{"Status":true,"Message":"","Response":{"post":{"postuid":"5a570475-5005-49d7-95df-46747ae5d3fb","tenantuid":"d8b744fc-2e70-4089-bb80-dd1d08f6c7b2","projectuid":"fc6490ac-7527-4f49-b06e-46f701280e85","title":"Chat Reports","slug":"article/chat-reports","html":"\u003Cp\u003EChat reports show how much the AI agent resolves on its own, how quickly your team responds, when you\u0027re busiest and how many people to have on, and how visitors rate their conversations. They also show what visitors ask about and which questions your documentation doesn\u0027t answer yet. Open them from \u003Cb\u003EInbox\u003C/b\u003E, then \u003Cb\u003EReports\u003C/b\u003E. The reports are split into tabs: \u003Cb\u003EOverview\u003C/b\u003E, \u003Cb\u003EBusy times \u0026amp; staffing\u003C/b\u003E, \u003Cb\u003ESpeed\u003C/b\u003E, \u003Cb\u003EQuality\u003C/b\u003E, \u003Cb\u003EAI agent\u003C/b\u003E, \u003Cb\u003ETeam\u003C/b\u003E and \u003Cb\u003ESources\u003C/b\u003E.\u003C/p\u003E\u003Ch2 id=\u0022video_overview_or_reports\u0022\u003EVideo overview or reports\u003C/h2\u003E\u003Cp\u003EBelow is a video overview of the reporting capabilities.\u003C/p\u003E\u003Ciframe src=\u0022https://player.vimeo.com/video/1237703949\u0022 width=\u0022640\u0022 height=\u0022360\u0022 frameborder=\u00220\u0022 allowfullscreen=\u0022\u0022\u003E\u003C/iframe\u003E\u003Ch2 id=\u0022choosing_a_period_and_exporting\u0022\u003EChoosing a period and exporting\u003C/h2\u003E\u003Cp\u003EUse the menu at the top right to choose \u003Cb\u003ELast 7 days\u003C/b\u003E, \u003Cb\u003ELast 30 days\u003C/b\u003E, \u003Cb\u003ELast 90 days\u003C/b\u003E or \u003Cb\u003ELast 12 months\u003C/b\u003E. Every tab uses the same period. A conversation counts in the period it started.\u003C/p\u003E\u003Cp\u003E\u003Cb\u003EExport CSV\u003C/b\u003E downloads every conversation in the period, one row each, for Excel or a BI tool. Each row includes when it started, how it ended, the handoff reason, the first response time, the time to close, the rating and comment, the start page, the proactive message, the country, the device and the type of visitor. Dates are in UTC and durations are in seconds.\u003C/p\u003E\u003Ch2 id=\u0022how_the_figures_are_measured\u0022\u003EHow the figures are measured\u003C/h2\u003E\u003Cul\u003E\u003Cli\u003EMost times are \u003Cb\u003Emedians\u003C/b\u003E: the middle value, so a few very slow conversations don\u0027t distort them. \u003Cb\u003Ep90\u003C/b\u003E is the time that 9 in 10 were faster than. It shows how long your slowest cases take.\u003C/li\u003E\u003Cli\u003EDays and hours are in your \u003Ca href=\u0022/article/chat-support-hours\u0022\u003Esupport hours\u003C/a\u003E\u0027 time zone, or your own when support hours are off. The line under the tabs says which.\u003C/li\u003E\u003Cli\u003EConversations opened without a question or a reply, such as a proactive message that was opened and closed, are left out of the figures.\u003C/li\u003E\u003Cli\u003ERates are shown in green when they\u0027re good and in red when they need attention.\u003C/li\u003E\u003Cli\u003EIn a very busy period, figures that are based on messages cover the most recent conversations. The page tells you when this happens.