Briefing
Agents are crossing app boundaries. The handoff matters.
A source-based briefing on Google Workspace and Claude: where tasks start, where work happens, and what users still need to verify.
Read the briefingExplainer
What is Instinct? The personal assistant behind the name
A text. A task. An assistant that takes it from there. We look at what Instinct promises—and what a real-world trial still needs to prove.
Read the explainerMore to explore
Methodology
An agent should leave you with proof
Our testing method: a real task, explicit permissions, a result you can inspect, and a record of the work still left to you.
Read our methodThe daily drawing
“It says ‘Done.’ I’m on page four of what that meant.”
On delegating to agents: a confirmation is short; the record of what happened is not.
Original drawing for Agent Report, made with AI assistance. A conceptual illustration, not a depiction of any product.
How to read a report
Every article says which kind of work it contains.
We publish source reviews, analysis and practical guides. No hands-on trials have been published yet; when they are, they will carry their own label.
Our standard of evidence- Vendor claim
- A capability described by the company.
- Source review
- Our reading of linked documentation or announcements.
- Hands-on observation
- An outcome we directly inspected during a disclosed trial.
- Analysis
- Our interpretation, including uncertainty and questions for further testing.