Sales Engine Pro Official

Discovers companies matching the ICP, confirms them with Apollo, and writes vetted accounts to the Target Accounts table.

1. 01Using the ideal customer profile {{icpDefinition}}, run at most 3 to 5 web searches to find real companies that match. Target about {{numberOfAccounts}} companies (default to 10 if not provided). Compile a candidate list with company name and best-guess domain. Do not invent companies.Output: A candidate list of company names with domains.
2. 02For each candidate, use Apollo organization enrichment by domain to confirm industry, employee count, and headquarters. Drop any company that cannot be confirmed or that clearly falls outside the ICP (wrong size, wrong industry, or on the exclusions list).Output: A confirmed list with industry, employee count, and headquarters for each surviving company.
3. 03Score each confirmed company from 0 to 100 for ICP fit with a one-line rationale. Then write the vetted companies as new rows in the Target Accounts table with Account Name, Domain, Industry, Employee Count, Headquarters, Fit Score, Fit Rationale, Status set to New, and Discovered On set to today. Write at most 15 rows to stay within limits.Output: Confirmation that rows were written, then a short readable summary using headings and bullet points: how many accounts were added and the top few by fit score with their rationale. Never output JSON or raw data.

Reads Pending prospects, enriches them via Apollo, and writes back title, seniority, department, company details, and on-file flags.

1. 01Read rows from the Prospects table whose Enrichment Status is Pending. Take at most {{maxToProcess}} of them (default to 4 if not provided) to stay within limits.Output: The list of pending prospects to enrich this run, with their name and company.
2. 02For each selected prospect, use Apollo people matching (with reveal flags off) and organization enrichment to confirm the person and gather Title, Seniority, Department, LinkedIn URL, and company details. Determine only whether an email and a phone are on file as Yes or No. Never retrieve or store the actual email address or phone number.Output: For each prospect, the confirmed professional details plus Email On File and Phone On File as Yes or No.
3. 03Update each prospect row in the Prospects table with the gathered Title, Seniority, Department, LinkedIn URL, company details, Email On File, and Phone On File, and set Enrichment Status to Enriched. If a prospect could not be confirmed, set Enrichment Status to Not Found and leave a short note.Output: Confirmation of which rows were updated, then a short readable summary using headings and bullet points: how many were Enriched and how many Not Found. Never output JSON or raw data.

Researches a named company and returns a short brief: what they do, size, location, recent signals, and a suggested outreach angle.

1. 01Research the company {{companyName}} (domain {{companyDomain}} if provided). Use Apollo organization enrichment for firmographics (industry, size, headquarters) and web search for recent signals such as funding, launches, hiring, or leadership changes. Use only what the tools return; do not invent.Output: Raw confirmed facts: firmographics and any recent signals found, with a note on anything that could not be confirmed.
2. 02Write a concise brief for a rep: what the company does, rough size and location, any notable recent signals, a short read on why they might be a fit, and one suggested outreach angle. If the company could not be confirmed, say so plainly.Output: A short, readable brief using headings and bullet points. Never output JSON or raw data.

Searches for public buying signals on enriched prospects and their companies, and writes a short Intent Signal back to the Prospects table.

1. 01Read Enriched prospects from the Prospects table that do not yet have an Intent Signal. Take at most {{maxToProcess}} (default to 5 if not provided) to stay within limits.Output: The list of prospects to scan this run, with name and company.
2. 02For each prospect, run 1 to 2 searches on the company for recent public signals such as relevant hiring, funding, leadership changes, launches, or expansion. Judge whether any signal suggests they may be in-market. Use only what search returns.Output: For each prospect, either a one-line intent signal with its basis, or a note that no clear signal was found.
3. 03Update each prospect row in the Prospects table, writing the one-line signal to the Intent Signal column. Leave it blank where no clear signal was found.Output: Confirmation of which rows were updated, then a short readable summary using headings and bullet points: how many had a signal and the most promising few. Never output JSON or raw data.

Scores a lead or prospect for fit against the ICP, with a tier and rationale.