\u003C/li\u003E\u003C/ul\u003E\u003Ch2 id=\u0022overview\u0022\u003EOverview\u003C/h2\u003E\u003Cp\u003EThe headline numbers, conversations per day, a week-by-week trend, and how every conversation ended.\u003C/p\u003E\u003Cfigure\u003E\u003Cimg class=\u0022lazy-load\u0022 data-src=\u0022https://graffiti-auf7e6dwhxhcbwek.z03.azurefd.net/d8b744fc-2e70-4089-bb80-dd1d08f6c7b2/fc6490ac-7527-4f49-b06e-46f701280e85/images/47f77c215b574d9588ef862b527beef6.png?v=-1565854526\u0022 data-width=\u0022986\u0022 data-height=\u00221333\u0022 style=\u0022max-width: 100%;\u0022 alt=\u0022Overview tab with headline numbers, conversations per day, week by week and how conversations ended\u0022/\u003E\u003Cfigcaption\u003EThe Overview tab\u003C/figcaption\u003E\u003C/figure\u003E\u003Ctable border=\u00221\u0022 style=\u0022border-collapse: collapse; width: 100%;\u0022\u003E\u003Cthead\u003E\u003Ctr\u003E\u003Cth\u003EFigure\u003C/th\u003E\u003Cth\u003EWhat it means\u003C/th\u003E\u003C/tr\u003E\u003C/thead\u003E\u003Ctr\u003E\u003Ctd\u003EConversations\u003C/td\u003E\u003Ctd\u003EConversations started in the period, and how many were closed\u003C/td\u003E\u003C/tr\u003E\u003Ctr\u003E\u003Ctd\u003EAI resolution rate\u003C/td\u003E\u003Ctd\u003EOf the conversations the AI answered in, the share it resolved without a person, split into confirmed and assumed (see below)\u003C/td\u003E\u003C/tr\u003E\u003Ctr\u003E\u003Ctd\u003EEscalation rate\u003C/td\u003E\u003Ctd\u003EThe share of conversations handed to your team\u003C/td\u003E\u003C/tr\u003E\u003Ctr\u003E\u003Ctd\u003EFirst response (median)\u003C/td\u003E\u003Ctd\u003ETime from the handoff to the first reply from a person, with the p90 underneath\u003C/td\u003E\u003C/tr\u003E\u003Ctr\u003E\u003Ctd\u003ETime to close (median)\u003C/td\u003E\u003Ctd\u003ETime from the start of a conversation to when it closed\u003C/td\u003E\u003C/tr\u003E\u003Ctr\u003E\u003Ctd\u003ECSAT\u003C/td\u003E\u003Ctd\u003EThe share of ratings that were 4 or 5 out of 5, with the number of ratings and the average\u003C/td\u003E\u003C/tr\u003E\u003Ctr\u003E\u003Ctd\u003EConversations per day\u003C/td\u003E\u003Ctd\u003EDaily volume, with the conversations handed to your team in red\u003C/td\u003E\u003C/tr\u003E\u003Ctr\u003E\u003Ctd\u003EWeek by week\u003C/td\u003E\u003Ctd\u003EConversations, AI resolution, handoffs, CSAT and first response for each week, starting on Monday. The current week is still filling up.\u003C/td\u003E\u003C/tr\u003E\u003Ctr\u003E\u003Ctd\u003EHow conversations ended\u003C/td\u003E\u003Ctd\u003EEvery conversation in the period, counted once: AI resolved (confirmed or assumed), answered by a person, started by your team, waiting for a person, missed handoff, unresolved or in progress, and no question asked\u003C/td\u003E\u003C/tr\u003E\u003C/table\u003E\u003Ch3 id=\u0022how_ai_resolutions_are_counted\u0022\u003EHow AI resolutions are counted\u003C/h3\u003E\u003Cul\u003E\u003Cli\u003E\u003Cb\u003EConfirmed:\u003C/b\u003E the visitor clicked \u003Cb\u003EThat helped\u003C/b\u003E, or said the problem was solved.