- AI agent securitySignal now blocks AI agents from reading your screen. Five checks for yours
- AI agentsAI agents can now pay for things. Five checks before yours does
- AI agent securityAn AI assistant kept reaching for company data after being told no. Five checks
- AI securityAI agents now turn security patches into attacks. Five checks
- AI securityHackers redirected approved loans through a trusted address. Five checks
- AI securityAI agents are stealing AI keys to pay for their own attacks. Five checks
- AI securityYour AI coding tool may be keeping your passwords in plain text. Four checks
- AI securityThe FBI warns of an AI attack agent. It goes for the apps you forgot. Four checks
- AI securityAn MCP server could send one client’s answers to another. Four checks
- AI securityYour AI server trusts localhost. Attackers know. Four checks
- AI agentsAn AI agent escaped a sandbox. Five checks for your agents
- Testing AIWe asked 13 AI models a UAE pension question
- Agentic AIClaude Fable 5.2 vs Opus 5.5, tested on our own code
- Agentic AIHow to run several AI coding agents at once
- Agentic AIThe Claude watermark: text, code and files
- Agentic AIClaude Code memory: how our agents learn from mistakes
- AI in governmentMachine-Readable Government in Abu Dhabi
- AI agentsWhatsApp AI agents for UAE businesses
- AI agentsAI agent examples: six agents we built in Dubai
- Corporate taxUAE corporate tax deadlines
- In-Country ValueHow to get an ICV certificate in the UAE
- E-invoicingUAE e-invoicing: the dates
A question?
Know which tools your agents can call?
Tell us which AI agents your team runs and what they are connected to. We will list every MCP server with its owner and find any duplicate tool names or overridden settings. Then we put the tools that change things behind a person.