1. 01Compare the lead {{leadDetails}} against the ideal customer profile {{icpDefinition}}. Assess fit across industry, company size, geography, persona or title, and any buying signals present. Note where the lead matches and where it does not.Output: A short assessment of matches and mismatches across the fit dimensions.
2. 02Produce a fit score from 0 to 100, a tier (High for 70 and above, Medium for 40 to 69, Low for below 40), a one to two line rationale, and the single biggest gap or risk.Output: A readable result with clear labels: Score, Tier, Rationale, and Biggest gap. Never output JSON or code blocks.

Drafts a concise, personalized cold email plus a follow-up, grounded in the product knowledge base.

1. 01Read the prospect context {{prospectContext}} and the goal {{goal}} if given. Search the Product Knowledge Base for the most relevant value points, positioning, and proof for this prospect. Do not use any product claim that is not supported by the knowledge base.Output: A short list of the specific value points and any proof to use for this prospect, drawn from the knowledge base.
2. 02Draft a first-touch cold email: a short subject line and a body of about 90 to 130 words that opens with a specific, relevant hook about the prospect, ties to one or two value points from the knowledge base, and ends with a low-friction call to action. Then draft one brief follow-up message for a few days later. Keep it human and specific, not generic. Do not claim anything was sent.Output: A readable draft with clear labels: Subject, Email body, and Follow-up. Plain prose, never JSON or code blocks.

Drafts a short LinkedIn connection note and a first message, grounded in the product knowledge base.

1. 01Read the prospect context {{prospectContext}} and goal {{goal}} if given. Search the Product Knowledge Base for one or two relevant value points. Do not use any claim not supported by the knowledge base.Output: A short list of the value points and hook to use, drawn from the knowledge base.
2. 02Draft a LinkedIn connection note under 300 characters that is specific and non-salesy, then a short first message of about 60 to 90 words to send after they connect, referencing a relevant hook and ending with a light call to action. Keep it human. Do not claim anything was sent.Output: A readable draft with clear labels: Connection note, and First message. Plain prose, never JSON or code blocks.

Drafts a short multi-touch nurture sequence for prospects who are not ready yet, grounded in the product knowledge base.

1. 01Read the prospect context {{prospectContext}}. Search the Product Knowledge Base for useful angles, resources, and value points relevant to this prospect. Do not use any claim not supported by the knowledge base.Output: A short list of value-led angles and any resources to reference, drawn from the knowledge base.
2. 02Draft a nurture sequence of {{numberOfTouches}} touches (default to 3 if not provided), spaced over a few weeks. Each touch should lead with something helpful rather than a hard pitch, stay short, and build toward a soft call to action by the last touch. Suggest timing for each. Do not claim anything was sent.Output: A readable sequence with a labeled block per touch: Timing, Subject or hook, and Message. Plain prose, never JSON or code blocks.

Qualifies an open opportunity against a simple framework and writes a qualification summary and next step back to the deal.

1. 01Read the opportunity named {{dealName}} from the Sales Opportunities table. If helpful, check the Product Knowledge Base for fit against what we sell. Assess it across need, budget signal, authority, timing, and product fit, using only the information present. Note what is known and what is missing.Output: A short internal assessment across need, budget, authority, timing, and fit, with gaps called out.
2. 02Write a qualification summary with a readiness read (strong, developing, or weak), the single most important open question, and a concrete recommended Next Step. Update the opportunity row: set the Next Step and append the summary to Notes. Do not change the Amount or Stage.Output: Confirmation the row was updated, then a readable summary with labels: Readiness, Key open question, and Next step. Never output JSON or code blocks.

Drafts a clear, tailored proposal for a deal, grounded in the product knowledge base and the opportunity details.

1. 01Read the deal context {{dealContext}} and buyer priorities {{buyerPriorities}} if given. Search the Product Knowledge Base for the relevant offering, pricing, and proof. Use only what the knowledge base supports; never invent pricing or terms. Note anything the seller must confirm before sending.Output: A short outline: the buyer's situation, the fit, the relevant offering and pricing from the knowledge base, and open items to confirm.
2. 02Draft a proposal with these sections: a brief summary of the buyer's goal, the recommended solution and scope, pricing as supported by the knowledge base, expected outcomes framed honestly, and clear next steps. Flag any placeholder the seller must fill. Keep it concise and client-ready.Output: A readable proposal draft organized under clear section headings, with a short list of placeholders to confirm at the end. Never output JSON or code blocks.