\u003C/li\u003E\u003Cli\u003E\u003Cb\u003EAssumed:\u003C/b\u003E the AI gave the last answer, the conversation was never handed to your team, and the visitor didn\u0027t come back within 24 hours.\u003C/li\u003E\u003C/ul\u003E\u003Ch2 id=\u0022busy_times_andamp_staffing\u0022\u003EBusy times \u0026amp; staffing\u003C/h2\u003E\u003Cp\u003E\u003Cb\u003EBusiest times\u003C/b\u003E is a grid of days and hours. Each square is an average per week, and darker squares are busier. Switch what it shows with the buttons above it:\u003C/p\u003E\u003Cul\u003E\u003Cli\u003E\u003Cb\u003EConversations:\u003C/b\u003E conversations started.\u003C/li\u003E\u003Cli\u003E\u003Cb\u003EHanded to the team:\u003C/b\u003E conversations handed to a person. This is the work your team has to cover.\u003C/li\u003E\u003Cli\u003E\u003Cb\u003ETeammates active:\u003C/b\u003E how many teammates replied or wrote a note in each hour, on average. Compare it with the handoffs to find hours nobody covers.\u003C/li\u003E\u003C/ul\u003E\u003Cp\u003EBelow the grid you see the \u003Cb\u003EBusiest day\u003C/b\u003E, the three \u003Cb\u003EBusiest hours\u003C/b\u003E of the week, the \u003Cb\u003EBusiest time of day\u003C/b\u003E, the share of conversations \u003Cb\u003EOutside support hours\u003C/b\u003E (when support hours are on), and \u003Cb\u003EMost chats at once\u003C/b\u003E: the most conversations one teammate replied in within an hour.\u003C/p\u003E\u003Cfigure\u003E\u003Cimg class=\u0022lazy-load\u0022 data-src=\u0022https://graffiti-auf7e6dwhxhcbwek.z03.azurefd.net/d8b744fc-2e70-4089-bb80-dd1d08f6c7b2/fc6490ac-7527-4f49-b06e-46f701280e85/images/8b51d4de4f84483fa6911600473f7a3c.png?v=-1572873001\u0022 data-width=\u0022986\u0022 data-height=\u00221601\u0022 style=\u0022max-width: 100%;\u0022 alt=\u0022Busy times and staffing tab with a weekly heatmap of conversations, summary cards and the staffing plan with uncovered hours outlined in red\u0022/\u003E\u003Cfigcaption\u003EThe Busy times and staffing tab\u003C/figcaption\u003E\u003C/figure\u003E\u003Ch3 id=\u0022the_staffing_plan\u0022\u003EThe staffing plan\u003C/h3\u003E\u003Cp\u003EThe \u003Cb\u003EStaffing plan\u003C/b\u003E suggests how many teammates to have available in each hour of the week. The AI answers everyone else, so you only need people for the conversations handed to your team. The plan aims to answer 80% of handoffs within 5 minutes.\u003C/p\u003E\u003Cp\u003EIt uses Erlang C, the standard staffing model for support queues. It looks at three things: the average number of handoffs in that hour, how long a person spends on a conversation, and how many chats one person handles at once. Set the last one with \u003Cb\u003EChats one person handles at once\u003C/b\u003E (3 by default). Every hour that has handoffs gets at least one person.\u003C/p\u003E\u003Cul\u003E\u003Cli\u003E\u003Cb\u003EHours outlined in red need cover.\u003C/b\u003E The plan suggests someone for that hour, but no teammate was active in it during the period.\u003C/li\u003E\u003Cli\u003E\u003Cb\u003EIt\u0027s a rough guide until you have 4 weeks of data.\u003C/b\u003E With less, a few busy days can change the plan a lot, and the note under the plan says so.