Please tell us what we can do to make Featurebase the best product for you.
@mention Fibi in Slack to get answers
Allow customers and teammates to @mention Fibi in a Slack channel or thread to get answers from your documentation. Customers could ask Fibi before tagging your team. Teammates could bring Fibi into an existing discussion to help answer a customer's question or find information internally. Fibi should use the thread for context and reply in the same place, with a way to hand over to your team when human help is needed. Quick internal questions should not create unnecessary support conversations.
Advance notice before AI model changes
Notify customers in advance before the underlying AI model behind the support agent is changed, including the lead time and the channel used, and disclose which AI model(s) are currently in use. Prompts and knowledge bases tuned to the current model's behavior can degrade in answer quality when the model changes without warning, making performance changes hard to trace. The primary use case is investigating changes in answer quality rather than gating rollout approvals, but advance notice remains a desired feature. As a possible approach, the data science team evaluating the product suggests handling model changes like software versioning: release a new version of Featurebase that uses the different model while still supporting the current version, let customers evaluate and tune their prompts for the new model, then switch to the new version, after which support for the old version ends.
Manage Fibi custom actions via API & MCP
Create and update Fibi custom actions through the API and MCP. This would let an AI agent configure and maintain actions without having to complete each setup through the dashboard.
Configurable crawling interval and manual force recrawl for Fibi training data
Allow setting custom automatic recrawling intervals (e.g., daily or multiple times per day) for website training data sources like status pages, along with a direct button to force an immediate recrawl.
AI conversation attribute categorization without Fibi as a step
I want AI conversation attributes to categorize and route conversations based on their meaning, without requiring a 'Let Fibi answer' step or a reply to the customer first. Exact keyword matching is not reliable enough. For example, we route incoming emails to either our Questions or Bugs team. Questions should use our documentation to answer the customer. Bugs need diagnostic questions to collect the missing details, then a faster handoff to a human. The AI should first read the email silently, set the relevant conversation attributes, and let the Workflow route it to the correct team and instructions. Fibi can then reply if that branch requires it, or the conversation can go straight to a human.
Improve Fibi's resistance to completing unrelated tasks
Improve Fibi’s resistance to use as a general-purpose assistant. Fibi should decline unrelated tasks, such as translating personal messages, and redirect users to company support topics. Visitors can currently abuse Fibi as their GPT alternative in certain scenarios.
Toggle to allow or disallow images in Fibi responses
Add a setting to control whether Fibi can include images in responses. When disabled, Fibi must send text-only replies, including no separate image galleries or email image attachments.
Option for AI Agent to look for in a specified collection of articles for a workflow
If i have 3 Workflows for A, B, C, i would like Fibi AI agent to only look for in the corresponding collection of article. If the workflow A is running, Fibi AI agent should only look in the A collection articles, etc. Today he is mixing collection in this anwser leading to totally inconsitent answer. We’ve tried to be strict in his prompt but it still happen sometimes.
Git repository integration for AI agent training data
Connect a Git repository (GitHub, GitLab) as a first-class knowledge source for the Fibi AI Agent, so that training content is maintained where the documentation already lives. Requested behaviour Connect one or more repositories and select file patterns (for example docs/**/*.md). Re-index on push, and show the diff between the previous and current version of each training file so reviewers can see exactly what changed. Preserve manual edits made in Featurebase across re-indexing, rather than overwriting them. Report per-file index status so a failed file is visible without opening every entry. A customer evaluating Featurebase raised this after comparing with Gleap's Code Repositories feature, where a connected repo generates knowledge entries automatically on each re-index and manual edits are kept. Today the Training Data API and MCP make this possible to build from the customer side using stable externalId values, but there is no native connector, no change detection and no diff view. Related: Source Markdown Files from Git Repositories (Help Center scoped) and APIv2 for Fibi Training Data Management.
Option to whitelist crawler IP addresses or User-Agent for website training data
Allow teams to whitelist the Fibi website crawler in their WAF/firewall by providing a published list of crawler IP addresses or a dedicated User-Agent string.
Fibi AI agent automatically create feature requests from conversations
I want an option or setting to let Fibi AI agent automatically create feature requests/posts in Featurebase directly from customer conversations. This is important because it would fully automate logging feedback.
Custom Actions for Support Agent Copilot
I would like the support agent Copilot to have access to the same custom actions that Fibi can use. This would allow me to run actions, such as checking user permissions, directly from the Copilot interface during a conversation. It makes sense for these actions to be available to both Fibi and the support agent Copilot, enabling me to provide full support within the chat without needing to switch to a different system.
Planned
Fibi follow-up setting customization
There should be a way to configure Fibi's follow-up behavior, including options like: Fibi will confirm whether the user still needs assistance - Fibi asks a short follow-up question after answering, such as “Did that answer your question?” Fibi will offer escalation - Fibi checks in and offers to connect the user with a teammate if they still need help. No follow-up - Fibi sends only the main answer and does not send follow-up prompts or idle nudges. Fibi, currently always sends follow-up prompts and idle nudges based on internal logic, but there is no surfaced setting to disable or customize that behavior.
Fibi Agent Tool & Reasoning Transparency
Problem The Fibi agent is currently a black box with no visibility into which tools are being called (especially custom actions) and behind the scenes reasoning. This makes it difficult to triage poor responsive, evaluate how effective custom action instructions are, and know if custom actions are being called or not. Vision Have an expandable section within the chat thread in the support dashboard that shows tool calls and reasoning text. Out of scope Tool call and reasoning visibility changes to the user in the chat window.
Allow drafting Fibi Actions
Currently Fibi Actions need to be created from start to finish - without an option to leave it in a Draft state - making it tedious to re-enter information. Accidentally dismissing a modal without a dirty form state confirmation leads to loss of work.
Planned
AI-detected conversation tags
Allow Fibi to automatically set conversation tags based on conversation context, similar to how conversation attributes can currently be detected and updated by AI. Today, tags can be applied through workflow rules such as keywords or explicit tag actions, which does not cover cases where the correct tag depends on understanding the full conversation.
Toggle Modes for Copilot - Read & Write / Action-Specific Options
It would be great to have a toggle feature in Copilot that allows users to switch between different modes such as Read-only, Draft creation, Posting, and Ticket management. This would make Copilot more predictable and tailored to users' specific needs, improving workflow efficiency when using AI assistance for various inbox tasks.
Option to exclude specific data / changelogs from Fibi AI knowledge base
Fibi AI currently references outdated v1 solutions from public changelogs. Provide an option to exclude specific changelogs from Fibi's knowledge base to prevent it from providing irrelevant or deprecated information. This logic would apply to roadmaps, and other Featurebase native datasets.
Per-brand Fibi name and custom instructions
I want to be able to configure a unique name and specific custom instructions for the Fibi AI Agent for each individual brand in a multi-brand setup. Currently, these settings are global, but for a true multi-brand experience, Fibi should be able to have a different identity (name and personality) depending on which brand's Messenger or Help Center the customer is interacting with.
AI Agent: Attach images/screenshots from chat to created posts
I want the Fibi AI Agent to be able to automatically attach screenshots and images provided by users in the chat to the feedback posts it creates. This is important because users often provide visual context for bugs or features that is lost when the agent only creates a text-based post.