# Sales templates

Lead research, account briefs and prospect lists.

- [Inbound lead researcher](https://marketplace.agentrun.ai/templates/inbound-lead.md): Researches each inbound lead from your form or CRM (the person, the company), scores it 0-100 against your ideal customer profile with the evidence for each criterion, suggests the next step, and posts the brief to the CRM record or a Slack channel. Learns from your corrections.
- [Competitive battlecard](https://marketplace.agentrun.ai/templates/battlecard.md): Name your company and one competitor, and get a sourced battlecard a seller can use in a deal. It covers the competitor's positioning and target customers, public pricing and recent price changes, a capability-by-capability comparison with yes, no, partial or unclear marked per cell, strengths to respect, weaknesses backed by reviews and incidents, recent moves, win themes, objection responses and questions that expose gaps. Every claim is cited. Where it cannot verify your side or their price, it says unclear or contact sales.
- [Deal hygiene](https://marketplace.agentrun.ai/templates/deal-hygiene.md): Once a week, a Slack post listing the open HubSpot deals that need a look, biggest first. A deal is listed when it has had no activity for longer than you allow, has no next step, or is past its close date. Each line says which of the three, the amount, the stage and the owner. A deal still listed from last week is marked as such. It only reads HubSpot and posts to one channel. It posts on its own only if you pick Never for approvals at install; it stays held to your pipeline and channel either way.
- [Meeting prep brief](https://marketplace.agentrun.ai/templates/meeting-prep.md): Give it a person, their organization and what the meeting is for, and it returns a one-page brief built from public professional sources. You get a dated career table, recent statements and news, a snapshot of the organization, talking points, tailored questions and the topics to tread lightly on. Every claim is cited. When the name could be two people, it says which one it assumed. It never uses family, health, religion, politics or home details.
- [Pipeline goal](https://marketplace.agentrun.ai/templates/pipeline-goal.md): Checks your HubSpot pipeline every morning and posts one Slack message the first time the open deals add up past the goal you set. You choose the plain total or one weighted by each stage's win probability. Closed deals, other pipelines and deals with no amount don't count, and a missing amount is never guessed. It posts once per goal, never twice, and only reads HubSpot. It posts on its own only if you pick Never for approvals at install; it stays held to your pipeline and channel either way.
- [Open tender finder](https://marketplace.agentrun.ai/templates/tender-finder.md): Every Monday, the open public tenders and RFPs that match what you sell, in the countries you name. Each one is checked on the buyer's official notice page for status and deadline, and comes with the buyer, the stated value, eligibility against what you hold, and a link to the notice. New tenders are separated from ones you already saw, tenders closing within a week are flagged, and nothing is guessed when a notice does not say. It never registers, logs in or bids.
- [Follow-up drafter](https://marketplace.agentrun.ai/templates/follow-up-drafter.md): When a new email lands in a Gmail label you pick (say, follow-up), it reads the whole thread and writes your next reply as a Gmail draft in that thread, in your own voice. It answers each question from what the thread already says and leaves a bracketed blank for anything only you know (a price, a date, a yes). It never sends. Each draft waits for your yes before it's saved, and you press send. It skips threads where you wrote last, a draft already waits, or the sender asked not to be contacted.
- [Meeting follow-up](https://marketplace.agentrun.ai/templates/meeting-follow-up.md): At the end of each workday it goes through the meetings that ended today with people from outside your company and saves a follow-up email for each one as a Gmail draft. Each draft thanks them, lists the invite's agenda with a bracketed blank for each outcome, and leaves a blank for the next step. It never invents what was agreed and never sends. Each draft waits for your yes before it's saved, then you fill the blanks and press send. Internal meetings, ones you declined, cancelled ones and ones it already drafted are skipped.
- [Outreach opener](https://marketplace.agentrun.ai/templates/outreach-opener.md): Give it a person, their company and their email address, and it researches both on the public web, then writes a short first email that opens on one recent, sourced fact about them or their company and says why you're writing. It saves the email as a Gmail draft to that address and never sends; the draft waits for your yes before it's saved. It never claims a fact it didn't read, never treats an old fact as news, and says so when it can't confirm the person works there.
- [Buyer evidence pack](https://marketplace.agentrun.ai/templates/buyer-evidence.md): Before a call with a skeptical buyer, list the objections you expect and get, for each one, the public customer results, ROI figures, reviews, certifications and independent studies that answer it. Every row is dated and linked, says whether it comes from the vendor or a third party and how close the customer is to your buyer, and comes with talking points and one question to ask. Evidence that cuts against you is shown too, thin objections are named as gaps, and no figure is scaled to the buyer.
- [Lead list builder](https://marketplace.agentrun.ai/templates/lead-list-builder.md): Describe your ideal customer and get a list of matching companies, each checked against its own website, with up to two people per company by job title and a source for every row. It needs a monid key for the company and people search. It gives names and job titles only, no emails or phone numbers.
