100+ ready-to-use AI prompts for sales and CRM work

Show all my open deals (responsible manager — [Manager name]). For each, show: company name, pipeline stage, deal value, date of last activity, whether a next step exists and its deadline. Based on this data, identify the top 3 deals to focus on this week — with reasoning for each.

Find the most recent objection from the customer in the deal history with [Company name]. Explain what might be behind it, what data is already in the CRM, what data is missing, and suggest three response options — no pressure, no invented promises.

Find open deals where the customer hasn't responded for more than [X] days since the manager's last contact. For each: - briefly summarize the context - identify a possible reason for the silence based only on the history - suggest a relevant reason to reach out again - prepare a short message that doesn't open with "just following up"

Check the [Contacts / Companies] folder for duplicates. The primary field for finding matches is [choose one: email address / phone number / company name]. Show suspicious pairs or groups of records with the same or very similar value in that field. For each pair, show: the matching field value, the names of both records, the creation date, the responsible manager — so I can decide which record to keep and which to delete or merge.

Find my open deals at the [On hold / Paused] stage where the planned return date has already passed or no specific date was recorded. For each deal: - briefly summarize why it was put on hold - show the last agreement with the customer - identify whether the timing is right to restart the conversation - suggest a specific reason to reach out - prepare a short message to the customer based on the deal context If it's too early to re-engage, suggest a date for the next contact and a task. Don't invent new reasons or changes in the customer's situation that aren't in the CRM.

I'm preparing for a meeting with [Manager name]. Analyze their work over the last [X weeks / month] across the following: - Results: number of deals created and closed, total value of closed deals, conversion rate (closed / created). - Activity and initiative: number of activities in the activity log (calls, emails, meetings). For each deal — who initiates contact more often: the manager or the customer? How many deals have the last step belonging to the customer, with no follow-up from the manager yet? - Deal quality: deals with no activity for more than [X] days, deals with no recorded next step, overdue tasks. Are there deals where the manager responds when contacted but doesn't drive the deal forward themselves? Based on this, identify 2–3 strengths and 2–3 areas for improvement with specific examples from deals.

Prepare materials for the weekly sales team meeting for the period [from date] to [date]. Analyze the data in the [Folder name] folder and put together a structured report. **1. Results for the week** Show: - number and value of won deals - number and value of lost deals - number of new deals - average deal value - number of deals that moved to the next stage - progress against the weekly or monthly target - change vs. the previous week **2. Current pipeline** For each stage, show: - number of open deals - total value - average time at this stage - deals stuck longer than [X] days - deals with no activity or next step **3. At-risk deals** Find deals showing one or more signals: - no activity for more than [X] days - an overdue task - the expected close date has passed - the close date has been moved multiple times For each, show the manager, value, stage, and risk signal. **4. Forecast** Show: - the total value of deals managers expect to close by end of [month / quarter] - the realistic total based on stage, activity, and next steps - the large deals that matter most for hitting the target **5. Results by manager** For each manager, show: - won and lost deals - total value of won deals - new deals - active deals - deals without a next step - overdue tasks - forecast to end of period - one key positive change - one main risk or issue Format the output as a short meeting brief: key numbers first, then issues, questions for managers, and decisions. Highlight only what needs to be discussed or acted on.

Find records in the [Deals / Contacts / Companies] folder where the following required fields are not filled in: [field 1], [field 2], [field 3]. Show a list: record name, responsible manager, which fields are empty. Group by manager.

Analyze the work of sales managers in the [Folder name] folder over the last [X weeks / months] and identify who is consistently failing to keep CRM data up to date. For each manager, check: Data completeness: - share of deals where fields [Field 1], [Field 2], [Field 3] are not filled in - deals without a value or expected close date - deals without a linked company or contact - deals without a recorded need, decision-maker, or reason for loss Data freshness: - open deals with a past expected close date - deals stuck at the same stage for more than [X] days - records not updated in more than [X] days Next steps: - deals without an open task - overdue tasks For each manager, show: - number of open deals checked - number and share of deals with each type of issue - overall share of outdated or incomplete records - three specific examples of deals with the most critical issues - change vs. the previous equivalent period Divide managers into three groups: - CRM is maintained consistently - Some issues that need fixing - Data is consistently not updated, distorting oversight and forecasting Don't evaluate managers on activity volume alone. Account for their portfolio size and number of assigned deals.

Find all active deals in the [Folder name] folder with no open task. For each deal, show: - company - responsible manager - stage - deal value - date of last activity - last agreement with the customer Based on the stage and communication history, suggest the next task, the responsible manager, and a recommended deadline. Output as a table. Don't create tasks yet — show the list first and wait for my confirmation. After approval, create the selected tasks.

Show the current state of the sales pipeline across all open deals. Analyze at three levels: 1. Overall picture by stage: for each stage — number of deals, total value, average deal age at this stage vs. the normal cycle [specify the norm, e.g. 7 days at this stage]. 2. At-risk deals: highlight deals stuck at the same stage for more than [X] days, deals with no activity for more than [Y] days, deals with no recorded next step. For each — responsible manager and date of last contact. 3. Forecast: what is the total realistic value that could close by end of [month / quarter], accounting for stage and activity level? Which deals are most at risk of falling through?

Analyze deals created over the last [X months] and compare them against the sales target for the next [X months]. Show: how many new deals are being created each month; their total value; average conversion to won deal; whether the current flow is enough to hit the upcoming target. Summarize where a pipeline shortfall might emerge and when it would affect results.

Find open deals where the expected close date has changed more than [X] times or been pushed back by more than [Y] days in total. Show the change history, manager, value, stage, and last activity.

Find deals created in the last [X] days with no meaningful manager activity: no call, personal email, message, or note. Show: - company - creation date - source - value - responsible manager - how long the deal has been sitting without action Group results by manager and highlight deals that need immediate attention.

Compare the number of active deals, tasks, overdue tasks, and activities across managers. Identify managers whose workload is significantly above the team median, and show which deals could be redistributed.

