Fini's self-maintaining knowledge layer. It writes help articles from resolved tickets, flags conflicts, and grounds every AI answer in one cited source.
Replies
Best
Sounds very interesting, I have not seen per resolution pricing. I would be more cautious about the setup/onboarding. If it needs to tie into your APIs, this is basically like a full-on product integration vs. an additional extension. What is the typical onboarding time for a customer from signup to full autonomy for a SaaS? I would think it would take lots of time from your CTO to get it done.
@adam_el_gerbi We achieve full autonomy in 30 days after a customer signs up. After that, there could be of course fine tuning and feedback loops happen with our team of AI engineers to increase the resolution rate upto 90% as AI act on case to case basis the complexity and the use case. We typically achieve 90% resolution in 60 days from start date.
Report
The knowledge-tree-as-single-source makes sense for the ingest side. The contradictions that got us though weren't visible at ingest, they only showed up at answer time: two docs each internally fine, but a specific question pulled a clause from each and the combination was wrong. Nothing flagged on load because individually they were consistent. Do you run any contradiction check at answer-assembly, or is it all resolved when the tree gets built?
Report
There is a real need for this. As we’ve been building agents for SMBs in SEA. We’ve seen first hand that knowledge base is hard to build and maintain for these small organization. Any system that can automate that would be very useful.
Replies
Sounds very interesting, I have not seen per resolution pricing. I would be more cautious about the setup/onboarding. If it needs to tie into your APIs, this is basically like a full-on product integration vs. an additional extension. What is the typical onboarding time for a customer from signup to full autonomy for a SaaS? I would think it would take lots of time from your CTO to get it done.
Fini
@adam_el_gerbi We achieve full autonomy in 30 days after a customer signs up. After that, there could be of course fine tuning and feedback loops happen with our team of AI engineers to increase the resolution rate upto 90% as AI act on case to case basis the complexity and the use case. We typically achieve 90% resolution in 60 days from start date.
The knowledge-tree-as-single-source makes sense for the ingest side. The contradictions that got us though weren't visible at ingest, they only showed up at answer time: two docs each internally fine, but a specific question pulled a clause from each and the combination was wrong. Nothing flagged on load because individually they were consistent. Do you run any contradiction check at answer-assembly, or is it all resolved when the tree gets built?