Ivan

Commented on ModelGate · Sep 11, 2026

Managing 3 different SDKs and billing portals for OpenAI, Anthropic and Google is a massive headache for FinOps. Routing them all through a single gateway to get a unified spend view is exactly how multi-model stacks should be handled. Since each provider calculates and prices tokens slightly differently, does ModelGate normalize the token math across the dashboard or does it just log the raw counts exactly as the provider returns them?

Commented on Ari by Ariso · Aug 15, 2026

Trying to remember why a decision was made a few months ago can be harder than finding the decision itself. I’ve had to search old conversations and meeting records just to answer a simple “why did we do this?” question. This tool finding those old decisions could save time. It would be even better if the result showed who made the decision, when it was made and what led to it. Sometimes the reason matters just as much as the decision.

Commented on Savyre AI Coding Workflow · Aug 10, 2026

Savyre's hiring assessments skip the algorithmic trivia and focus on real-world debugging instead which is exactly how you actually test someone. How long does it usually take a hiring manager to set up one of these role-specific assessments?