Agents
Articles under the Agents category.
Figma’s MCP server plugs design systems into AI agents
Figma’s remote MCP server lets agents and IDEs query components, tokens, styles, and usage rules directly from your design system. Expect cleaner handoffs, faster reviews, and automation that follows your standards.
ChatGPT Agent is the first mainstream computer-using AI
On July 17, 2025, OpenAI turned chat into computer use. ChatGPT Agent researches, clicks, and acts inside a virtual computer with narration and approvals. Explore strengths, limits, and how to put it to work.
GitHub Copilot’s Coding Agent Hits GA: A Teammate, Not a Tool
GitHub Copilot’s coding agent is now GA and ready to own end to end tasks. It plans changes, runs tests in isolated runners, opens draft PRs, and works within branch protections and review gates.
Agentforce 3 shifts the AI race to control, scale, and trust
Agentforce 3 reframes the AI platform race around control, scalability, and trust. With Command Center observability, native MCP interoperability, and automatic model failover, Salesforce pushes agents from demos to dependable digital labor.
Amazon’s agentic Seller Assistant transforms SMB e-commerce
Amazon is evolving Seller Assistant into a permissioned agent that plans, executes, and reports across inventory, account health, compliance, and ads. See what changed on September 17, 2025 and why it matters for SMBs.
Inside Notion 3.0 Agents: A Playbook for Enterprise AI
Notion 3.0 turns AI into real agents that can read, plan, and write inside your workspace. This playbook shows how to deploy them safely, measure outcomes, and pair Notion with AgentsDB for memory, policy, and observability.
Claude joins Microsoft 365 Copilot: building multi-model agents
Microsoft is adding Claude to Microsoft 365 Copilot and Copilot Studio. Learn how multi-model routing changes agent design, governance, cost, and safety, with a practical blueprint you can implement this month.
Google’s AP2 arrives to unlock real commerce for AI agents
Google’s Agent Payments Protocol, AP2, arrived on September 16, 2025 to give AI agents a trustworthy way to pay. Here is how mandates, A2A integration, and verifiable receipts turn agent promises into real checkout.
Claude for Chrome makes the browser the agent runtime
Anthropic’s new Chrome extension lets Claude click, type, navigate, and fill forms directly in your browser, while new defenses cut measured prompt injection success from 23.6% to 11.2%. Here is what that unlocks for real workflows and how teams should prepare with governance, telemetry, and guardrails.
OpenAI and Databricks bring GPT‑5 natively to Agent Bricks
OpenAI and Databricks struck a $100 million alliance to make GPT-5 and other OpenAI models native on Agent Bricks, signaling a pivotal shift in the enterprise agent platform race. Here is what it means and what CIOs can pilot in the next two quarters.