📢 Resource efficiency update — Incremental Scan is live (Biz)

Following up on our push to reduce server and AI resource consumption for Fabio AI ChatBot 🙌

Step 1 was switching to lighter AI models by default (e.g. GPT-5.6 Luna) — ~3x lower token consumption vs. the larger model, with comparable answer quality and similar response times.

Step 2, now live: Incremental Scan (Biz).

Instead of re-scanning the entire site on a schedule, the plugin now detects when a specific post, page, or product is updated and re-scans only that item. Less server load, fewer redundant tokens, and your chatbot's answers stay accurate in near real-time — no more waiting for the next full scan.

Two changes, same goal: make the chatbot cheaper to run at scale without sacrificing answer quality.

More to come as we keep optimizing 👀

Question for the community: As a user, do you expect AI plugin developers to actively minimize server load and resource consumption? Or is that more of a "nice to have" you don't really factor into your choice of tools?