\u003C/li\u003E\u003C/ul\u003E\u003Ch2 id=\u0022speed\u0022\u003ESpeed\u003C/h2\u003E\u003Cp\u003EHow long visitors wait, both for any answer and for a person.\u003C/p\u003E\u003Cfigure\u003E\u003Cimg class=\u0022lazy-load\u0022 data-src=\u0022https://graffiti-auf7e6dwhxhcbwek.z03.azurefd.net/d8b744fc-2e70-4089-bb80-dd1d08f6c7b2/fc6490ac-7527-4f49-b06e-46f701280e85/images/f068e2266eff4f52ad7d5ae94c67665a.png?v=-1550750502\u0022 data-width=\u0022986\u0022 data-height=\u00221349\u0022 style=\u0022max-width: 100%;\u0022 alt=\u0022Speed tab with first answer, first response, reply time and close time, the share of handoffs answered within 1, 5, 15 and 60 minutes, and missed handoffs\u0022/\u003E\u003Cfigcaption\u003EThe Speed tab\u003C/figcaption\u003E\u003C/figure\u003E\u003Ctable border=\u00221\u0022 style=\u0022border-collapse: collapse; width: 100%;\u0022\u003E\u003Cthead\u003E\u003Ctr\u003E\u003Cth\u003EFigure\u003C/th\u003E\u003Cth\u003EWhat it means\u003C/th\u003E\u003C/tr\u003E\u003C/thead\u003E\u003Ctr\u003E\u003Ctd\u003EFirst answer\u003C/td\u003E\u003Ctd\u003ETime from the visitor\u0027s first message to the first answer from the AI or a person\u003C/td\u003E\u003C/tr\u003E\u003Ctr\u003E\u003Ctd\u003EFirst response after handoff\u003C/td\u003E\u003Ctd\u003ETime from the handoff to the first reply from a person, and how many handoffs were answered\u003C/td\u003E\u003C/tr\u003E\u003Ctr\u003E\u003Ctd\u003E\u2026within support hours\u003C/td\u003E\u003Ctd\u003EThe same, counting only the time you were open. A handoff on Friday evening that\u0027s answered on Monday morning counts only the minutes after opening, and a reply sent before opening counts as zero. Shown when support hours are on.\u003C/td\u003E\u003C/tr\u003E\u003Ctr\u003E\u003Ctd\u003EReply time\u003C/td\u003E\u003Ctd\u003EHow long visitors waited for each answer from a person\u003C/td\u003E\u003C/tr\u003E\u003Ctr\u003E\u003Ctd\u003ETime spent per conversation\u003C/td\u003E\u003Ctd\u003EAn estimate of a teammate\u0027s time: a minute for each message from your team, plus the time between them, up to 10 minutes per gap\u003C/td\u003E\u003C/tr\u003E\u003Ctr\u003E\u003Ctd\u003ETime to close\u003C/td\u003E\u003Ctd\u003EStart to close for conversations a person handled, and for ones the AI resolved\u003C/td\u003E\u003C/tr\u003E\u003Ctr\u003E\u003Ctd\u003EResolved in one reply\u003C/td\u003E\u003Ctd\u003EOf the closed conversations a person handled, the share closed after one reply from your team. Several messages in a row count as one reply.\u003C/td\u003E\u003C/tr\u003E\u003Ctr\u003E\u003Ctd\u003EMissed handoffs\u003C/td\u003E\u003Ctd\u003EConversations handed to your team that got no reply from a person within an hour\u003C/td\u003E\u003C/tr\u003E\u003C/table\u003E\u003Cp\u003E\u003Cb\u003EHow quickly people were answered after a handoff\u003C/b\u003E shows the share of handoffs answered within 1, 5, 15 and 60 minutes, how the response times were spread, and the median by the hour of the handoff. It shows you the hours when visitors wait longest.