This week brought major steps forward for AI agents working together. The Linux Foundation launched the Agent2Agent (A2A) protocol on June 23, creating a common language for different AI systems to communicate securely. This open standard—supported by Google and over 100 companies—lets agents from various platforms team up safely. Meanwhile, a KPMG survey showed rapid growth in agent adoption, with 33% of businesses now using AI agents. The report highlighted that advanced multi-agent teams are becoming key for handling complex tasks. Looking ahead, the upcoming Agentic AI Summit will tackle collaboration challenges like managing agent identities and permissions.

These developments show agent collaboration moving from experiments to real-world use. Businesses now see teams of AI agents as essential tools for staying competitive. The new A2A protocol solves technical hurdles while the KPMG data proves companies are investing heavily in this teamwork approach. As more agents learn to work together, they'll handle bigger challenges across industries worldwide.

Extended Coverage
Put an agent to work

Stop reading agent demos. Give one a job you repeat every week.

Describe the work, test the first result, and keep the agent available without running your own server.

Runs without your laptopBrowser + messaging appsBackups and clonesMemory survives restarts

Plans start at $29/month. Cancel anytime.

Hosted agent

OpenClaw or Hermes

saved state
Browser
WhatsApp
Telegram
Slack
“I checked the inbox, handled the routine messages, and sent you the one question that needs a decision.”
Create an AI worker that keeps running after this tab closes.
Open Agent Factory