Find deals that moved past the [stage name] stage but are missing key qualification criteria: [need], [budget], [timeline], [decision-maker]. Compare the share of such deals by manager and their downstream conversion rate.

Analyze open deals in the [Folder name] folder. For each stage, show the average time deals spend there and compare it to the norm of [X days]. Highlight the stages where deals take the longest.

Find open deals where the [Expected close date] field is not filled in. Output a table: deal, manager, value, stage, and date of last activity.

Find deals that were moved back to an earlier pipeline stage in the last [X months]. Show the deal, manager, value, previous and new stage, and date of the change.

Analyze won deals over the last [X months]. For each manager, show the number of won deals and average cycle from creation to close. Don't compare managers without accounting for deal volume.

Analyze the top [X] won deals with the shortest cycle over the last [X months]. For each, show: - company and segment - manager - value - lead source - deal length - number of activities before closing - number of contacts involved - key events that preceded moving to the next stage Compare these deals against the average metrics for all won deals in the same period. Summarize: - which characteristics appear most often in fast deals - which segments, sources, or managers close faster - which manager actions most often precede a fast close - which practices could be applied to other deals Don't claim that the identified factors caused the fast close. Show only repeating patterns in the data.

Find open deals where there have been more than [number] activities in the last [X] days but the stage hasn't changed. Show: - deal and manager - value and current stage - number of activities - time at current stage - last agreement - whether a next step exists Identify the likely reason for the stall based on the deal history and suggest one specific action to move it forward.

Compare won and lost deals over the last [X months]. Find behavioral signals that appear more often in won deals: customer response speed, number of contacts involved, whether a meeting took place, communication regularity. Don't claim causality — show only statistical patterns in the available data.

For leads created during [period], calculate the time from record creation to the manager's first activity. Show the median, average, share of leads with no contact within [1 hour / 1 day], and conversion by response speed.

Analyze deals in the [Folder name] folder over the last [X months] where a discount was given. Find records where the [Discount] field is filled in, or where the final deal value differs from the initial amount (fields [Initial value] and [Final value]), or where timeline notes mention a discount, price negotiation, or reduced rate. Scale of discounts: total number of deals with a discount, their share of all deals for the period. Average discount as a percentage and in monetary terms. Total revenue lost to discounts. By manager: for each manager — how many deals included a discount, average discount size, largest discount given. Who discounts most often, who gives the largest discounts? Are there managers who close without discounts or with minimal ones? By segment: in which industries, company sizes, or acquisition channels are discounts most common? Are there segments where discounting has become the norm rather than the exception? Impact on results: compare deals with and without discounts — conversion rate in each group, average deal cycle, whether the discount actually helped close faster. Are there deals where a discount was given but the deal was still lost — meaning the discount had no effect on the outcome? Discount size vs. result: break discounted deals into groups — up to [5%], [5%–10%], over [10%]. What is the conversion rate and average deal value in each group? Is there a threshold beyond which discounts stop influencing the customer's decision? Summarize: are discounts a tool that genuinely helps close deals, or have they become a habit? Which managers or segments need attention, and is it worth revisiting the discount policy?

Analyze sales team results for [current month] and compare with [previous month] and [the same month last year], if data is available. Results: total value of closed deals, number of closed deals, average deal value, ratio of new to existing customers (expansion). Is the average deal value changing — is the team giving more discounts, or are different-sized customers coming in? Pipeline and conversion: number of new deals entering the pipeline for the month. Stage-by-stage conversion — how many deals moved from each stage to the next, where is the biggest drop-off. Overall lead-to-closed-deal conversion. Average deal cycle — is it getting shorter or longer compared to the previous month? Acquisition channels: group new deals and leads by [Lead source] field. For each channel — number of leads, number of deals, conversion rate, and total value. Which channel brought the highest-quality leads this month? Team activity: total number of activities across the team (calls, emails, meetings), average number of activities per closed deal. Is there a correlation between activity and result — who worked more and did it affect their revenue? Forecast for next month: what is the total value of deals currently in the pipeline, how many of them are realistically likely to close next month based on stage and activity? Summarize: where is there positive momentum, where is there a dip, and what most likely influenced the difference?

Find all deals with a "Lost" status over the last [X months]. For each, show: company name, manager, deal value, the stage at which it was lost, reason for loss (field "Reason for loss"), and date of last activity before closing. Then assess each loss reason — was it objective or controllable: - Objective reasons (outside the manager's control): budget cut, customer chose a competitor with a different fit, project frozen at the company level - Controllable reasons (the manager could have influenced the outcome): slow follow-up, no next step recorded, objection not addressed, customer went cold with no re-engagement To categorize, look at the activity history: if the last activity was more than [X] days before the deal was marked lost — that's a signal of a controllable reason. Summarize: what share of losses were potentially controllable, which managers appear most often in controllable losses, and at which stage are we most often losing deals?

Compare sales manager results for [month / quarter]. For each manager, show two sections: Results: number of closed deals, total value, conversion rate (closed / created), average deal value, average deal cycle. Activity: total number of activities (calls, emails, meetings), average number of activities per closed deal, number of deals where the manager initiated the last contact vs. deals where the customer made the last move. Highlight: who gets the best results with the fewest activities (efficiency), who puts in a lot of effort but closes little (quality or approach issue), who is below the team average on both results and activity.

Analyze open deals in [folder] over the last [X days]. Review communication history and compile a list of deals where: 1) the manager hasn't left a written note after a call or meeting; 2) no follow-up task is scheduled. Output as a table with manager names and company names.

Find open deals where manager involvement could help move things forward: - value exceeds [amount] - deal has been at the same stage for more than [X] days - there's a difficult objection - a senior contact from the customer's side is involved - the manager has failed to agree on a next step multiple times For each, explain the issue and suggest how the manager could help.

Find open deals that probably have no real potential left: - no activity for more than [X] days - expected close date has passed - no next step - customer has not responded multiple times - communication includes a refusal or indefinite postponement For each, show the facts and suggest: keep active, move to nurture, or close as lost. Don't change the status automatically.