\u003C/p\u003E\u003Cp\u003E\u003Cb\u003EMissed handoffs\u003C/b\u003E lists the most recent ones, with the reason for the handoff, whether it happened during or outside support hours, and whether the visitor left an email. Click \u003Cb\u003EOpen\u003C/b\u003E to go to the conversation and follow up.\u003C/p\u003E\u003Ch2 id=\u0022quality\u0022\u003EQuality\u003C/h2\u003E\u003Cp\u003EVisitors can rate a conversation when it closes. CSAT is the share of ratings that were 4 or 5 out of 5.\u003C/p\u003E\u003Cfigure\u003E\u003Cimg class=\u0022lazy-load\u0022 data-src=\u0022https://graffiti-auf7e6dwhxhcbwek.z03.azurefd.net/d8b744fc-2e70-4089-bb80-dd1d08f6c7b2/fc6490ac-7527-4f49-b06e-46f701280e85/images/cb3df52c5ad848bbb1e8e533dc3ca09f.png?v=-1553448621\u0022 data-width=\u0022986\u0022 data-height=\u0022988\u0022 style=\u0022max-width: 100%;\u0022 alt=\u0022Quality tab with CSAT overall, for the AI and with a person, rating response rate, came back within 24 hours, the ratings spread and low ratings to review\u0022/\u003E\u003Cfigcaption\u003EThe Quality tab\u003C/figcaption\u003E\u003C/figure\u003E\u003Ctable border=\u00221\u0022 style=\u0022border-collapse: collapse; width: 100%;\u0022\u003E\u003Cthead\u003E\u003Ctr\u003E\u003Cth\u003EFigure\u003C/th\u003E\u003Cth\u003EWhat it means\u003C/th\u003E\u003C/tr\u003E\u003C/thead\u003E\u003Ctr\u003E\u003Ctd\u003ECSAT\u003C/td\u003E\u003Ctd\u003EAll ratings in the period\u003C/td\u003E\u003C/tr\u003E\u003Ctr\u003E\u003Ctd\u003ECSAT: AI only\u003C/td\u003E\u003Ctd\u003EConversations no person took part in\u003C/td\u003E\u003C/tr\u003E\u003Ctr\u003E\u003Ctd\u003ECSAT: with a person\u003C/td\u003E\u003Ctd\u003EConversations a teammate handled\u003C/td\u003E\u003C/tr\u003E\u003Ctr\u003E\u003Ctd\u003ERating response rate\u003C/td\u003E\u003Ctd\u003EThe share of closed conversations that were rated\u003C/td\u003E\u003C/tr\u003E\u003Ctr\u003E\u003Ctd\u003ECame back within 24h\u003C/td\u003E\u003Ctd\u003EThe share of closed conversations where the same visitor started a new one within 24 hours, with the figure for 72 hours underneath. A high rate suggests problems that only looked solved.\u003C/td\u003E\u003C/tr\u003E\u003Ctr\u003E\u003Ctd\u003ERatings\u003C/td\u003E\u003Ctd\u003EHow many ratings of each star there were\u003C/td\u003E\u003C/tr\u003E\u003Ctr\u003E\u003Ctd\u003ELow ratings to review\u003C/td\u003E\u003Ctd\u003EThe latest 1 and 2 star ratings, with the comment, who handled the conversation, and a link to open it\u003C/td\u003E\u003C/tr\u003E\u003C/table\u003E\u003Ch2 id=\u0022ai_agent\u0022\u003EAI agent\u003C/h2\u003E\u003Cp\u003EHow the \u003Ca href=\u0022/article/configuring-the-chat-ai-agent\u0022\u003EAI agent\u003C/a\u003E is doing, what it costs, and where your content can help it do better.\u003C/p\u003E\u003Cfigure\u003E\u003Cimg class=\u0022lazy-load\u0022 data-src=\u0022https://graffiti-auf7e6dwhxhcbwek.z03.azurefd.net/d8b744fc-2e70-4089-bb80-dd1d08f6c7b2/fc6490ac-7527-4f49-b06e-46f701280e85/images/33c10c463977411c9f362bc7e2698f1f.png?v=-1530837862\u0022 data-width=\u0022986\u0022 data-height=\u00221398\u0022 style=\u0022max-width: 100%;\u0022 alt=\u0022AI agent tab with involvement, resolution, automation and answer rates, time saved, AI cost, handoff reasons, articles the AI answered from and