# Ask Fibery AI Assistant questions about data in Fibery (databases content, docs content) **URL:** \ **Category:** Ideas & Features\ **Created:** [April 5, 2023, 9:59am UTC](https://community.fibery.io/t/ask-fibery-ai-assistant-questions-about-data-in-fibery-databases-content-docs-content/4272 "2023-04-05T09:59:58Z")\ **Posts on this page:** 7\ **Page:** 1
**Author:** ![Michel\_Daviot](https://sea2.discourse-cdn.com/flex020/user_avatar/community.fibery.io/michel_daviot/32/6094_2.png) [@Michel\_Daviot](https://community.fibery.io/u/Michel_Daviot)\ **Post date:** [April 5, 2023, 9:59am UTC](https://community.fibery.io/t/ask-fibery-ai-assistant-questions-about-data-in-fibery-databases-content-docs-content/4272/1 "2023-04-05T09:59:58Z")
Thanks for this new feature. Here are 2 use cases I’d appreciate to see covered in the future: # Long document summary Today the limitation in tokens is too strict for my usage. When I want a summary, it’s because the original document is quite long (eg : an R&D document 5 pages long). # Smart questions on all my workspace content We store a lot of textual information in documents and rich text fields of entities about how our software is supposed to work. I’d love if the AI assistant would be able to “index” this information (daily probably) and we would be able then to ask it questions and get answer based on our own data, rather than on the “standard indexes” of openai. ---
**Author:** ![Lee\_Denny](https://sea2.discourse-cdn.com/flex020/user_avatar/community.fibery.io/lee_denny/32/8158_2.png) [@Lee\_Denny](https://community.fibery.io/u/Lee_Denny)\ **Post date:** [December 10, 2023, 12:23pm UTC](https://community.fibery.io/t/ask-fibery-ai-assistant-questions-about-data-in-fibery-databases-content-docs-content/4272/2 "2023-12-10T12:23:06Z")
Yes would love to be able to do things like this: ![Screenshot 2023-12-10 at 12.21.01](https://us1.discourse-cdn.com/flex020/uploads/fibery/original/2X/2/21089b97565a3e8ce54cf206a1cd1821f8f03732.png) ---
**Author:** ![Lee\_Denny](https://sea2.discourse-cdn.com/flex020/user_avatar/community.fibery.io/lee_denny/32/8158_2.png) [@Lee\_Denny](https://community.fibery.io/u/Lee_Denny)\ **Post date:** [January 18, 2024, 9:01pm UTC](https://community.fibery.io/t/ask-fibery-ai-assistant-questions-about-data-in-fibery-databases-content-docs-content/4272/3 "2024-01-18T21:01:03Z")
Thanks for implementing this - being able to connect databases is great - in my given example it struggles with referencing correct date ranges though - i ask for 2023 but it gives 2022 links. Maybe being able to choose which fields it can index could help? ![Screenshot 2024-01-18 at 20.58.01](https://us1.discourse-cdn.com/flex020/uploads/fibery/original/2X/e/ec3e678f7d95697c058b2865b2b42ab5e02c21a5.jpeg) ![Screenshot 2024-01-18 at 21.00.34](https://us1.discourse-cdn.com/flex020/uploads/fibery/original/2X/f/f447aaf514b490e94181dfbda6f7c6ae14f5c40e.png) ---
**Author:** ![Dimitri\_S](https://sea2.discourse-cdn.com/flex020/user_avatar/community.fibery.io/dimitri_s/32/1683_2.png) [@Dimitri\_S](https://community.fibery.io/u/Dimitri_S)\ **Post date:** [January 19, 2024, 12:23am UTC](https://community.fibery.io/t/ask-fibery-ai-assistant-questions-about-data-in-fibery-databases-content-docs-content/4272/4 "2024-01-19T00:23:04Z")
It’s a limitation to how the RAG systems work. Basically it’s retrieving the top 5 records that are the most relevant to your query and then uses their contents to answer your question. So if you ask questions that are beyond what those 5 records can answer it’s very likely going to not answer your question and/or hallucinate. Asking a question that spans many records will require at a minimum giving the AI the ability to write it’s own QraphQL queries but more likely will also require it to write it’s own code to process those queries. Something like what the ChatGPT code interpreter or advance analysis tool, or whatever it’s called now. @Lee_Denny ---
**Author:** ![mdubakov](https://sea2.discourse-cdn.com/flex020/user_avatar/community.fibery.io/mdubakov/32/10_2.png) [@mdubakov](https://community.fibery.io/u/mdubakov)\ **Post date:** [January 19, 2024, 7:02am UTC](https://community.fibery.io/t/ask-fibery-ai-assistant-questions-about-data-in-fibery-databases-content-docs-content/4272/5 "2024-01-19T07:02:20Z")
> [@Dimitri\_S](#): > > Asking a question that spans many records will require at a minimum giving the AI the ability to write it’s own QraphQL queries This is our goal for near future. Indeed right now the chatbot knows nothing about Fibery structure, time, and other things. ---
**Author:** ![mdubakov](https://sea2.discourse-cdn.com/flex020/user_avatar/community.fibery.io/mdubakov/32/10_2.png) [@mdubakov](https://community.fibery.io/u/mdubakov)\ **Post date:** [May 22, 2025, 1:37pm UTC](https://community.fibery.io/t/ask-fibery-ai-assistant-questions-about-data-in-fibery-databases-content-docs-content/4272/6 "2025-05-22T13:37:01Z")
You can try our new AI Agent now > [@May 22, 2025 / roll\_eyes Fibery Smart Agent (beta), Whiteboard Sections improvements](https://community.fibery.io/t/may-22-2025-fibery-smart-agent-beta-whiteboard-sections-improvements/8842): > > Fibery Smart Agent (beta) I know you all tired of AI, but sometimes it can be really helpful. Today we’re releasing the second iteration of Fibery Smart Agent that can answer quite complex questions around your Fibery data, work with rich text in databases, generate text reports, identify patterns and insights across multiple records and categorise data using AI-powered semantic analysis. How good it is? Well, the best way is to try it for yourself. Click Fibery AI in the left menu a… ---
**Author:** ![Chr1sG](https://sea2.discourse-cdn.com/flex020/user_avatar/community.fibery.io/chr1sg/32/3941_2.png) [@Chr1sG](https://community.fibery.io/u/Chr1sG)\ **Post date:** [May 22, 2025, 1:54pm UTC](https://community.fibery.io/t/ask-fibery-ai-assistant-questions-about-data-in-fibery-databases-content-docs-content/4272/7 "2025-05-22T13:54:55Z")