Analyze successfully closed deals in the [Folder name] folder over the last [X months]. Group by [Industry / Company size / Country / Lead source]. For each segment, show: - number of deals and total value - average deal value and average cycle - average number of activities before closing (from activity history) - lead-to-closed-deal conversion, if lead data is available Then assess each segment's efficiency: calculate the ratio of average deal value to average cycle length and average number of activities. Which segment delivers the most revenue with the least team effort? Based on this, recommend: which segments to focus on next quarter, which to deprioritize or exit — with supporting numbers.

Find all deals with a "Lost" status in the [Folder name] folder over the last [X months]. Analyze across four dimensions: 1. Where in the pipeline we lose: at which stage deals are most often closed as lost, total value of losses at each stage. Is there a stage with disproportionately high drop-off? 2. Why we lose: group by "Reason for loss" field. Which reason is most common, which is most costly by total value of losses. Do certain reasons repeat for a specific manager or segment? 3. Could we have retained them: for each loss reason, assess — was it objective or controllable? Use activity history as a guide: if more than [X] days passed between the last activity and the deal being marked lost — the manager likely didn't follow through. What share of losses was potentially controllable? 4. Patterns by customer profile: are there common characteristics among lost deals by industry, company size, country, or lead source? Are we consistently losing in a specific segment — and if so, is the issue with managers, positioning, or pricing? Summarize: identify 2–3 specific changes worth making — to the sales process, to work with specific managers, or to the approach for a specific segment.

Analyze the team's active deals and each manager's workload. Consider: - number and total value of open deals - number of tasks and overdue tasks - deal stages and complexity - date of last activity - the manager's experience with similar customers or segments Identify overloaded managers and suggest which deals could be transferred to colleagues without significant risk of losing context. For each proposed transfer, show: - the deal and current manager - reason for the transfer - recommended new manager - why they're a good fit - what needs to be handed over along with the deal Don't reassign without my confirmation.

Analyze all leads in the [Folder name] folder created between [from date] and [to date]. Group by [Lead source] field. For each channel, show: - total number of leads and change vs. the previous equivalent period - number of qualified leads — those where [field name, e.g. "Qualification"] contains [e.g. "Qualified" / "MQL" / "SQL"] or where the deal reached [stage name] - how many leads converted to deals and their total value - overall conversion rate (all leads → deals) and conversion among qualified leads separately - average deal value and average deal cycle Then assess channel quality across two dimensions: - Volume vs. quality: which channel brings the most leads overall, but with a low share of qualified ones? Which channel brings fewer leads, but most of them are qualified and convert well? - Efficiency vs. effort: which channel offers the best combination of conversion rate and deal value with the shortest cycle? Summarize: which channels to scale, which to optimize (high volume, low quality — possibly a targeting or messaging issue), which to consider exiting — with supporting numbers.

In the [Folder name] folder, find all leads and deals where [Lead source / Campaign] contains [campaign name] for the period [from date] to [to date]. Campaign budget — [amount in currency]. Show the full campaign picture: - total number of leads and weekly trend — where was the peak, where was the drop - number of qualified leads — where [qualification field] contains [e.g. "Qualified" / "SQL"] or where the deal reached [stage name]. What share of total leads were qualified? - overall conversion (all leads → deals) and conversion among qualified leads separately - total value of closed deals, average deal value, average cycle from lead to close - cost per lead (budget / total leads), cost per qualified lead (budget / qualified leads), cost per closed customer (budget / closed deals) - campaign ROI: (total value of closed deals − budget) / budget × 100%. If there are still open deals in the pipeline — calculate current ROI and potential ROI separately, accounting for open deals - number of lost deals and the most common loss reasons (field "Reason for loss") — are there reasons that appear specifically for this campaign? Separately: compare this campaign's cost per lead and conversion with the average across other channels in the same period — was the campaign more or less effective than the alternatives? Summarize: did the campaign break even, and if not — how many deals from the current pipeline need to close to reach profitability? What worked, what didn't, and is it worth scaling or repeating with adjusted targeting or messaging?

Compare two campaigns: [Campaign A name] and [Campaign B name] for the period [from date] to [to date]. Find leads and deals for each in the [Folder name] folder. For each campaign, show: - number of leads, conversion to deals, total value, average deal value, average deal cycle - number of lost deals and top loss reasons - lead profile: which industry, company size, and country are most common among customers who closed successfully Then compare: which campaign had better conversion, which had a higher deal value, which had a shorter cycle. Is there a difference in customer profile between the two campaigns? Summarize: which campaign — or which elements from each — should form the basis for the next launch.

For [Campaign name], analyze disqualified and lost leads. Group the reasons: wrong industry, company size, geography, budget, no real need, wrong contact, wrong timing. Compare against the campaign's targeting and messaging.

Find lost or disqualified leads with the following reasons: - not now - no budget at the moment - project on hold - come back later Exclude anyone who explicitly opted out of communication. For the rest, show the company, reason, date of last contact, recommended re-engagement date, and a relevant topic for re-outreach.

Analyze won deals over the last [X months] and group by [Lead source] field. For each source, show: - number of won deals - total value - average and largest deal value - average sales cycle - the largest deals from this source Also highlight sources that brought few customers but large deals. Summarize which sources work best for attracting high-value customers. Don't assess cost efficiency if budget data isn't in the CRM.

Analyze lost deals over the last [X months] and group by [Lead source / Channel] field. For each channel, show: - number of lost deals - total value - share of lost deals among all deals from this channel - stages where deals were most often lost - most common loss reasons - customer segments where losses repeat most often Don't draw conclusions based on the number of lost deals alone — account for the total number of deals from each channel. Summarize where the problem is likely in lead quality, and where it may be in the subsequent work of the sales team.

