The new ChatGPT Agent Mode combines the Operator's ability to browse and interact with websites with Deep Research's ability to analyze and synthesize information from multiple sources. I tested ChatGPT's Agent Mode and was quite disappointed. Honestly, I find it surprising that OpenAI made this feature available to the public, considering that they have led the way with their chatbot so far. In my view, ChatGPT's Agent Mode is a flawed concept because it forces an AI agent to use a web browser, a relatively primitive tool designed for inferior human intelligence.

Source

I tested three MCP servers in Anthropic Claude Sonnet 4: Claude Gmail Search, Zapier Gmail MCP server, and GongRzhe’s Gmail MCP Server. I also submitted the same search prompt to Gemini in Gmail. The results varied greatly. Only two AI tools passed my test, one failed, and the most promising MCP server turned out to be useless.

Source

Anthropic has introduced two new concepts for connecting AI models to resources through MCP: desktop extensions and connectors. Extensions are available only on Claude Desktop (Windows and Mac), while connectors are supported on both the desktop and the Claude.ai web app. All desktop extensions are local MCP servers, but not all local MCP servers qualify as extensions. Conversely, all remote MCP servers are considered connectors; however, not all connectors are remote MCP servers. Although some theoretical documentation about these new concepts exists, I mainly categorized them based on how Claude Desktop organizes the different types of MCP servers.

Source

VS Code version 1.102 introduced several useful new features in GitHub Copilot. Command allow/deny lists let you specify which commands the Copilot agent can execute without asking for permission. The resubmit feature enables you to edit a previous request and resubmit the prompt. Additionally, the new VS Code version includes various updates for managing MCP servers, including a curated catalog of MCP servers.

Source

A new study by METR got a lot of attention online. It claims that developers often overestimate the productivity boost from AI tools. In a coding test, the researchers found that AI caused a 19% "slowdown" for developers. In my opinion, it's not AI coding that's overhyped, but rather the study's findings.

Source

The number of GitHub Copilot concepts continues to grow, and their similar names can easily confuse. This post offers an overview of all the concepts, along with a link to find more information. The main confusion stems from the Copilot tools on GitHub.com and GitHub Copilot in VS Code. Although there is some overlap, keeping these two areas separate is essential.

Source

Microsoft Azure MCP Server allows AI agents like VS Code GitHub Copilot in Agent Mode to communicate with your Azure resources through natural language prompts. Azure MCP Server supports services such as Storage, Cosmos DB, Key Vault, and Logs.

Source

Google's new Gemini CLI allows up to 60 model requests per minute and 1,000 daily requests. Professional developers might hit these limits quickly, but many IT admins will find the free plan sufficient. Compared to Anthropic Claude Code and OpenAI Codex CLI, I find Google's open-source AI-powered terminal more useful for the AI-augmented admin.

Source

The brand-new Warp 2.0 no longer wants to be just an AI-powered terminal. The Warp team appears to be taking inspiration from Anthropic’s Claude Code and OpenAI’s Codex CLI. Both AI-driven coding tools target devs who prefer to code in a terminal instead of working in an Integrated Development Environment (IDE). Zach Lloyd, Warp's CEO, is eager to join the AI agent race, believing that features like the Agent Management Panel, diffs, and a built-in editor can transform a CLI tool into a vibe coding platform or what he calls an Agentic Development Environment (ADE).

Source

Recently, leading AI companies announced support for remote MCP, allowing an MCP client to connect to a remote MCP server via Streamable HTTP, which still supports Server-Sent Events (SSE). The Streamable Data Input/Output (SDIO) protocol remains essential for local integrations and remote services, which are accessible only through conventional APIs. In my opinion, the excitement surrounding new model releases has lost its significance. AI model developers seem to primarily focus on optimizing their models for AI benchmarks. However, the genuine innovations occur in the technologies surrounding AI models—most notably in AI agents and the supporting infrastructure in which remote MCP servers will play an important role.

Source

The VS Code May 2025 update (version 1.101), released a few days ago, introduces a range of new features primarily focused on GitHub Copilot. My favorite addition is the custom chat mode, which lets you create a personalized mode alongside the built-in options: Ask, Edit, and Agent. In this post, I'll also explore the new chat tool sets and the undoing edits feature. While the Simple Browser feature was included in the previous release, it deserves discussion. Furthermore, I will briefly summarize the MCP enhancements.

Source

The MCP catalog in Docker Desktop has been available for a couple of weeks now. However, MCP support only works properly in the just-released Docker Desktop 4.42. The Docker Desktop MCP server catalog significantly simplifies installing MCP servers for any MCP client. I tested it with Gordon (Docker Desktop chatbot), Anthropic Claude Desktop, and VS Code GitHub Copilot on macOS, but the process should be identical on Windows.

Source

Warp, the top terminal app with AI support, has introduced new features in its GA release, including MCP support and Refine for AI responses. The Preview release now allows image uploads and the saving of reusable AI prompts. I also found a few new features that weren’t mentioned in the Launch Log 3 post.

Source

Creating an AI agent in Amazon Bedrock involves a relatively complex process. The example in this post has been simplified for clarity. Once you have your first Agent setup working, exploring all the features that AI agents in AWS offer becomes much easier. The Bedrock Agent I discuss uses a Lambda function, which can be triggered by the AI model when the user prompt indicates its usefulness. An AWS Lambda function is a serverless compute service that runs your code in response to events without provisioning or managing servers. These functions may involve complex logic, enabling the AI agent to perform sophisticated tasks autonomously.

Source

OpenAI recently introduced the Agents SDK, a Python-based framework that enables developers and DevOps engineers to build AI agents. The example in this post showcases a script that uses the OpenAI Agents SDK to connect an AI agent to Anthropic’s filesystem MCP server. This integration enables the AI agent to analyze the contents of a monitoring log.

Source

The leader in coding models has rolled out Claude Code to the public. Anthropic's terminal-based AI coding assistant automates editing, testing, and managing git workflows using natural language commands. Although you cannot install Claude Code as a VS Code extension via the marketplace, its integration into the open-source IDE is straightforward, and the user experience closely resembles GitHub Copilot, Cline, or Roo Code. My review of the preview version was somewhat critical because I dislike coding in the terminal. However, Claude Code now integrates well with VS Code and JetBrains, so I changed my original verdict.

Source

OpenAI's Sam Altman envisions a future where countless AI agents operate autonomously across the internet, managing tasks on behalf of users and interacting with each other to perform complex operations without human intervention. Realizing this vision necessitates a new internet protocol that supports the sophisticated communication required for AI systems. Google’s new Agent2Agent (A2A) Protocol addresses this need by providing an open standard that enables autonomous AI agents to communicate across diverse systems. This post delves into the necessity of A2A, its current supporters, distinctions from Anthropic’s Model Context Protocol (MCP), the types of data it handles, and offers a straightforward example to illustrate its application.

Source

In a remarkably short period, MCP has established itself as the standard for secure and efficient connections between AI models and external data sources and tools. Microsoft has integrated MCP into VS Code, Windows will get it, OpenAI plans to implement it for ChatGPT, and the top terminal application, Warp, has introduced MCP support in its Preview version. I installed the official Perplexity MCP server for my test and incorporated it into Warp.

Source

The relatively new VS Code technical terms chat participants, chat variables, and slash commands can be accessed with the prefixes @, #, and / in GitHub Copilot. This post explains the differences and gives usage examples.

Source