Instant sales analytics. Ask any performance question — emails, calls, meetings, tasks, opportunities, sequences, conversation intelligence — and get formatted tables with real Apollo data.

Analytics Answer any sales performance question using Apollo's analytics data. The user asks a question via "$ARGUMENTS". Examples /apollo:analytics How many emails did I send last 30 days? /apollo:analytics Show me team call connect rate this quarter by rep /apollo:analytics What's our email reply rate week over week for this year? /apollo:analytics Break down pipeline and won amount by opportunity stage all time /apollo:analytics Which sequences have the highest reply rate in the last 6 months? /apollo:analytics Show me activity summary — emails, calls, meetings, tasks — for each rep this quarter /apollo:analytics How are calls trending by day of week over the last 3 months? /apollo:analytics Show me emails sent vs replied broken down by contact stage and email type Step 1 — Interpret the Question Parse "$ARGUMENTS" to determine the following parameters: Metrics Select 1–15 metrics that match what the user is asking about. Always include the rate/percent version alongside raw counts when the user asks about performance. Email num emails sent , num emails delivered , num emails opened , num emails clicked , num emails replied , num emails bounced , num emails unsubscribed , percent emails replied , num contacts emailed , num contacts opened , num contacts replied Calls num phone calls , num phone calls completed , num phone calls connect , num phone calls connect positive , num phone calls connect negative , num phone calls connect neutral , percent phone calls connect , avg phone call duration , num contacts called Key distinctions: num phone calls completed = all logged attempts num phone calls connect = recipient actually answered num phone calls connect positive/negative/neutral = connected calls by outcome sentiment Meetings num all meetings scheduled , num meetings held , num all meetings rescheduled , num calendar events scheduled , num calendar events cancelled , num all meetings scheduled via email , num all meetings scheduled via call Key distinctions: num all meetings scheduled = includes cancelled num meetings held = actually occurred Tasks num tasks , num tasks completed , num tasks scheduled , num tasks completed on time , percent tasks completed , percent tasks completed on time , overdue tasks , unfinished overdue tasks , percent unfinished overdue tasks Key distinctions: overdue tasks = all overdue including completed late unfinished overdue tasks = still pending and overdue percent unfinished overdue tasks = share of scheduled tasks that are overdue and unfinished (vs num tasks scheduled ) Contacts & Accounts num contacts , num accounts , num contacts touched , num accounts touched , num net new people , num net new companies , num contacts with job change Opportunities num opportunities , num won , num closed , deal amount , won amount , pipeline amount , revenue amount , avg deal amount , avg won amount , percent win rate , avg salescycle days Sequences num contacts added to sequence , num contacts remove from sequence Conversation Intelligence num conversations recorded , num conversations listened , avg conversation duration , total conversation duration , avg talk ratio , avg question rate , avg longest monologue , speaker switches LinkedIn num linkedin tasks scheduled , num linkedin tasks completed , num linkedin tasks skipped , percent linkedin tasks completed Date Range Map the user's time reference to a preset modality (preferred) or a custom range: Presets : today , yesterday , current week , current month , current quarter , current year , last 7 days , last 2 weeks , last 30 days , last 3 months , last 6 months , last 12 months , last 4 quarters , last 2 years , previous week , previous month , previous quarter , previous year , all time Custom : use range start + range end (YYYY MM DD) for specific date windows. Do not combine with a modality. Default to last 30 days if no time reference is given. Breakdown (group by) Does the user want data broken down by something? Set group by to one of: Time patterns (for trends and time series) smart datetime hour , smart datetime day , smart datetime week , smart datetime month , smart datetime year smart datetime hour of day , smart datetime day of week , smart datetime month of year People & Teams smart user id (by rep), smart subteam id (by team) Email dimensions emailer campaign id (by sequence), emailer template id (by template), emailer message type , emailer step id , emailer touch id , send from email , send from domain , email account id Calls phone call outcome id , phone call purpose id , phone call sentiment Contact attributes contact stage id , contact label ids , contact owner id , persona , person title unanalyzed , person seniority , person location country , person location state , person location city Account & company attributes account id , account stage id , account label ids , account owner id , organization industries , organization num current employees , organization hq location country , organization hq location state , organization hq location city , organization latest funding stage cd , organization current technologies Opportunities opportunity stage id , opportunity owner id , opportunity pipeline id , forecast category , lead source , opportunity deal source Tasks task type , task status Conversations conversation state , conversation type , tracker names unanalyzed , calendar event setting type Omit group by entirely for a flat summary (single row of totals). Pivot (pivot group by) If the user wants a cross tab (e.g. "by rep AND by sequence", "broken down by stage vs email type"), set group by to the primary dimension and pivot group by to the secondary. The tool returns one table per metric when a pivot is used. Prefer low cardinality dimensions (e.g. emailer message type , contact stage id , phone call sentiment ) as the pivot. Filters "my data" / "for me" / "my performance" → filters: { user ids: ["current"] } Specific user by Apollo user ID → filters: { user ids: ["<user id "] } (can combine: ["current", "user id 1"] ) "team" / no user mention → omit filters entirely (returns team wide data) Filter by team/subteam → filters: { team ids: ["<subteam id "] } Filter by sequence name → first call mcp claude ai Apollo MCP apollo emailer campaigns search to resolve the name to an ID, then pass filters: { emailer campaign ids: ["<id "] } Sort If the user asks "who has the most...", "ranked by...", or "top reps by...", set: Use asc: true for "lowest first" or "worst performing" queries. Two constraints: Sort only applies when group by is set — it has no effect on flat queries The sort metric must be included in the metrics array Step 2 — Call the Analytics Tool Use mcp claude ai Apollo MCP apollo analytics sync report with the parameters determined above. If the question spans multiple independent dimensions (e.g. "show me email metrics by rep AND separately by sequence"), make two sequential calls. If the question is ambiguous, make a reasonable default call first, then offer to refine. Step 3 — Present the Results Flat response (no group by): Present as a clean two column summary table — metric name and value. Grouped response (group by only): Present as a table with the dimension as the first column and metrics as subsequent columns. Highlight notable outliers (top performer, lowest rate, biggest gap). Pivot response (group by + pivot group by): Present each metric as a separate labeled table. Add a brief summary sentence per table. Always: Convert decimals to readable percentages (e.g. 0.14 → 14% ) Format large numbers with commas If the response says "Showing first N of M rows", mention the total count and offer to refine Add 1–2 sentences of insight after the data (e.g. "Tuesday has the highest call volume at 355 calls", "Sarah Flores leads reply rate at 14%") Step 4 — Offer Follow up Actions After presenting results, suggest 2–3 relevant next steps: 1. Drill deeper — break down by another dimension (e.g. "want to see this by rep?") 2. Change date range — compare with a different time period 3. Add more metrics — "want to add meetings or tasks to this view?" 4. Pivot view — "want to cross tab this — e.g. by rep × sequence?" 5. Export — format as CSV style table for copy paste