actions\u0022/\u003E\u003Cfigcaption\u003EThe AI agent tab\u003C/figcaption\u003E\u003C/figure\u003E\u003Ctable border=\u00221\u0022 style=\u0022border-collapse: collapse; width: 100%;\u0022\u003E\u003Cthead\u003E\u003Ctr\u003E\u003Cth\u003EFigure\u003C/th\u003E\u003Cth\u003EWhat it means\u003C/th\u003E\u003C/tr\u003E\u003C/thead\u003E\u003Ctr\u003E\u003Ctd\u003EAI involvement\u003C/td\u003E\u003Ctd\u003EThe share of conversations the AI answered in\u003C/td\u003E\u003C/tr\u003E\u003Ctr\u003E\u003Ctd\u003EAI resolution rate\u003C/td\u003E\u003Ctd\u003EOf those, the share the AI resolved without a person\u003C/td\u003E\u003C/tr\u003E\u003Ctr\u003E\u003Ctd\u003EAutomation rate\u003C/td\u003E\u003Ctd\u003EThe share of all conversations the AI resolved on its own. It\u0027s the involvement multiplied by the resolution rate.\u003C/td\u003E\u003C/tr\u003E\u003Ctr\u003E\u003Ctd\u003EHanded to the team\u003C/td\u003E\u003Ctd\u003EOf the conversations the AI answered in, the share later handed to a person\u003C/td\u003E\u003C/tr\u003E\u003Ctr\u003E\u003Ctd\u003EAnswer rate\u003C/td\u003E\u003Ctd\u003EThe share of the AI\u0027s answers where it found the answer in your content\u003C/td\u003E\u003C/tr\u003E\u003Ctr\u003E\u003Ctd\u003ETeammate time saved\u003C/td\u003E\u003Ctd\u003EAn estimate: the AI\u0027s resolutions multiplied by the time a person usually spends on a conversation\u003C/td\u003E\u003C/tr\u003E\u003Ctr\u003E\u003Ctd\u003EAI cost\u003C/td\u003E\u003Ctd\u003EWhat the AI cost for chat in the period, and the cost per AI resolution\u003C/td\u003E\u003C/tr\u003E\u003C/table\u003E\u003Cul\u003E\u003Cli\u003E\u003Cb\u003EWhy conversations were handed to the team:\u003C/b\u003E the most common reasons, such as the visitor asking for a person, a \u003Ca href=\u0022/article/chat-question-rules\u0022\u003Equestion rule\u003C/a\u003E, or the AI not finding an answer.\u003C/li\u003E\u003Cli\u003E\u003Cb\u003EArticles the AI answered from:\u003C/b\u003E each article the AI cited, in how many conversations, and how those conversations went. An article that\u0027s cited often but rarely resolves the question is worth improving.\u003C/li\u003E\u003Cli\u003E\u003Cb\u003EActions:\u003C/b\u003E each \u003Ca href=\u0022/article/chat-actions\u0022\u003Eaction\u003C/a\u003E the AI called, how many times, the share of calls that succeeded, and the median time each call took. This only appears when the AI has called an action.\u003C/li\u003E\u003C/ul\u003E\u003Ch3 id=\u0022topics\u0022\u003ETopics\u003C/h3\u003E\u003Cp\u003E\u003Cb\u003ETopics\u003C/b\u003E shows what visitors come to the messenger about. Click \u003Cb\u003EAnalyze topics\u003C/b\u003E: the AI takes the opening question of each conversation in the period (up to 400) and groups them into topics, such as \u003Ci\u003EPassword Reset\u003C/i\u003E, \u003Ci\u003EPricing\u003C/i\u003E or \u003Ci\u003ECancel Account\u003C/i\u003E. It takes a few seconds. For each topic you see:\u003C/p\u003E\u003Cul\u003E\u003Cli\u003E\u003Cb\u003EConversations:\u003C/b\u003E how many, and their share of the total;\u003C/li\u003E\u003Cli\u003E\u003Cb\u003EAI resolved:\u003C/b\u003E the AI resolution rate for that topic;\u003C/li\u003E\u003Cli\u003E\u003Cb\u003EEscalated:\u003C/b\u003E the share handed to your team;\u003C/li\u003E\u003Cli\u003E\u003Cb\u003ERating:\u003C/b\u003E the average rating.