Conversation history

History is the single record of every conversation your workspace has — phone calls, web widget voice and chat, WhatsApp text and voice, email, and every connected messaging channel — sorted by most recent activity. A conversation appears here the moment it starts, not just after it ends.

​

The list

Each row shows the contact, the assistant that handled it, type, direction, status, duration, date, a short summary, and the contact’s tags. Reply threads — every inbound and outbound turn on the same email thread or messaging conversation — are grouped into one row, so a back-and-forth reads like a single conversation instead of one row per message.

​

Conversation summaries

Conversation Summary shows a generated recap only. If none is available, the list cell stays empty and the summary section is hidden. The email subject, original messages and transcript remain available in the details. Success explanations stay in Analysis.

• Calls, widget conversations and WhatsApp voice: a summary is generated after the conversation ends when a usable transcript is available. Older calls may finish processing after you open their details; refresh to see a newly saved summary.
• Messaging channels, including Instagram, Gmail, Outlook and Zendesk: analysis runs when the conversation ends, either manually or after the connection’s configured inactivity period.
• Native email: the thread is analyzed after a successful automatic reply. Skipped or failed replies and outbound-only threads can have no summary.

An ongoing conversation, insufficient content or unsuccessful analysis can leave the summary empty. Translate keeps its bilingual transcript without automatically generating a summary.

​

Filtering

Choose Add filter, pick a category and value, then click Apply. Applied filters become compact chips. Click a chip to edit it; hover or focus it to read a long value in full. Use × to remove a filter, + to add another, or Clear all to reset them. Direction appears as an icon before the contact; hover or focus it to see its name. Narrow the list by any combination of:

• Type — Call, Avatar (web voice with a virtual avatar), Live chat (widget text chat), WhatsApp voice, WhatsApp, Email, or a specific messaging platform (Telegram, Slack, Messenger, Teams, Discord, Google Chat, X, plus any Beta connectors your workspace has enabled).
• Direction — inbound, outbound, or web.
• Status — queued, in progress, completed, failed, no answer, busy, or skipped.
• Assistant or Campaign.
• Tags — show only conversations whose contact carries a given tag. Opening History from an Audience contact narrows the list to that one contact.
• Search — matches phone numbers and call summaries, the contact name or handle on messaging channels, and email addresses, subjects, and message bodies.

Filters combine, and the list paginates underneath them. A date range isn’t a filter in the app — use from and to on the API when you need one.

​

Conversation detail

On desktop, Overview, Insights (voice calls) and Details switch the left column. The recording and transcript stay visible on the right, and the bottom action buttons reveal their labels on hover or keyboard focus. On mobile, call details are organized into Overview (contact, summary and analysis), Transcript (recording and conversation), Insights (voice measurements), and Details (call information, usage and automation). Open Actions at the bottom to see the available operations and their credit costs. Open a row for the full picture:

• Recording and transcript (calls) — play the recording in the built-in player or download the audio file. The transcript follows the playback, and selecting a line jumps the audio to that moment. After a call you can request an Enhanced transcript re-generated from the recording and switch between it and the live one.
• Input variables — values passed into the conversation before it started (pre-chat form answers, campaign lead data, API-supplied variables).
• Analysis — sentiment, the success verdict with its reason, any structured fields your assistant’s post-call analysis is configured to extract, and the per-call AI QA scorecard (score, pass or fail, and the criteria behind it) when your assistant has scorecards enabled.
• Webhook & Automation — delivery status for any outbound webhook tied to the conversation, with the HTTP response.
• Usage & cost for that conversation.

​

Actions

Select one or more rows — or act on the open conversation directly — to: Messaging conversations add a few controls of their own. You can reply by hand from the conversation; Stop AI and Resume AI decide whether the assistant keeps answering — stop it to take over yourself, resume it to hand the conversation back; and End conversation closes it out. On WhatsApp there’s one extra step: replying by hand to a conversation that already ended prompts you to either keep it completed or Resume AI, which reopens it for auto-replies and restarts the inactivity timer. That’s only possible while Meta’s 24-hour service window is still open, and resuming does not extend that window.

​

Exporting

The Export button downloads the current filtered page as a CSV (contact, assistant, type, direction, status, duration, date, and summary). Apply filters first to scope what’s included, then export — each page of results exports separately.

