Moody's sales reps get agent-built account briefs and review every outreach draft

The task

Moody's sales reps used to prepare for customer conversations by researching each account by hand across several disconnected systems. Relevant news such as a regulatory action, an executive change or a merger could go unnoticed before anyone linked it to a sales opportunity. Getting ready for a first meeting meant pulling customer details and market context together from many places.

What they did

The company built what it calls a sales recon agent on Agentforce, inside the Salesforce CRM its reps already use. Before the agent works with any data, Informatica cleans and reconciles duplicate and mismatched records at the source. Data 360 and MuleSoft give the agent access to Moody's own company data, news and event signals, and approved operational data such as meeting recordings and email history. The agent runs in the background and tracks signals like mergers, leadership moves and regulatory events. When one matters for a customer, it lays out the context, drafts an outreach message and points to Moody's products that might fit. Before a booked meeting it assembles an account brief, and afterwards it helps write up the outcome and suggests record updates. Salesforce engineers worked alongside Moody's AI team on the build.

What the source reports

According to the source, reps who use the agent at least twice a week book 20% more meetings than reps who do not use it. The source reports that these active users move about one-third more opportunities into the middle of the pipeline and reach the trial stage up to 32% faster. According to the company, onboarding time for new reps has dropped by about 50%, and adoption among sellers is above 61%.

Where the approval sits

The rep stays in charge of every message. The agent drafts outreach and highlights possible solutions for the rep to evaluate, and the rep reads the draft, edits it where needed and sends it. After a meeting the agent suggests updates to the CRM records, and the rep reviews those as well.

Worth knowing

The source is a Salesforce customer story about its own product, so the figures come from the vendor and its customer. They compare frequent users with non-users and do not come from a controlled test. The setup relies on extensive data preparation across several enterprise systems, which a smaller team may not have. The story does not show the prompts, the costs or how often drafts needed changes.

More in this category

• Research and briefings

  A Claude Cowork skill builds one morning brief from calendar, chat, and tasks

  A team built a Claude Cowork skill that gathers the day's calendar, recent messages, and open tasks into one brief each morning. The brief is a summary: a person reads it, and the post describes no step where anything is sent.

  Read the entry
• Research and briefings

  A scheduled agent watches competitor pages and writes a daily brief

  A company has an AI agent check competitor pages and web mentions every morning and write one brief per competitor. The brief is internal reading material for the team, and the agent sends nothing to competitors.

  Read the entry
• Research and briefings

  A scheduled AI briefing replaces a manual morning round of inbox and calendar

  A technology executive has Claude Cowork prepare a briefing of urgent email, the day's calendar, and a short action list every morning. The author reads it, and the post shows no step where anything is sent.

  Read the entry