Product Wishlist | Community
Skip to main content

    Idea Pipeline

    Filter by idea status

    Browse by category

    3160 Ideas

    Philipp Hofmann
    Philipp HofmannNew Participant

    Allow Fin to adapt a custom personalityPlanned

    One of the great advantages of language models such as GPT, is that it can easily cover a huge variety of different tones in the language and by that - be more human. In my feeling, this is also one of the main benefits comparing Fin to a classic Chat Bot Model.However, I feel in the current implementation Intercom lacks way behind, of what could actually be achievable here. Many other GPT based custom bots allow a setting called “Custom base prompt”, which adds a custom user input to the base prompt of the conversation, before the bot answers. This would allow users, to actually custom brand the tone of their  Chatbot and match to their brand.Intercom customers cover a huge range of different industries, corporate scales and end-customer groups, which currently all get addressed the same way, although GPT would actually be able to to this way more personal. I want to give you an example:Our customers are graduation students, so Gen-Z individuals. Fin answers very professionally atm, as it would talk with a 60 years old corporate purchaser. By adding an input field to the Fin Profile like “Set a custom tone of voice for Fin” we as a company could write there: “You are talking with Gen-Z individuals and should use a very relaxed and young communication style. Feel free to build in jokes to your answers, but to not exaggerate. Keep your answers as short as possible.” … we could adapt the voice tone of Fin to actually work seamlessly with our customers and add a huge benefit, compared to a classic chat bot.From product perspective there may be a concern of manipulating the Fin answer style too hard via the free text input, so as a variant to the implementation idea on top, I could also imagine selection dropdowns instead of free text input.  Something like:Communication tone: Professional (Default) | Funny | Rough | Flirty | Poem …Main Target Audience: 16-24 | 24-38 | 39-50 ...( or millieus, industries, free input, tbd)etc. TLDR: Setting to set custom voice tone of Fine to align with brand communication style  

    NickBxNew Participant

    Fin Tagging in Conversation Notes for AI Re-engagementSubmitted

    Problem Statement: Currently, when Fin (Intercom's AI agent) hands over a conversation to human team members, it cannot be re-engaged to assist further in that conversation. This limits our ability to leverage Fin's capabilities for follow-up tasks, information gathering, or customer communication during ongoing support cases.Proposed Solution: Enable @fin tagging functionality within the internal notes section of conversations, similar to how team members can be tagged with @mentions. This would allow human agents to give Fin specific directions and tasks after handover has occurred.How It Would Work: Team members could type @fin followed by instructions in the conversation notes, and Fin would receive and act on these directions immediately.Use Cases & Examples:Information Gathering: @fin - please can you find out more about how the customer has their caching setup? Customer Communication: @fin - please can you respond to the customer and thank them for their patience while we investigate. Technical Follow-up: @fin - I've found a problem with the WP Rocket plugin, ask the customer if we can change the Cache life-span value to one week. Documentation Requests: @fin - can you send the customer our guide on SSL certificate installation?Benefits:Seamless collaboration between AI and human agents Faster response times for routine tasks Reduces human agent workload for standard communications Maintains conversation context and continuity Leverages Fin's knowledge base access during complex casesExpected Outcome: This feature would create a hybrid support model where human expertise and AI efficiency work together throughout the entire customer journey, rather than being limited to initial contact only.