​

Activity notifications

Each assistant carries its own notification matrix, configured from Assistant → Settings → Automations → Notifications, that controls whether workspace owners and admins get an email when new activity lands in History for that assistant. The matrix has one row per channel — Calls, Avatar, Live chat, WhatsApp voice, WhatsApp, Telegram, Slack, Messenger, Teams, Discord, Google Chat, X, and Email — and a checkbox turns email on or off per channel, independently for each assistant. Every channel starts switched on, so this is a list to opt out of rather than into. The same per-channel switch also governs the device alerts a member can turn on for their own browser or installed app under Browser notifications.

​

Related channel views

• Email history covers the email-specific reading view (reply states, sender/recipient/subject, attachments) in more depth.
• Live monitoring & supervisor covers listening in on and intervening in a call while it’s still happening.

​

API and MCP

• REST: GET /api/v1/history (calls:read) — filter with type, direction, status, assistant_id, campaign_id, lead_id, tags, search, from, to, limit, offset.
• REST: GET /api/v1/history/emails/{id} reads one email thread’s full detail.
• REST: POST /api/v1/history/actions runs the actions above — reanalyze, retranscribe, resend_webhook, resume_ai, blacklist_add, blacklist_remove — on up to 50 records at a time, addressed by kind (call, messaging, or email). retranscribe is the exception: it takes exactly one call id per request.
• REST: GET /api/v1/calls, GET /api/v1/calls/{id}, and GET /api/v1/calls/{id}/recording cover the call-specific view, including the recording file, for type: call rows.
• MCP: list_history, get_email_history_item, run_history_actions, plus list_calls / get_call for the call-specific view.

​

Message labels

New incoming messages can receive a Possible scam label. Unsolicited sales pitches, SEO offers and paid award promotions in email can receive Advertising. Labels appear beside the message and in the History list after background processing. These are advisory hints and may be wrong. Messages remain visible, replies continue as usual, and no message is moved, deleted or marked as spam in a connected mailbox, including Gmail. No label does not mean a message is safe. Booking and customer enquiries should remain unlabelled. Workspace owners and admins can switch Message labels on or off in Settings → Workspace, when included in their plan. Changes apply to new messages; existing labels remain. Members with write access can dismiss an incorrect label in the message details. History API responses and the history MCP tools include active labels. Use dismiss_inbox_label to dismiss one, and get_inbox_label_settings / update_inbox_label_settings to manage the workspace setting.

​

Remove conversations from History

Workspace owners and admins can select one or more conversations and choose Remove, or use the same action in a conversation’s details. Active conversations must finish first. The selected conversations are removed for the whole workspace: they disappear from History and new exports, and their call/history API and MCP detail links return not found. Stored conversation content remains subject to your workspace’s existing retention policy. Removal does not reset that policy’s clock, erase data immediately, refund credits, or change historical usage and statistics. Previously issued download links remain valid until they expire; existing exports and copies sent to connected systems are unaffected. Use POST /api/v1/history/actions with action: "remove", the conversation kind, and up to 50 ids. The MCP equivalent is run_history_actions. A child email message ID removes its whole thread. Check per-record results when processing a batch. The action requires calls:write; user-owned credentials additionally require workspace owner/admin access. A new incoming message makes a removed email or messaging thread visible again. Old message imports and outgoing messages do not.

​

Call insights

Open a voice call in History, then choose Insights. On desktop, the recording and transcript remain visible beside the insights. On mobile, selecting a measured reply opens its transcript location.

​

Recording and transcript

Select a recorded transcript turn or timeline marker to listen at that point. Download sits beside playback speed, with elapsed and total time underneath. Audio output delay appears beneath the player on hover or keyboard focus, and remains visible on touch devices. Speech before the recording starts is marked Before recording and has no playback target. Consent and recording settings continue to govern which audio is available. Create Simulation Test and Add to FAQ are in the same action area as the other call operations. Hover or focus an icon to see its label; on mobile, open Actions. FAQ requires workspace Beta Features and a usable conversation. Review the proposed answer before publishing it.

​

Availability and older calls

Voice insights cover phone calls, web voice and WhatsApp voice calls. Text chats do not display voice timing or recording controls. The exact measurements depend on the conversation mode and which data was captured; unavailable values are not treated as zero. Older calls can display insights from data already stored. Opening an old call does not recover missing measurements or trigger a historical synchronization. New calls can include more measurements. No assistant setting change is required to view available insights. The public call-detail API and the MCP Get call tool include the same customer-facing insights.