\u003C/li\u003E\u003C/ul\u003E\u003Cfigure\u003E\u003Cimg class=\u0022lazy-load\u0022 data-src=\u0022https://graffiti-auf7e6dwhxhcbwek.z03.azurefd.net/d8b744fc-2e70-4089-bb80-dd1d08f6c7b2/fc6490ac-7527-4f49-b06e-46f701280e85/images/8e37ed4203664c72bf69d6f1cdfc9f6b.png?v=-179554871\u0022 data-width=\u00221186\u0022 data-height=\u0022587\u0022 style=\u0022max-width: 100%;\u0022 alt=\u0022Topics table listing topics such as Password and sign-in and Billing and refunds, with conversation counts, AI resolved, escalated and average rating\u0022/\u003E\u003Cfigcaption\u003ETopics\u003C/figcaption\u003E\u003C/figure\u003E\u003Cp\u003EClick a topic to see example questions, each linking to its conversation. A topic with a low resolution rate or a high escalation rate is worth a new article, a \u003Ca href=\u0022/article/chat-question-rules\u0022\u003Equestion rule\u003C/a\u003E or an \u003Ca href=\u0022/article/chat-actions\u0022\u003Eaction\u003C/a\u003E.\u003C/p\u003E\u003Cp\u003EEach period\u0027s analysis is saved until you click \u003Cb\u003ERefresh\u003C/b\u003E, so it doesn\u0027t change on its own as new conversations come in.\u003C/p\u003E\u003Ch3 id=\u0022questions_the_ai_couldnt_answer\u0022\u003EQuestions the AI couldn\u0027t answer\u003C/h3\u003E\u003Cp\u003EThis list shows the visitor\u0027s exact words each time the AI couldn\u0027t find an answer in your articles. Each one is a gap in your documentation. Write an article that answers it, publish it, and the AI can resolve that question next time. Click \u003Cb\u003EOpen\u003C/b\u003E to read the whole conversation. Click \u003Cb\u003EDismiss\u003C/b\u003E to remove a question you won\u0027t write an article for, such as spam, something off-topic, or a question you\u0027ve already covered. Dismissing only takes it off this list; the conversation is kept.\u003C/p\u003E\u003Cfigure\u003E\u003Cimg class=\u0022lazy-load\u0022 data-src=\u0022https://graffiti-auf7e6dwhxhcbwek.z03.azurefd.net/d8b744fc-2e70-4089-bb80-dd1d08f6c7b2/fc6490ac-7527-4f49-b06e-46f701280e85/images/8a02b2b76df3452ebb16ea757c675721.png?v=1923104863\u0022 data-width=\u00221186\u0022 data-height=\u0022464\u0022 style=\u0022max-width: 100%;\u0022 alt=\u0022Questions the AI could not answer, each with Open and Dismiss\u0022/\u003E\u003Cfigcaption\u003EQuestions the AI could not answer\u003C/figcaption\u003E\u003C/figure\u003E\u003Ch2 id=\u0022team\u0022\u003ETeam\u003C/h2\u003E\u003Cp\u003E\u003Cb\u003ETeammates\u003C/b\u003E lists everyone who replied to visitors in the period, with their conversations, replies, internal notes, first responses and the median \u003Cb\u003EFirst response\u003C/b\u003E after a handoff, their \u003Cb\u003EReply time\u003C/b\u003E, their CSAT, and \u003Cb\u003EMost at once\u003C/b\u003E: the most conversations they replied in within one hour. When you have more than one team, \u003Cb\u003ETeams\u003C/b\u003E shows conversations, handoffs, first response and CSAT for each.