Resources
Thinking on routing, judgment, and getting AI spend under control.
Posts, guides and release notes from the people building Verybear. No filler, no lorem ipsum.
Why we route tasks, not models
Model routers pick a cheaper model for the same prompt. That's not the problem worth solving. The problem is that nobody wrote down how the task should be done in the first place.
Morgan Idris
January 14, 2025
Your AI bill is a judgment problem, not a token problem
Finance keeps asking which model to cut. Wrong question. The spend that actually hurts is the spend nobody decided to make.
Morgan Idris
January 28, 2025
Flows beat prompts: how one person's know-how becomes everyone's
Prompt libraries are where good practice goes to die in a shared doc nobody opens. Flows are where it goes to actually run.
Jules Okafor
February 6, 2025
What a CFO should actually ask about AI spend
Not "how much are we spending." Five sharper questions that tell you whether your AI spend is under control or just quiet.
Ren Castillo
February 19, 2025
Setting up budgets per team in 10 minutes
A short, practical walkthrough: set a budget per team, an alert threshold, and know exactly what happens when a team gets close.
Jules Okafor
February 25, 2025
Writing a good playbook
A playbook is the difference between a flow that works and a flow that just runs. Here's how to write one that actually changes the output.
Morgan Idris
March 4, 2025
Verybear 1.4: discovery inbox, staged rollout, Microsoft sign-in
A redesigned discovery inbox for new flows and optimizations, staged rollout for policy changes, and Microsoft sign-in for every tier.
The Verybear team
March 12, 2025
7 of 7 items