Feature Request

Description We need more granular permission control in Respond.io so we can restrict technical settings to a dedicated role. Right now, it would be helpful to separate access for: - Workflows - AI Agent configuration - Organisation settings - Channel settings. This would let us give day-to-day users access only to their operational tools, while keeping technical/admin settings limited to a small trusted team. It would improve security, reduce mistakes, and make role management easier for larger teams. Use case: We want managers or operators to handle broadcasts, inbox work, or reporting, without giving them access to workflow or technical configuration areas.

Today, an administrator is unable to make a member absent if they forget. Therefore, adm should be able to perform this type of operation, of course, by recording logs.

i update my document, and i cant delete the old ones

Use case: The AI Agent to detect when an outbound message has failed so it can take the right next step automatically. Why this matters: When a message fails, the conversation may need human intervention. If the AI Agent can see the failed status, it can: assign the conversation to a human add an internal comment with context trigger a workflow for follow-up retry after a few minutes Expected outcome: This would help reduce missed replies, speed up resolution, and ensure failed outbound messages are handled consistently.

I checked the Users report docs, and it currently supports date-based filters only — for example: Today Yesterday Last 7 Days Last 14 Days Last 30 Days This Month Last Month It also uses your workspace timezone . So at the moment, there isn’t an hour-by-hour range filter like 12:00 AM to 6:00 AM in the Users report. If you’d like this as a product improvement, you can submit it here: https://respond.canny.io/feature-request

Business Problem: A Contact can only hold a single Lifecycle Stage at a time, so each Contact represents exactly one lead. Accounts that involve multiple parallel opportunities under one conversation — such as a family with several children enrolling, where each child is a separate lead — can't be tracked individually without creating duplicate Contacts. Desired Outcome: Allow multiple leads/deals to be linked to a single Contact, each progressing through its own Lifecycle Stage independently Track and report on each lead/deal separately while keeping them under one conversation Mirror the HubSpot model, where several deals can be associated with one contact Use Cases: Schools: A single family conversation enrolls more than one child, with each child at a different stage of the enrollment funnel.

Business Problem: Currently, each AI Agent follow-up must be scheduled within 24 hours (1 day) of the previous message. This caps automated re-engagement at a one-dat cadence, which is too short for sales and retention cycles where prospects often need several days or weeks before they are ready to respond. Desired Outcome: Let users set follow-up intervals beyond 24 hours (e.g. 3 days, 1 week) per follow-up step, so AI Agent can re-engage on longer cadences. Use Cases: A sales AI Agent re-engages an unresponsive lead after 3 days, then again after 1 week. Current Workaround: Build a separate Workflow with a Wait step and a Send a Message step to re-engage past 24 hours. This duplicates the follow-up logic outside the AI Agents and risks sending duplicate messages.

You need to have a full test studio that you can simulate full conversations and see everything that is occuring from http requests to workflows and to see step by step the data in and out. Also http requests need better response handling and capabilities to map easy to contact fields plus the ability to use full api javascript to invoke api calls vs http requests for everything this should be a module available in workflows plus the ability to directly trigger flows from the ai agent instructions.

Business Problem: When AI auto-generates a conversation summary upon closing, there is no way to configure how that summary is produced. The language of the summary defaults to English regardless of the language the conversation was conducted in, and there is no option to choose the type of summary output — for example, a bullet-point breakdown, a brief one-liner, or a structured recap with key fields like issue, resolution, and next steps. This limits the usefulness of AI-generated summaries for multilingual teams and businesses with different reporting or handoff needs. Desired Outcome: To be able to configure the language and format/type of auto-generated conversation summaries at the workspace level.

Business Problem: There is currently no notification when AI credit consumption approaches its monthly limit. When credits hit 100%, all AI features pause immediately. High-volume organizations have no way to anticipate depletion. Desired Outcome: Send an alert to Organization Admins when AI credit usage reaches a defined threshold — starting at 50%. Use Case: A high-volume organization relies on AI Agents for automated support and lead qualification. A 50% usage alert lets the admin monitor consumption mid-cycle, redistribute AI usage, and top up credits ahead of time — preventing the sudden pause of AI features that today happens only once credits are fully exhausted.