Skip to content
Agents tracked: 258 Downloads (7d): 219M up 6.1% GitHub stars: 5.5M VS Code installs: 148M Releases (7d): 293 Agent status: 2 with issues Updated Oct 7, 2026
Case study Major Tom

How Major Tom re-engaged dormant leads with HubSpot's Prospecting Agent

Digital agency Major Tom used HubSpot's Prospecting Agent to run personalized multi-touch emails to dormant CRM leads. HubSpot reports meetings, proposals and a closed deal within about three weeks.

The problem

The agency had about 7,000 dormant contacts going back to 2020 and no sales capacity to re-engage them. Its earlier outreach was generic and often asked about budget before learning the prospect's needs.

How they did it

  1. Configured the agent to reference each contact's full CRM history.
  2. Added the agency's brand voice and tone, plus on-brand keywords such as 'audit' and 'free guarantee'.
  3. Embedded self-booking meeting links in the emails.
  4. Ran sequences of three to four emails per contact against dormant MQL and SQL segments, adjusting by segment response.

Results

  • In just over three weeks, the agent re-engaged more than 1,000 dormant MQL and SQL contacts, and 24 meetings were booked.
  • More than $750,000 in proposals followed, with approximately 25% expected to close. One deal at around $200,000 closed.
  • HubSpot estimates roughly 300 rep-hours of manual research saved.

As reported by the source (HubSpot case study); AgentGid did not measure these figures.

Takeaway. Point an outreach agent at old CRM leads you've already qualified. They're a low-risk first test, and the agent can use their history to personalize.
AgentGid's take

This suits a small sales or marketing team already on a paid HubSpot Sales Hub plan with a CRM history worth mining. The setup is light, but you'll need to write brand voice guidance and review the emails. Watch the cost: at $1 per recommended lead, 7,000 contacts would run about $7,000, and the results are HubSpot-reported. Regie.ai (Free + $49/mo) is a cheaper option to test first.

The agent used here

Similar use cases