Analyze all leads created in the [Folder name] folder between [from date] and [to date], grouped by [Lead source / Channel / Campaign]. For each lead, calculate the time from record creation to the manager's first meaningful activity: a field update, call, personal email, or message. Exclude automated emails and system changes. For each channel, show: - number of leads - average and median time to first contact - share of leads contacted within [1 hour] and [1 business day] - share of leads with no activity at all - conversion to deal and to won customer Compare how conversion changes depending on response speed. Summarize: - which channels are processed fastest and slowest - where slow response most often correlates with lower conversion - which channels or managers need attention - what first-contact SLA would be reasonable to set

Analyze lost deals over the last [X months] and find mentions of competitors or alternative solutions in notes and correspondence. Show: - which competitors were mentioned most often - how many deals and how much value was lost to each - what reasons customers gave for choosing the competitor - which segments this happens in most Summarize which messaging, positioning, or content gaps are worth investigating.

Find leads with [MQL / Qualified] status that sales disqualified or closed as lost. Analyze the reasons and group by: - channel and campaign - industry and company size - manager Show which reasons repeat most often and where MQL criteria don't match actual sales requirements. Summarize what should change in the MQL definition or qualification rules.

Find leads and deals created in the last [X months] where the [Lead source] field is not filled in. Output a table with: number and share of such records, responsible managers, deal value, and whether the source can be identified from UTM parameters, correspondence, form submissions, or activity history.

Analyze activity history and manager notes in won deals in the [Folder name] folder for the period [from date] to [to date]. Find mentions by leads and customers of ad campaigns, case studies, articles, webinars, videos, guides, and other marketing materials. Summarize: - top 5 materials and campaigns mentioned most often in won deals - the context in which they were mentioned - what data is missing for a more precise assessment Don't conclude that the content directly caused the sale. Show only the connection visible in the CRM.

Analyze closed won deals in the [Folder name] folder over the last [X months]. Group by [Industry] field. For each niche, show: - number of deals, total value, average deal value, average deal cycle - lead-to-closed-deal conversion - average number of activities before closing — how "heavy" is this niche for the team - trend vs. the previous equivalent period — is the niche growing or stagnating Separately: look at lost deals in each niche — what is the loss rate and what are the dominant loss reasons? Are there niches where we enter a lot but rarely close? Summarize: which 2–3 niches to prioritize next quarter based on potential, close speed, and available team capacity. Which niches to deprioritize and why.

Find all companies and deals in the [Folder name] folder where [Industry] field contains [niche name]. Analyze everything available about this segment in the CRM. Company profile: what is the typical size (field [Number of employees]), country, and contact job title? Who is most often the initiator in this niche — the owner, department head, or manager? Pain points and needs: what was mentioned in notes and correspondence as the main request or problem? Which topics came up most often during negotiations? Objections and barriers: what objections were recorded in notes, at which pipeline stages did progress most often stall, and what are the dominant loss reasons (field "Reason for loss"). Behavioral patterns: how many contacts are typically needed before a decision is made, what is the typical deal cycle, and which team members have been most successful closing deals in this niche? Summarize: what to keep in mind when entering this niche — what messaging resonates, which objections to prepare for, and what the target contact profile looks like.

Analyze successfully closed deals in the [segment name / industry] segment in the [Folder name] folder over the last [X months]. Review activity history for each deal — call notes, emails, manager comments. Step 1 — Customer language: Find direct quotes and phrases customers used to describe their problems and needs. How did they describe their pain — what words, what context? Which phrases repeat across multiple customers? What did they say about why they started looking for a solution now? Step 2 — What worked on our side: Which arguments, phrases, or angles from our side appear most often in deals that closed successfully? At what stage did customers most often decide to move forward — and what preceded that moment? Step 3 — Messaging based on real customer language: Using the phrases found, as close to the original as possible, write: - For LinkedIn: a short message of up to 3 sentences — open with the customer's pain in their own words, state the promise, add why now - For cold email: subject line and opening paragraph — no filler, the first sentence should be a recognizable pain for this segment, phrased the way customers actually talk about it - For ads: 2–3 headline and subheadline options — the headline uses the customer's pain or outcome in their own language, the subheadline gives a specific promise After each message, note which real CRM phrase it's based on. No generic phrasing — only what the data supports.

Analyze all deals with a "Closed / Won" status in the [Folder name] folder over the last [X months]. Find common characteristics across four dimensions: - Company profile: dominant industry, typical company size (field [Number of employees]), country, business type if a field exists. - Deal profile: average deal value, average cycle, typical lead source (field [Lead source]), average number of activities before closing. - Contact profile: which job title appears most often among decision-makers in closed deals — who actually makes the decision in this segment? - Behavioral patterns: at which stage does active customer interest most often emerge, how many contacts are needed before a decision, is there seasonality in closed deals? Summarize in ICP (Ideal Customer Profile) format: who this is, where to find them, how they behave in the pipeline, and what matters to them when making a decision.

I'm preparing for a renewal conversation with [Company name]. Find the customer in the [Folder name] folder and prepare a brief. Show: - length of relationship, current plan, and renewal date - the customer's initial goals and recorded outcomes - recent contacts, positive and negative feedback - unresolved issues or commitments we haven't fulfilled - churn risk signals - upsell or cross-sell opportunities Rate the churn risk as low, medium, or high and explain what data supports this. Prepare: - a brief summary of the customer's current state - key arguments for renewal - questions to ask at the meeting - issues that need to be addressed - a possible next step or expansion offer Don't invent value that isn't in the CRM. If customer outcomes haven't been recorded, flag that as a question for the meeting.

In the [Folder name] folder, find all customers where I am responsible — [Name] — and check the activity history for each. Identify records with no contact (email, call, meeting, note) in the last [X] days. For each customer, show: company name, date of last contact, type of last activity, current plan (field [field name]), start date, and upcoming renewal date if available (field [Renewal date]). Sort by longest time without contact. Separately highlight those with a renewal coming up within [X] days — they are the top priority.

