Weekly AI Tools
What the agentic platforms actually shipped each week, read by someone who has to put these things into production rather than demo them.
The series
Every week the agentic AI feed fills with model launches and capability demos. Very few of them change what an enterprise can actually run. The releases that do tend to be unglamorous: an identity model for agents, an approval queue for tools, a billing meter, an audit trail. This is my running log of those, and of what they imply for the architecture underneath.
The question the series keeps asking is not what a platform can now do, but what it will let you put in front of a customer, and who signed off on it.
Week 33 
Weekly AI Tools That Matter to Me: Part 4, Week 33
In eight days Anthropic shipped scanning for third-party skills, Google shipped an administrator approval queue for them, and Treasure AI redefined a saved workflow as a skill. Software supply chain vocabulary, applied to prose. Meanwhile the read-only phase of agent integration ended without an announcement.
Week 32 
Weekly AI Tools That Matter to Me: Part 3, Week 32
Three agent platforms published releases in the same week and shipped no new model, no new agent type and no new autonomous behaviour. What they shipped instead was enterprise identity, tool-call tracing and consumption billing, which are the three things that were actually blocking rollouts.
Week 31 
Weekly AI Tools That Matter to Me: Part 2, Week 31
One frontier model landed this week, and it was not the story. The consequential releases were an administrator key that makes MCP tool approvals expire with the session, and a console for finding out which agents you are already running.
Week 30 
Weekly AI Tools That Matter to Me: Part 1, Week 30
The first edition of a new weekly series on agentic work platforms. This week the big three stopped selling capability and started selling control: OpenAI Presence, cryptographic agent identity in Gemini Enterprise, and governed publishing in Microsoft Copilot.