Find the right prompt for the job

Build an audience for an acceleration campaign on {topic} targeting open opportunities in {journey_stage} that have not engaged with that content yet. Include account, top 3 buying group contacts, and a personalization angle from their existing engagement history.

Recommend tier assignments for new accounts added to our database in the last {days} days based on: qualification score, fit data (industry, revenue, employee count), engagement to date, and intent signals. Output Tier 1 / Tier 2 / Tier 3 / Disqualify with rationale for each.

For the {program_name} acquisition program running the last {days} days, show accounts touched, accounts that progressed a journey stage, pipeline created, average marketing engagement points per account, and cost per account journey-stage advance.

Compare accounts that closed-won in the last {days} days against accounts of similar profile that closed-lost. Show median marketing engagement points, web visits, sales touches, contacts engaged, and time spent in each journey stage for each group. Highlight where the two groups diverged most.

For the last {days} days, show pipeline created per marketing program, per SDR sequence, and per content asset. Include accounts touched, pipeline $ influenced, journey-stage advances, and cost (if available) per advance. Rank top and bottom performers.

Show accounts with high anonymous web visits (more than {min_visits} in the last {days} days) but fewer than {max_known} known contacts. Include the pages they’re visiting, qualification score, and journey stage. These are de-anonymization and contact-enrichment priorities.

Identify customer accounts where marketing engagement points dropped more than {drop_threshold}% in the last {days} days, a key champion contact has gone silent for more than {silent_days} days, or they’ve engaged with competitor intent topics. Show account, CSM, renewal date, and signal type.

Build a list of {n} accounts in {industry} and {company_size_range} that are in Aware or Target journey stage, have a qualification score above {min_score}, and have not been touched by an awareness campaign in the last {days} days. Include account, owner, score, and recommended channel based on past response patterns.

Build a target list of accounts in {industry} that match our ICP, are not yet in our CRM, and have shown intent on {topic_list} above {threshold} in the last {days} days. Include firmographics, intent topics, and rank by qualification score.

For my top 10 target accounts in {tier}, show current contacts on file by persona. Identify the personas missing for a complete buying committee at this account size, list any known contacts at the company not yet in our database, and suggest research sources or enrichment priorities.

For {company_name}, show the current buying group: every contact engaged in the last {days} days, their title, persona, job level, last activity, and marketing engagement points. Identify missing personas typical for our buying committee (economic buyer, technical evaluator, end user, champion) and recommend contacts to add or research.

At {company_name}, identify the most engaged contact in the last {days} days. Show their title, total marketing engagement points, content/pages consumed, recency of activity, and whether they’ve engaged with high-intent content (pricing, demo, competitive). Rank top 3 likely champions and explain why.

Analyze the last {n} closed-won deals in the {segment} segment. Show the average number of marketing touches, sales touches, web visits, content engagements, and unique contacts engaged before close. Break down by journey stage and identify which activity types correlate most strongly with closed-won versus closed-lost.

List accounts researching {competitor_keywords} or {technographic_tags} in the last {days} days. Include account name, whether they’re a current customer or prospect, journey stage, owner, contacts engaged, and intent topic trend. Flag at-risk customers separately from competitive-displacement opportunities.

For {company_name}, show which personas have engaged with our {product_line} content in the last {days} days. Identify the buying group needed for a {target_product} cross-sell, gaps in our current contact coverage, and recommend a next step for each missing persona.

Show customers that previously reached the {target_stage} stage for an expansion opp but went silent more than {days} days ago. Include reason for stall if known, last engaged content, and current intent signals. Rank by expansion potential.

For deals closed in the last {days} days at {segment}, show median time per journey stage. Compare against my current open opportunities and flag deals that have exceeded the median time in their current stage by {variance}%.

Find accounts in {journey_stage} where a Director-level or above contact has engaged in the last {days} days but the account owner has had zero sales touches with them. List account, contact name, title, engagement signals, and recommend an outreach angle based on the content they consumed.

Show customer accounts that have shown intent on {expansion_topic_list} in the last {days} days, have marketing engagement points trending up, and have no open expansion opp. Include account, CSM, current ARR, contacts engaged, and recommended product or service to position.