Find [Company name] in the [Folder name] folder. Last contact was [X] days ago. Before writing — analyze the activity history: what was discussed on recent calls and in emails, what requests or issues the customer had, what remains unresolved or promised on our side, and what plan they're on and how long they've been a customer. Based on this, find a specific reason to reach out — not "just checking in," but something genuinely relevant to this customer: an unresolved issue, a natural follow-up to the previous conversation, a change in their profile, or an approaching renewal date. Write a short personalized email: subject line, 3–4 sentences in the body — open with a specific reason, not a generic phrase. Tone — warm, no pressure. Goal — restart the conversation and learn how things are going.

Find active customers whose renewal date falls within the next [X] days and who are missing important data: - renewal date - current plan or subscription terms - contract value - primary contact - decision-maker - recorded customer outcome - possible reason for non-renewal - next step For each customer, show which data is missing and where it might be found: in correspondence, notes, deals, or linked contacts.

Find my active customers where: - there is no open task - there is no specific agreed next action in correspondence or notes For each, briefly summarize the last communication and suggest an appropriate next step. Separately highlight customers with an upcoming renewal, unresolved issues, or an extended period without contact.

Analyze active customers in the [Folder name] folder. Find those who may be ready to expand based on the following criteria: Current profile: plan below [plan name], relationship length more than [X months], number of users or usage volume approaching the current plan limit (field [field name] if available). Behavioral signals: activity history includes mentions of team expansion, new processes or workflows, requests for features available on a higher plan, or positive product feedback. Activity: last contact was no more than [X] days ago — customer is engaged and reachable. For each customer, show: company name, current plan, relationship length, responsible manager, and the specific signal that makes this customer a upsell candidate. Sort by relationship length — longest first.

Find customers with a long relationship, positive feedback, repeat purchases or plan upgrades, and no unresolved issues. Create a list of candidates for a case study, testimonial, referral, or webinar participation — and explain the signal for each.

Show the full state of my customer portfolio (responsible manager — [Name]). For each customer, check activity history and show: date of last activity, type of last contact, number of open tasks, current plan, and renewal date if available. Group into three categories: - Active — contact within the last [30] days, open tasks or a planned next step - Quiet — [31]–[60] days without contact, but renewal not approaching - At risk — more than [60] days without contact, or renewal coming within [X] days with no contact in the last [Y] days For the "At risk" group — for each customer, show what the last point of contact was and whether there are any unresolved issues in the activity history. This is the priority list for the week.

Analyze two groups of customers in the [Folder name] folder over the last [X months]: - Group A — customers who renewed (field [Renewal date] is filled in or status changed to [renewal status name]) - Group B — customers who did not renew or churned (status [churn status name] or field [Reason for leaving] is filled in) Compare the two groups across four dimensions: Customer profile: industry, company size (field [Number of employees]), country, plan, relationship length at the time of renewal. Are there characteristics that appear more often among those who left? Activity and engagement: average number of activities in the timeline in the last [X months] before the renewal date, who initiated contact more often — the customer or us, average number of days between contacts. Is there a difference in activity patterns between the groups — for example, did those who left go quiet [X] days before the renewal date? Signals in activity history: which topics and phrases appear more often in notes and emails from customers who left — complaints, objections, unanswered requests, competitor comparisons. What is typical for those who renewed — positive feedback, expansion requests, team engagement? Team performance: time between last contact and renewal date in each group. Did customers who left receive any renewal communication — and if so, at what stage and how did they respond? Is there a difference by manager — who has a higher renewal rate? Summarize: which 3–5 signals most clearly distinguish a customer at risk of leaving from one who will stay. At what point do these signals typically appear — and how much time is there to respond? What can the CS team do differently to catch the risk in time.

Analyze customer notes, support interactions, and correspondence for [period]. Group recurring issues by theme, show the number of customers affected, their plan, segment, and resolution status. Separate one-off cases from systemic problems.

In the [Folder name] folder, find customers showing signs of churn risk. For each, check for a combination of signals: Low engagement signals: no contact for more than [X] days, no open tasks, no planned next step. Dissatisfaction signals: activity history includes notes or emails with complaints, negative feedback, or mentions of unresolved issues. Exit signals: renewal is approaching (field [Renewal date] — less than [X] days away) with no renewal conversation having taken place. For each customer, show: company name, which signals triggered, date of last contact, plan, relationship length. Sort by number of signals — highest risk first. Summarize: who needs urgent outreach this week and with what message — based on which signal is dominant.

In the [Folder name] folder, find all customers where [Renewal date] falls within the next [X] days. Sort by renewal date — soonest first. For each customer, show: company name, renewal date, current plan, responsible manager, date of last contact, and whether a renewal conversation has already started (look in activity history for mentions of renewal, contract, or agreement in the last [X] days). Group into two categories: - Already in conversation — renewal-related activity exists in the last [X] days - Not yet contacted — renewal is approaching, but no renewal conversation has started For the "Not yet contacted" group — show relationship length and current relationship status (date and type of last contact) for each customer. This is the priority outreach list for the week.

Analyze my customer portfolio and create a list of no more than [10] priorities for this week. Consider: - upcoming renewals - churn risk - unresolved issues - extended time without contact - upsell opportunity - unfulfilled commitments - scheduled check-ins For each customer, show the reason for prioritization and the next action.

I'm preparing for strategic negotiations with [Company name]. Find all information about this company in the [Folder name] folder and prepare a full overview. Relationship history: when they first entered the CRM, how the relationship developed — what deals were made, for how much, and what the trajectory has been from first contact to now. Current state: active deals or contracts, current plan or scope of engagement, open tasks, date of last contact, and who on our team manages this customer. Key moments from activity history: what was discussed at important meetings, what requests, objections, or unresolved issues there were. Were there any conflicts or difficult situations — and how were they resolved? Potential: are there open opportunities for expanding the relationship, and are there signals in the activity history about their plans or needs? Summarize: what is our current position with this customer and what's important to keep in mind going into the meeting.

Analyze the [Folder name] folder for data quality. For each key field — [field 1], [field 2], [field 3] — show what percentage of records are filled in, and which managers have the most empty fields. Also check: are there records with no activity in the activity log, duplicate companies or contacts (matches by email or name), deals without a responsible manager. Summarize: which data is least reliable right now and where it might be distorting analytics — for example, if [Lead source] is filled in for only [X]% of records, channel analysis will be inaccurate.