Reviews a draft proposal or quote for accuracy, clarity, and consistency with the knowledge base before it goes out.

1. 01Read the draft {{draftToReview}}. Check every product claim, price, and term against the Product Knowledge Base. Identify anything unsupported, inconsistent, unclear, or risky, and note anything important that is missing (such as scope, assumptions, or next steps).Output: An internal list of issues found, each tagged as accuracy, clarity, consistency, or risk, with the specific location.
2. 02Produce review notes: a short overall read (ready to send, minor edits, or needs work), then the prioritized issues with a suggested fix for each, then a brief list of anything to confirm before sending. Do not rewrite the whole document.Output: A readable review with headings: Overall read, Issues and fixes, and Confirm before sending. Never output JSON or code blocks.

Reads the Sales Opportunities table and produces a prioritized digest of totals and at-risk deals with recovery actions.

1. 01Read all rows from the Sales Opportunities table. Identify at-risk open deals using these signals: no recent activity (stale Last Activity), a Close Date that is in the past or very near while the Stage is not Closed Won or Closed Lost, or a low Win Probability. Ignore deals already Closed Won or Closed Lost for the risk list.Output: An internal list of the at-risk deals with the reason each is flagged.
2. 02Produce a prioritized digest: first a short summary with the count and total value of open deals and a breakdown by stage, then the at-risk deals ordered by amount (highest first), each with the deal name, account, amount, why it is at risk, and a recommended recovery action.Output: A readable digest using headings and bullet points, with dollar amounts. Lead with the summary, then the at-risk list. Never output JSON or raw rows.

Reads Customer Accounts and flags upcoming renewals, churn risk, and expansion opportunities with a recommended play for each.

1. 01Read all rows from the Customer Accounts table. Using a horizon of {{horizonInDays}} days (default to 90 if not provided), identify accounts with renewals due within the horizon, accounts at churn risk (low Health Score, Down usage trend, or low seat utilization), and accounts that look ready to expand (high health, Up usage, high utilization). Use only the table.Output: An internal grouping of accounts into renewals due, churn risk, and expansion candidates, with the basis for each.
2. 02Produce a prioritized report with three sections, Renewals due, Churn risk, and Expansion opportunities. In each, list the accounts (name, ARR, renewal date where relevant) ordered by ARR, with a one-line reason and a recommended play for each.Output: A readable report using the three headings and bullet points, with ARR figures. Never output JSON or raw rows.

Audits CRM Contacts for data quality issues and writes concise flags back to each affected record.

1. 01Read up to {{maxToProcess}} rows (default to 25 if not provided) from the CRM Contacts table. Check each for data quality issues: missing email, company, or job title; a stale Last Contacted date; a lifecycle stage that looks inconsistent; and likely duplicates based on matching name or email. Use only the table.Output: An internal list of records with the specific issues found for each, and a separate list of suspected duplicate pairs.
2. 02For each affected record, write a concise note in the Data Quality Flags column describing the issue (for example: missing email; stale, no contact in 180 days; possible duplicate of the same name). Do not delete or overwrite any other field. Leave clean records unchanged.Output: Confirmation of which rows were flagged, then a readable summary using headings and bullet points: totals by issue type and the suspected duplicate pairs. Never output JSON or raw rows.

Turns raw call or meeting notes into a clean CRM summary with action items, and updates the matching contact record.

1. 01Read the raw call notes {{rawCallNotes}} for the contact {{contactName}}. Extract the key points: what was discussed, decisions made, objections or concerns raised, and any commitments or next steps, with owners and dates where stated. Capture only what the notes say; do not invent.Output: An internal structured extraction: discussion points, decisions, concerns, and action items with owners and dates.
2. 02Find the matching contact in the CRM Contacts table by name. Append a dated, concise summary to that record's Notes and update Last Contacted to the call date (today if not stated). Do not overwrite existing notes; add to them. If no matching contact is found, say so and do not create one.Output: Confirmation of the record updated (or that none matched), then a readable summary with headings: Summary, Decisions, and Action items. Never output JSON or code blocks.