Hi ! We are actually using HTTP

**Introducing guest access for apps** https://www.windmill.dev/changelog/guest-app-access This is the biggest license change of the last 4 years that purely benefit you and in a potentially substantial way, both for CE an EE users. We often had the feedback that it didn't feel fair to pay an operator seat just to access apps that you made. We didn't have a good response for it until now. Introducing **Guests**. Guests use your current SSO/SAML authorization but they do not count as operator but as guests so long as they only access an app and were not members of the workspace already. In addition, both CE and EE now allow 100 free guests. Past that, they count as 1/4 of a seat. We may be even more generous later with that pricing but that should already unlock a wide variety of use-cases that were made harder purely because of CE restrictions or EE pricing. Now CE works for organization up to 10 devs + 100 guests for free!

rubenf · 6d ago

💰** AI usage and cost tracking ** Token spend from AI sessions and the AI chat is now recorded per workspace, user, provider and model. ➡️ Admins see the whole workspace over the last 7, 30 or 90 days, grouped by day, user or model. ➡️ Every member can see their own usage. ➡️ Costs marked with ~ are estimates. A figure the provider billed back is shown as is, and a model with no known rate reads as unpriced. 📖 https://www.windmill.dev/changelog/ai-usage-and-cost

Fratera · 2w ago

🚀 AI agent evals (beta) A reusable AI agent could only ever run as a flow step, and there was nowhere to keep the inputs that exposed a problem in production. Evals fix that. **You can now measure an agent against a dataset of cases, score every answer, and diff two runs case by case.** ➡️ A dataset is a set of cases, each a question and an expected answer. It belongs to the reusable ai_agent resource, so it outlives the flow step and two runs of the same agent stay comparable. Up to 1000 cases per dataset. ➡️ A run is one flow job: a parallel loop over the cases, each answer scored by one branch per scorer. Scorers are your own code, or an LLM judge that returns a score and a reason. The run outlives the tab that started it. ➡️ Every run is kept, so you can answer the question that matters after a change: did it get better, or did one case break. Compare any two runs of a dataset and the difference shows up case by case and scorer by scorer. This is a beta, tell us what breaks. 📖 Read more: https://www.windmill.dev/changelog/ai-agent-evals

Fratera · 2w ago