Provide a full summary of the business for [month / quarter / period from [date] to [date]]. Sales results: total value of closed deals, number of new customers, average deal value, number of lost deals and total value of losses. How does this compare to the target — if a [Target / Goal] field exists? Pipeline: how many new deals entered the pipeline, total current pipeline value, stage-by-stage conversion — where is the biggest drop-off? How many deals in the pipeline are realistically likely to close by end of [next month / quarter]? Channels: which sources brought the most leads and the highest value of closed deals (field [Lead source]). Team: who delivered the best results, who is underperforming and by how much. Compare with the previous equivalent period: where is there growth, where is there a decline — and what most likely caused the difference?

Prepare a short management report for the last week. Show only changes that require attention: new large deals, won and lost deals, forecast changes, pipeline risks, key customers at churn risk, overdue critical tasks, and significant changes in team results. For each item, suggest a management decision or question for the responsible person.

Calculate what share of total revenue for [period] comes from the top 5, top 10, and top 20 customers. Show the highest-contributing customers, their current status, last activity, and risks. Assess the risk of over-reliance on a small number of customers without using external benchmarks.

Compare results for [current quarter / year] vs. [previous equivalent period]. For each metric, show the absolute difference and percentage change. Sales: total value of closed deals, number of deals, average deal value, number of new customers. Separately — ratio of new customers to expansion of existing ones: where is growth stronger? Lead quality: total number of leads, number of qualified leads (field [qualification field] = [value]), share of qualified leads as a percentage of total. Has lead quality changed — are there more or fewer qualified leads relative to total volume? Pipeline conversion by stage: for each transition — how many deals entered the stage and how many moved to the next: - [Stage 1] → [Stage 2]: conversion rate and change vs. previous period - [Stage 2] → [Stage 3]: conversion rate and change - [last stage] → Closed / Won: conversion rate and change Where did stage-to-stage conversion drop the most — that's where we're losing more than before. Where did it increase — what worked? Overall conversion: lead to deal overall, and separately for qualified leads. Average deal cycle — is it getting shorter or longer? Number of lost deals and their share of total. Channels: which sources grew in lead volume, which declined. How did conversion and lead quality change by channel — a channel may bring more leads but lower quality. What share of each channel contributes to total closed deal value — did it change? Team: average revenue per manager, number of deals per manager, average deal value per manager. How did the average number of activities per closed deal change — is the team more efficient or putting in more effort for the same result? Summarize: which changes are systemic trends (repeating across multiple periods) and which are one-off deviations. Which three metrics most need a management decision, and why.

Find the open deals without which the team won't hit the target for [month / quarter]. For each, show: - value - share of target - stage - projected close date - last activity - main risk - alternative deals in the pipeline Show a base, optimistic, and risk scenario for target attainment.

Identify customers that make up the largest share of revenue and check their current status. For each, show: - share of total revenue - relationship length - renewal date - last activity - open issues - dependency on a single contact person - possible risk signals Don't use external benchmarks. Show the concentration and facts so the executive can assess the risk.

Analyze won deals in the [Folder name] folder over the last [X months] and group separately by: - industry - company size - country or region - lead source - product or plan - customer type: new or existing For each segment, show: - number of won deals - total value - average deal value - lead-to-won conversion rate - average sales cycle - average number of activities before closing - share and total value of lost deals - trend vs. the previous equivalent period If the CRM contains cost, acquisition, or service data, use it and calculate actual segment profitability. If such data is not available, don't call the output "profitability." Use "highest-performing segments based on available CRM data" and evaluate by the ratio of: - revenue - conversion rate - cycle length - number of activities - overall effort to serve the customer Highlight: - segments with the highest total revenue - segments with the highest average deal value - segments with the shortest cycle - segments requiring the fewest activities per won deal - the fastest-growing segments - segments that consume a lot of team effort but deliver weak results Summarize which 2–3 segments to focus on next quarter, which need further review, and which to deprioritize. For each recommendation, provide specific supporting numbers.

We're considering entering [Country / Region]. Before making a decision — analyze what's already in the CRM for this geography in the [Folder name] folders. What's already in the database: how many companies and contacts from this market are in the CRM, how they came to us — lead source, and who on the team has worked with them. Attempts and results: find all deals with companies from this market — closed won, lost, open. For each group, show number of deals, total value, average deal value, and average deal cycle. Why we lost: for lost deals from this market — at which stage they fell apart, what the loss reasons were (field "Reason for loss"), and what was mentioned in notes as a barrier. Are there patterns specific to this market — price, competitors, regulatory environment, decision-making culture? Profile of customers who bought: among closed won deals — which industry is dominant, typical company size (field [Number of employees]), contact job title, lead source, average cycle and deal value. How do they differ from our customers in other markets? Behavioral differences: compare deal cycle and number of activities before closing in this market vs. other geographies. Does it take more time and contacts to close a deal here? Summarize: what we already know about this market from our own data, which hypotheses the numbers support, which risks are already visible — and what needs to be validated further before committing to a full market entry.

Analyze all closed won deals in the [Folder name] folder over the last [X months]. Group by [Industry] field, then separately by [Company size] and [Country]. For each segment, show: number of deals, total value, average deal value, average deal cycle, lead-to-won conversion, average number of activities before closing. Identify the top 3 segments for each dimension: highest total value, highest average deal value, shortest cycle, least effort required. Is there a segment that leads across multiple dimensions? Compare with the previous equivalent period: which segments are growing, which are stagnating, which have appeared or disappeared. Summarize: which segments to focus on next quarter and why — with specific supporting numbers.