Review all open opportunities forecast to close in the next {days} days. For each, show pipeline-predict score, buying group engagement depth (contacts engaged in last 14 days), qualification score trend, and any silence or stall signals. Flag opps where engagement data contradicts the forecast call.

Of accounts that showed surging intent on {topic} in the last {days} days, how many engaged with our owned channels (web, content, ads)? Show the conversion rate, average time from intent surge to first engagement, and which content they consumed first.

For accounts owned by {owner_name} that moved from {from_stage} to {to_stage} in the last {days} days, show the activities in the 30 days prior to the transition. Include marketing engagement (web visits, content downloads, event attendance, ad clicks), sales touches (emails, calls, meetings), and intent signal changes. Identify the top 3 activity patterns most common across transitions.

Based on the firmographic and behavioral profile of accounts we closed-won in the last {days} days in the {segment} segment, find {n} look-alike accounts not yet in our pipeline. Include match rationale.

For all opportunities created in the last {days} days, show the top 10 contributing activities (e.g. webinar X, content asset Y, ad campaign Z, SDR sequence A). Include account count touched, pipeline dollar value influenced, and average days-to-opp post-engagement. Sort by total pipeline influenced.

Show all accounts that became MQA in the last {days} days. For each: account, owner, qualification score, pipeline-predict score, top 3 engaged contacts with titles and recent activity, key intent topics, and a one-line recommended opening angle for the AE.

For my open opportunities, identify which accounts have fewer than {min_contacts} contacts engaged in the last 30 days or are missing engagement from {required_job_level} level. Show account name, opp stage, days in stage, current contacts and their roles, and the persona gaps. Sort by opp value descending.

Show all open opportunities owned by {owner_name} in Pipeline or SQL Opportunity stage. For each: opp value, days in stage, pipeline-predict score, qualification score trend (last 30 days), buying group engagement (number of contacts, last activity), top content consumed in last 14 days, and any intent surge. Flag opps with declining marketing engagement.

Across accounts currently in {journey_stage}, show which personas ({persona_list}) are engaging most in the last 30 days. Include average marketing engagement points per persona, top content consumed by each, and which personas typically appear only at later stages.

For the last {days} days, show which personas (job functions / levels) contributed most to closed-won deals. Include average marketing engagement points per persona on won deals, content types they engaged with, and rank personas by influence on revenue.

Show open opportunities owned by {owner_name} where the pipeline-predict score dropped by more than {threshold} in the last {days} days. For each, list the engagement signals that declined and recommend an intervention.

Find open opportunities where the account had no marketing engagement for {min_silent_days} days but engaged in the last {recent_days} days. Show account, opp stage, what they re-engaged with, who engaged, and recommend an outreach play.

For {company_name} with renewal in the next {days} days: pull current ARR, product usage trend, marketing engagement points last 90 days, contacts engaged with titles, support tickets summary if available, intent signals (positive and competitive), and content consumed. Produce a renewal-readiness summary I can review in 5 minutes.

Compare {segment_a} vs {segment_b} for the last {days} days on: accounts entering each journey stage, conversion rate stage-to-stage, average marketing engagement points, average days in pipeline, and win rate. Highlight where one segment significantly outperforms the other and hypothesize why.

Find accounts owned by {owner_name} in {journey_stage} for more than {days} days. For each, show last engagement date, marketing engagement points trend over the last 60 days, qualification score change, pipeline-predict score trend, key contacts engaged or missing, and which intent topics they’re still researching. Recommend the next best action.

Find accounts whose intent score on topics {topic_list} increased by more than {threshold} in the last {days} days. Include account name, current journey stage, qualification score, owner, top surging keywords, and whether they’re already in pipeline. Surface accounts not yet contacted by sales.

For accounts that reached the {target_stage} stage in the last {days} days, show the average days from first-known engagement to pipeline creation. Identify the fastest-converting accounts and the activities that accelerated them versus the slowest-converting and what was missing.

Give me this week’s GTM snapshot: (a) net new accounts entering MQA stage with owners and qualification scores; (b) accounts that advanced or regressed a journey stage and what drove it; (c) top 5 surging-intent accounts not yet in pipeline; (d) open opps with declining pipeline-predict score; (e) customer accounts with at-risk signals; (f) one recommended action per section.