Sales Agent: Case Study
We built our own lead gen agentbefore we sold it to anyone else.
Discovery, enrichment, CRM, outreach, tracking. Fully automated. It ran this morning at 6:45AM. Here is exactly how it works.
Note: The tools shown below are what we use for our own system, one example of how the architecture can be built. Your build uses whatever's already in your stack: your CRM, your email provider, your data sources. We're tool-agnostic by design.
The Architecture
Five stages. Fully autonomous.
Each stage runs in sequence, automatically, every weekday morning.
No human intervention between stages 1 and 3. Outreach requires a one-tap approval before sending.
The Numbers
What it actually costs and delivers.
How It Works
Stage by stage.
Discovery
Brave Search API Web SearchEvery weekday at 6:45AM, the agent runs 6 to 8 searches across the web looking for buying signals. Not brand mentions. Signals. Things like a law firm posting a Head of AI job, a hospital announcing an AI transformation initiative, or a manufacturer quoted in trade press talking about operational bottlenecks.
Each result gets scored against a litmus test before it moves forward: what does this company sell? If it is an AI company or a startup raising money to build AI, it gets rejected. The pipeline is only interested in businesses buying or adopting AI to improve an existing operation, not companies building AI as their product.
Results that pass are written to a staging file. The agent does not touch HubSpot, email, or anything external at this stage. Discovery is read-only.
Enrichment
Apollo.io Hunter.ioAt 7:00AM, a second agent reads the staging file and enriches each lead. High-priority signals, the ones with a named decision maker visible in the press, clear pain, and evidence of budget, go to Apollo first. The agent searches for the COO, VP of Operations, CTO, or Head of AI at that company and pulls back a verified email.
Medium signals go to Hunter for a domain search. This surfaces whoever is most contactable at that organization without burning Apollo credits on a weaker signal.
Credits are capped daily to stay within free tier limits. Apollo gets four lookups per day, Hunter gets three. If a lead cannot be enriched today, it waits. There is no point sending an email to a generic info@ address.
CRM
HubSpotEvery verified contact gets pushed to HubSpot automatically. A contact record is created with the email, title, and company. A deal is opened in the pipeline at the first stage. A note is attached to the contact with the buying signal, the source URL, and a suggested outreach angle: one sentence explaining why this person, at this company, at this moment.
The outreach draft is generated at this stage too, based on the signal and the contact details. The agent writes a short, plain email, not a template, not a sequence. One email that references something real about why we reached out.
Outreach
Resend API Signal (approval)The draft lands in a Signal message. One tap to send, one tap to skip. This is the only point in the pipeline that requires human input, and it takes about 30 seconds per lead. The email does not go out until someone approves it.
When it sends, it goes through Resend with tracking enabled. Every send is logged with a unique message ID tied to the HubSpot contact record. The sender is info@montebelle.com, a verified domain, not a free inbox.
The emails are short. They reference a specific signal. They say what we do. They ask one question. No pitch decks, no feature lists, no "I wanted to reach out."
Tracking
Resend Webhooks HubSpot NotesEvery morning at 9:30AM, a metrics agent polls Resend for email events and writes them back to HubSpot as notes. Opens, clicks, bounces, all logged against the contact. If someone clicked the link but did not reply, we see that. If an email bounced, the contact is flagged so we do not send again.
We are notified only on events that matter: an open from a warm lead, a click, or a bounce. The system stays silent otherwise. There is no daily report to read, no dashboard to check. The signal reaches us when something worth acting on happens.
Dog-fooding
This ran this morning at 6:45AM.
Not a simulation. Not a demo environment. The same system, running against real data, delivering real leads to our pipeline every weekday before we start work.
When a prospect asks "does this actually work?" the answer is a link to this page. We use it ourselves. The system found the prospects who are reading this right now.
That is the only honest way to sell it.
New lead enriched:
Signal: Regional hospital group quoted in Health Affairs: "AI for denial appeals reducing review time by 60%". CIO named.
Contact: John Bell, CIO: john.bell@montebelle.com
Angle: Proven AI ROI in appeals. Extension to other clinical workflows is the natural next step.
One tap to send. One tap to skip. That is the entire approval workflow.
The Point
We can build the same for your workflow.
Lead gen is one application. The same architecture applies to recruiting pipelines, partner sourcing, competitive monitoring, and procurement tracking. Any workflow where you currently spend hours on research and manual follow-up.
The components are the same. The data sources change. The integrations change. The outreach tone changes. The underlying agent, discover, enrich, decide, act, track, stays the same.
Recruiting
Monitor job boards for candidates matching your criteria. Enrich with contact details. Draft outreach. Track responses.
Partner Sourcing
Find adjacent businesses in your space. Qualify by audience and fit. Draft a partnership pitch. Log everything to CRM.
Competitive Intel
Track competitor announcements, pricing changes, and job postings. Deliver a daily briefing. Flag anything that needs a response.
Fixed price. Two to four weeks. You own the code.