Analyze active customers in the [Folder name] folder over the last [X months]. The goal — find customers with the best ratio of revenue to team effort in servicing them. Revenue per customer: total value of closed deals or current plan, number of deals, whether there have been upsells or expansions. Effort to service: total number of activities from the activity log over [last X months] — calls, emails, meetings, notes. Number of support requests or complaints if recorded in the CRM (field [field name] or tags [tag name]). Number of team members involved — one manager or several. Efficiency calculation: for each customer, calculate: [total deal value] / [number of activities]. This is the implied "value per activity" — the higher the number, the more efficient the customer. Sort customers by this metric — most efficient first. Highlight the top 10. Profile of the most efficient customers: find common characteristics among the top 10 — industry, company size (field [Number of employees]), country, lead source, plan, relationship length. Are there patterns? Bottom of the list: separately show customers with low revenue but high activity and support volume — they consume the most team resources relative to results. Summarize: what customer profile is most valuable to the business when service costs are considered. Does it match who marketing is currently targeting — and if not, what should be adjusted?

Group all active customers in the [Folder name] folder by [Country] field, then by [Region] if available. For each location, show: number of customers, total deal value, average deal value, trend vs. the previous equivalent period. Identify: where we are strongest by customer count, and where by deal value and average deal size (these may be different markets). Which markets are growing, which are stagnating, and are there markets where we have a presence but results are disproportionately low relative to effort. Summarize: which markets to prioritize for growth, which to revisit our approach to, and whether there are geographies where we're underrepresented but the customer profile resembles our best markets.

Analyze the full pipeline in the [Folder name] folder over the last [X months]. Look at losses at each level: Pipeline losses: for each stage — how many deals entered, how many moved forward, how many were lost and for how much. Where is the biggest drop-off in monetary terms? Losses by reason: group lost deals by "Reason for loss" field. Which reason costs us the most — not by volume, but by total value of losses? Which of these are controllable (the manager could have influenced the outcome) and which are objective? Losses by segment: in which industries, company sizes, or acquisition channels is the loss rate disproportionately high? Are there segments we invest significant effort in but rarely close? Churn losses: how many customers didn't renew in the last [X months], what is the total value of lost contracts, and is there a pattern by plan or relationship length among those who left? Summarize: top 3 places where we lose the most money, and what management decision could reduce those losses.

Analyze the current workload and productivity of the sales team in the [Folder name] folder over the last [X months]. Workload: how many open deals and active customers does each manager have, total pipeline value per person, number of activities per week per manager. Productivity: average number of deals closed per manager per month, average revenue per manager, how these metrics have changed over the last [3–6] months — is there growth or a plateau? Capacity: who on the team is already at the limit (many deals, high activity, but no growth in results), who has capacity to take on more. If lead volume increases by [X]% — can the team handle it without a drop in quality? Summarize: is there real capacity to scale right now, or does the team need to be strengthened or processes optimized first? How many additional leads per month can the team handle without losing conversion?

Analyze closed deals in the [Folder name] folder by month over the last [2–3 years]. For each month, show: number of closed deals, total value, average deal value, and number of new leads entering the pipeline. Identify: are there months that are consistently strong or weak year over year? How significant is the difference between peak and low months in percentage terms? Check for seasonality by segment separately: is it the same across different industries or company sizes — or do different segments have different peaks? Summarize with practical takeaways: when to increase marketing activity and budget, when to focus on retaining existing customers, and how to distribute team workload to capture leads during peaks without carrying excess capacity through slow periods.

We're planning to add a CRM folder for a new team — [team name, e.g. Customer success / Partners / Support]. Recommend an optimal structure: Which fields to create for this team and why each matters — what does it enable for analytics or team workflows? Which fields should be required, which optional? Which statuses or stages are needed for this type of record? After I confirm the structure — create the [name] folder with the agreed fields and settings.

Check the [Contacts] and [Companies] folders for possible duplicates. For contacts, look for matches on: - same email address - same phone number - same or very similar first and last name - same linked company and job title For companies, look for matches on: - same or very similar name - same website domain - same phone number - same company registration number or other identifier, if that field exists in the CRM Don't treat records as duplicates based on a partial name match alone. For each suspicious pair or group, show: - record names - fields where a match was found - unique data in each record - creation date - date of last activity - responsible manager - number of linked deals and activities Rate the likelihood of duplication as high, medium, or low and explain the reasoning. Output as a table. Don't delete or merge records automatically. After the table, suggest which record to keep as the primary one — but wait for my confirmation before making any changes.

Analyze the fields in the [Folder name] folder over the last [X months]. For each field, check: - what share of records it's filled in for - when it was last updated - whether managers are using it - whether it's used in filters, reports, or automations - whether it duplicates another field Highlight: - fields that are rarely used - fields filled in inconsistently - duplicates - important fields with low completion rates Output as a table: field, usage level, issue, recommended action, and potential risk.

Check values in [Country], [Industry], [Lead source], [Job title], [Status], and [other fields] across the [Folder name] folders. Find values that mean the same thing but are entered differently: different capitalization, abbreviations, typos, different languages, or outdated names. For each group, show: - current variants - number of records with each variant - recommended standard value - how many records need to be updated - whether the change would affect filters, reports, or automations Separately flag: - values that can be safely standardized - borderline cases that need manual review - fields where a predefined list would work better than free text Prepare a mapping table: "current value → standard value." Don't update records without my confirmation.

Check the [Phone] and [Email] fields in the [Contacts / Companies] folders for records where contact data may be incorrect. For email addresses, check for: - missing @ symbol - missing domain or part of the address - extra spaces - multiple addresses in one field - obvious typos in common domains - placeholder or test values like test, example, noemail - the same address duplicated across multiple records For phone numbers, check for: - too few or too many digits - missing country code - multiple numbers in one field - text comments inside the number field - inconsistent formatting - obvious test values - the same number across multiple contacts Group issues by type. For each record, show: - contact or company name - current field value - type of error - suggested corrected format, if it can be determined with certainty - responsible manager Don't invent missing digits, domains, or contact details. If the correct value can't be determined, flag the record as requiring manual review.

Check all open deals in the [Folder name] folder for records with no link to: - any company - any contact - either a company or a contact For each deal, show: - deal name - current stage - value - responsible manager - creation date - date of last activity - which links are missing Then check the activity history, deal name, correspondence, and notes and try to identify a possible company or contact this deal should be linked to. For each suggested match, show: - the record found - what data the suggested link is based on - confidence level: high, medium, or low Don't create links automatically. Show the list of suggested changes first and wait for my confirmation.