\u003C/p\u003E\u003Cfigure\u003E\u003Cimg class=\u0022lazy-load\u0022 data-src=\u0022https://graffiti-auf7e6dwhxhcbwek.z03.azurefd.net/d8b744fc-2e70-4089-bb80-dd1d08f6c7b2/fc6490ac-7527-4f49-b06e-46f701280e85/images/9e77134e3db14505b5c41fc01af0308c.png?v=-1538424771\u0022 data-width=\u0022986\u0022 data-height=\u0022715\u0022 style=\u0022max-width: 100%;\u0022 alt=\u0022Team tab with a table of teammates and a table of teams\u0022/\u003E\u003Cfigcaption\u003EThe Team tab\u003C/figcaption\u003E\u003C/figure\u003E\u003Ch2 id=\u0022sources\u0022\u003ESources\u003C/h2\u003E\u003Cp\u003EWhere conversations start and who starts them.\u003C/p\u003E\u003Cfigure\u003E\u003Cimg class=\u0022lazy-load\u0022 data-src=\u0022https://graffiti-auf7e6dwhxhcbwek.z03.azurefd.net/d8b744fc-2e70-4089-bb80-dd1d08f6c7b2/fc6490ac-7527-4f49-b06e-46f701280e85/images/9fcc10cf13944b05a0ccef312a1a592b.png?v=-1540765134\u0022 data-width=\u0022986\u0022 data-height=\u00221263\u0022 style=\u0022max-width: 100%;\u0022 alt=\u0022Sources tab with pages where conversations start, proactive messages, and visitors by country, device and type\u0022/\u003E\u003Cfigcaption\u003EThe Sources tab\u003C/figcaption\u003E\u003C/figure\u003E\u003Cul\u003E\u003Cli\u003E\u003Cb\u003EPages where conversations start:\u003C/b\u003E with the AI resolution and handoff rates for each page. A high handoff rate or low AI resolution on a page usually means it leaves visitors with a question your help content doesn\u0027t answer.\u003C/li\u003E\u003Cli\u003E\u003Cb\u003EProactive messages:\u003C/b\u003E conversations that began as a reply to each of your \u003Ca href=\u0022/article/chat-proactive-messages\u0022\u003Eproactive messages\u003C/a\u003E, and how they went.\u003C/li\u003E\u003Cli\u003E\u003Cb\u003EWho\u0027s asking:\u003C/b\u003E visitors by country (worked out from their time zone), by device, and by type: verified customers, identified but not verified, and anonymous.\u003C/li\u003E\u003Cli\u003E\u003Cb\u003EStarted by your team:\u003C/b\u003E conversations a teammate started from \u003Cb\u003EVisitors online\u003C/b\u003E.\u003C/li\u003E\u003Cli\u003E\u003Cb\u003EFollow-up form:\u003C/b\u003E how often visitors who were offered the name and email form left their email.\u003C/li\u003E\u003C/ul\u003E\u003Cp\u003EFor article-level insights, such as most-viewed and least-helpful articles, see the \u003Ca href=\u0022/article/dashboard\u0022\u003EDashboard\u003C/a\u003E. To make the AI search the right content, see \u003Ca href=\u0022/article/chat-knowledge-sources\u0022\u003EChat Knowledge Sources\u003C/a\u003E.\u003C/p\u003E","publish_status":0,"post_type":"Article","authoruid":"3dde8c16-763a-4a2b-ae0b-1d8c50c62e3d","author":{"authoruid":"3dde8c16-763a-4a2b-ae0b-1d8c50c62e3d"},"featured_image_updating":false,"meta_description":"Chat reports track AI resolution, team response times, visitor ratings, and unanswered questions to improve support with detailed metrics and insights.","display_toc":true,"has_workingcopy":false,"allow_indexing":true,"sort_order":14,"total_views":4,"date_published":"2026-09-26T16:45:00","date_updated":"2026-10-20T17:59:12.943","date_created":"2026-09-26T16:30:46.1"}}}