18 use cases that work with Salesforce, a crm system.
Agents usually read Salesforce to understand accounts, contacts and opportunities, then write back carefully: logging activities, filling fields from call notes, proposing cleanup or flagging deals that look at risk. Most good setups keep writes narrow, use the API user permissions of the person asking, and leave stage, amount and close date changes to a human.
18 use cases in this library work with Salesforce, across Call Coaching, Prospecting / Outbound, Pipeline Hygiene / CRM, Deal Review / Forecasting, RevOps Reporting. The first ones to look at: Alert deal owners to risk signals in new call transcripts within the hour; Deliver a one-page account brief to the rep before every meeting; Flag booked meetings where the prospect barely committed. 6 of them are vendor-neutral reference setups, where Salesforce is one of several interchangeable options. 18 of them include a copy-paste prompt.
Each entry explains what triggers the agent, which systems it reads from and writes to, the steps it follows, what it costs to run and the gotchas people hit. Every entry links to its original source, so you can read the full write-up before you copy a setup into your own Salesforce account.
Browse by category: Call Coaching, Prospecting / Outbound, Pipeline Hygiene / CRM, Deal Review / Forecasting, RevOps Reporting. Recipes that use it: Answer every inbound lead fast, Keep my pipeline honest, Run a great field day.
This agent reads new sales call recordings and alerts the deal owner when something risky comes up, like a competitor mention, a pricing objection or no next step. Risks surface the same day instead of at the weekly review.
Works with any of GongChorusAttention +5
Before every sales meeting, this agent sends the rep a one-page brief on the account: recent news, past conversations and open questions. Reps walk in prepared without digging through notes.
Works with any of Google CalendarOutlookSalesforce +7
When a meeting gets booked, this agent reviews the call and flags ones where the prospect barely committed. Managers can firm up or requalify those meetings before a salesperson spends time on them.
Works with any of NooksOrumOutreach +11
For reps who visit accounts in person, this agent picks the best accounts nearby, plans an efficient route, and preps a brief and leave-behind page per stop. Afterward it logs visits and next steps in the CRM.
Works with any of SalesforceHubSpotGoogle Maps +5
This agent builds a consistent profile of each open deal from calls and CRM data, and first tests whether that profile actually separates past wins from losses. Leaders get a deal score they have checked before trusting it.
Works with any of SalesforceHubSpotGong +6
This analysis checks whether deals that include an ROI or business-case conversation actually win more often, comparing like with like. Leaders can decide on a required sales step with evidence instead of instinct.
Works with any of SalesforceHubSpotGong +6
Reps and managers ask questions about deals and quotes in their work chat and get answers straight from the CRM, limited to what they are allowed to see. No digging through reports.
Works with SalesforceMicrosoft Teams
This agent checks new and changed leads for duplicates, including the same company spelled differently, and cleans them up with narrow, careful steps. The CRM stays tidy without someone hunting duplicates by hand.
Works with SalesforceSlack
Once a week, this agent reviews the CRM for duplicates, bad values, gaps and dead deals and proposes fixes that a person approves before anything changes. Cleanup becomes routine instead of a rushed purge.
Works with HubSpotSalesforceSlack +1
When a partner is active in one of your target or closed-lost accounts, this workflow drafts an email asking the partner's rep for an intro and posts it to Slack for approval. Partner overlap turns into warm intros instead of a report.
Works with CrossbeamSalesforceSlack +1
This agent reads finished sales call recordings, pulls out the summary and action items, and writes them back to the CRM. It is a build guide for engineers, including the pitfalls that break a naive setup.
Works with ChorusSalesforceHubSpot
Every weekday morning, an agent sends reps a briefing on their target accounts, and a second one helps turn a chosen theme into an outreach sequence. Reps spend less time on reading and writing and more on selling.
Works with NotionSalesforceSlack
Before a forecast call, this assistant pulls the latest forecast, recent deal changes and risk scores so a revenue leader can ask plain questions about them. It saves the weekly export-and-paste routine.
Works with ClariSalesforce
This agent researches target accounts to find which competitor they use and why, then puts that context in the CRM. Reps get something they can sell against instead of a bare yes or no.
Works with ClaySalesforceLinkedIn
For each new lead, this agent checks whether outreach makes sense, researches the person and company, and drafts an email the rep approves. Reps skip most of the digging and avoid stepping on a teammate's outreach.
Works with SalesforceGongLinkedIn +3
This is how one team moved its outbound reps onto a single platform where agents research accounts, write messages and support calling. The lesson: agents only help if the CRM context behind them is good.
Works with NooksSalesforce
When an account starts showing buying intent, this setup assigns it to one rep and sends them a ready-to-edit message. Intent signals stop sitting in a report nobody checks.
Works with 6senseCommon RoomSalesforce +1
This agent keeps researching a whole group of accounts, such as lost deals, and records things like the real reason a deal was lost. Reps stop redoing the same research every time they revisit an account.
Works with ClaySalesforceHubSpot +3
AI agent setups for sales leaders running leaner teams. Free, every week.
Free. One email a week. Unsubscribe anytime.