We want to create a new sales pipeline for [product / service / business line]. Process description: - target customer: [ICP description] - lead sources: [channels] - typical sales cycle: [number of days / months] - main steps in the process: [brief description] - who is involved in the deal: [roles] - outcomes we need to track: [metrics] - automations we plan to use: [if any] Analyze this process and suggest an optimal pipeline structure. For each stage, show: - name - goal of the stage - entry criteria - criteria for moving to the next stage - required fields - typical manager tasks - recommended maximum time at this stage - possible reasons for losing a deal at this stage - automations that could be set up Also suggest: - deal card fields - required and optional fields - loss reasons - tags or segments - reports worth building - data quality rules Avoid unnecessary stages that don't represent real progress in the deal. Explain why each proposed stage is needed. Show the structure for approval first. Don't create the pipeline or fields in the CRM without my confirmation.

Analyze usage of stages in the [Pipeline name] pipeline over the last [X months]. For each stage, show: - how many deals entered the stage - how many moved to the next stage - how many were won or lost directly from this stage - average and median time at this stage - how many deals are currently at this stage - which managers use it most often - whether managers skip this stage when moving deals forward - whether there are deals that land on this stage only formally and move on within a single day Highlight: - stages the team almost never uses - stages that are regularly skipped - stages that serve the same function - stages with no clear entry or exit criteria - stages where deals consistently stall - stages with names that may be unclear to the team For each problematic stage, suggest one action: - leave as is - rename - merge with another stage - change the criteria - remove - add an automation or required field Don't change the pipeline automatically. Prepare a table with current state, issue, proposed change, and expected outcome.

Check the [Folder names] folders and find all records where no responsible manager is assigned. Group by type: - contacts - companies - leads - deals - customers - other records For each record, show: - name - record type - creation date - current status or stage - value, if it's a deal - date of last activity - the last team member who interacted with the record - linked contacts, companies, and deals Based on activity history, linked records, and current distribution, suggest a possible responsible manager. For each recommendation, explain: - why this manager is proposed - whether they have existing linked records - confidence level for the recommendation Separately highlight active deals and customers without a responsible manager as the highest priority. Don't assign managers automatically. Show the proposed distribution first and wait for my confirmation.

Audit data quality in the [Folder names] folders and prepare a practical CRM cleanup plan. Check for: - duplicate contacts and companies - records without a responsible manager - empty required fields - invalid emails and phone numbers - deals without a linked company or contact - records with no activity in more than [X] months - test and placeholder records - deals without a next step - outdated statuses - open deals with a past expected close date - inconsistent field values - fields that are almost never used - records that may be distorting reporting For each type of issue, show: - number of records affected - share of the total database - examples - impact on team workflow or analytics - priority level - recommended action - whether it can be handled automatically or requires manual review Structure the plan in three phases: 1. Critical issues to fix first 2. Bulk changes that can be made after approval 3. Ongoing rules to keep things clean going forward Also suggest: - which fields to make required - which checks to run weekly or monthly - which automations can prevent the database from getting messy again - which data quality metrics are worth tracking Don't modify or delete any records. Show the audit results and step-by-step plan first.

Find records in the [Folder name] folder that match the following conditions: - [condition 1] - [condition 2] - [condition 3] The following fields need to be updated: - [Field name]: change from [current value or any] to [new value] - [Field name]: set value to [new value] - [Field name]: clear or replace according to [rule description] First, prepare a preview of the changes. For each record, show: - name - current field value - proposed new value - reason for the change - linked deals or other important records - possible risks Also show: - total number of records - how many will be updated - how many require manual review - which records should not be updated automatically Don't make any changes yet. Wait for my clear confirmation. After confirmation: - Update only the approved records - Don't update records flagged for manual review - After completion, show a report: which records were updated, which were skipped, and where errors occurred Don't delete any data unless separately approved.

We want to create a new folder in NetHunt CRM for [process or team name]. Purpose of the folder: [what the team will track here]. Users of the folder: [roles or teams]. Main processes: - [process 1] - [process 2] - [process 3] Required analytics: - [report or metric 1] - [report or metric 2] - [report or metric 3] First, suggest the folder structure. For each field, show: - name - field type - purpose - example value - whether it should be required - who should fill it in - at which stage it's needed - how it will be used in filters, automations, or reports Also suggest: - statuses or stages - loss or closure reasons - links to contacts, companies, deals, or other folders - fields for responsible manager, next step, and deadline - tags - access rules - automations - basic views and filters - data quality rules Avoid fields that duplicate each other or won't have practical use. First, show the full structure in table format and ask clarifying questions about any uncertain decisions. Don't create the folder or fields without my explicit confirmation. After confirmation: - Create the [Folder name] folder - Add only the approved fields, statuses, and links - Don't create automations or access rules that weren't separately approved After completion, show a list of what was created and separately note anything that couldn't be created or needs manual setup.

Prepare a CRM quality report for [month] and compare with the previous month. Show: - share of required fields that are filled in - number of duplicates - records without a responsible manager - deals without a next step - records with invalid contact data - overdue open deals - records with no activity - issues that were resolved during the month Provide a quality rating by category and the top three priorities for next month.

In the [Folder name] folder, find all open deals where the [Expected close date] field contains a date earlier than today — deals where the deadline has passed but the status is still active. For each deal, show: company name, responsible manager, deal value, current stage, expected close date, how many days overdue, and date of last activity from the timeline. Group by how long they've been overdue: - Up to 14 days — likely just needs a date update - 14 to 60 days — deal is at risk, needs attention - Over 60 days — likely no longer active For the "over 60 days" group, separately check the timeline: was there any activity at all after the close date passed? If not — these are candidates to close as lost or mark as inactive. Sort by deal value within each group — highest first. Group by manager — who has the most overdue deals and for what total value. Output as a list for manual review.