system using the Agent-to-Agent (A2A) protocol, with a LangChain orchestrator on ECS communicating with a Strands agent on Bedrock AgentCore via OAuth-authenticated calls.
-
From prototype to production: Engineering agents with Agent DLC
AWS introduces Agent DLC, a framework addressing measurement and evaluation challenges in moving agents from prototype to production, using a standardized lifecycle and explicit metrics for judging changes.
-
Holiday Extras is rethinking what it can build with Codex
Holiday Extras uses Codex to improve apps and booking conversion.
-
WTF are evals? How to test agents and the software they use
Article explains evaluation frameworks for testing AI agents and the software they interact with, covering discovery, selection and access patterns.
-
Build autonomous AI agents with Amazon Bedrock and Spring AI
AWS blog post on building autonomous AI agents with Amazon Bedrock and Spring AI, covering tool calling, memory, resilience, and multi-agent orchestration for Java developers.
-
Gemini 4 Hydrogen now available on AI Gateway
Google Gemini 4 Hydrogen model is now available on Vercel's AI Gateway, improving agentic coding, tool use and handling longer tasks in fewer steps.
-
Inkling 2 Small now available on AI Gateway
Inkling 2 Small from Thinking Machines is now available on AI Gateway. The multimodal reasoning model supports coding agents, visual understanding, and professional knowledge work, with text and…
-
OpenAI Codex on Amazon Bedrock
AWS published guidance on deploying OpenAI Codex through Amazon Bedrock for enterprises, addressing access, governance, and cost considerations.
-
Automating AWS Agent Registry updates with push-based architecture
AWS describes an event-driven pipeline using CloudTrail, EventBridge, and Lambda to automatically update the AWS Agent Registry when MCP servers change, without storing secrets.