Reads the company and confirms the trigger is real and recent
Outbound Researcher
installed in 72 hours.
Every morning the system scans your target accounts for public triggers. For each hit, three agents research the company, the person, and your matching proof at the same time, then a writer produces one short evidence-based email for your approval.
Daily scan, 6:40 AM: a 40-person logistics company posted three warehouse roles in Reno this week. Account, contact, and proof agents run in parallel; brief ready in 90 seconds.
Hi Marcus, saw the three warehouse hires in Reno this week. When teams grow that fast, the onboarding gear order usually lags the start dates. We stock and kit PPE for exactly that; the first kit ships in 48 hours. Worth a ten-minute call?
The agent graph.
This is what you are buying. Not one prompt in a loop: a trigger that fires without you, agents that run at the same time, a chain that only starts once they all report, and one gate where the work meets a person.
Goes off Scans on its own every morning
The trigger is public and dated. No trigger means no email, which is why volume stays low.
- Daily target-account scan
- Hiring, funding, expansion, leadership, pricing, or tech changes
- Inbound reply on any prior draft
In parallel Three researchers per hit
Company, person, and proof are researched concurrently so a full brief exists before a word is drafted.
Account Contact Finds the right person and their published business contact route only
Proof Selects your most relevant matching work
In series Then, in order
One fact, one offer, one source. The compliance agent is separate so the writer cannot talk itself past the rules.
Writer Drafts a 105-word email: observed fact, why now, relevant offer
Compliance Checks published-route-only, unsubscribe, honesty of every claim
Approval gate Where it meets you
Every message is approved by a person. This is the template where that is not negotiable.
- You approve, edit, or reject each draft
- Published business contact routes only; never guessed patterns or bought lists
- One follow-up maximum, then a full stop
- Any clear no suppresses the account permanently
Hands off Then it tracks the outcome
Rejected drafts are training data, so the next batch is closer to what you would actually send.
- Logs approved, edited, and rejected drafts with reasons
- Routes replies to you
- Suppresses accounts that decline
What fires it.
- Daily scan of your target account list
- A watched account publishes a hiring, funding, expansion, or pricing change
- A prior prospect replies at any time
Your tools, not ours.
- Your ideal-customer definition
- Web research
- CRM
Where it stops and asks.
Every message is approved by a person before it sends. No scraped first-name theater; one checkable fact, one relevant offer, and only published business contact routes. A dedicated compliance agent can reject a draft the writer thought was fine.
Best for
- B2B services
- Agencies
- IT providers
- Consultants
- Wholesalers and distributors
The arithmetic, labeled as a scenario.
Every number here is illustrative. On kickoff we replace it with your inquiry volume, quote value, list size, or ticket count, and the system reports observed results after that.
- Formula
- 5 approved drafts a day × 20 days × 8% reply rate
What you receive.
- Ideal-customer definition
- Trigger map
- Daily research and drafting routine
- Approval queue
- Reply tracker and suppression list
$2,500
- 90-minute kickoff: accounts, voice, rules, and approval boundaries
- Triggers wired to your forms, inbox, calendar, and tools
- Every agent in the topology configured on your real history
- A dry run on past cases before anything reaches a customer
- An approval desk you can run from your phone
- Live within 72 hours of kickoff
$400 after 30 days
- Hosting, scheduling, and the trigger watchers, 24/7
- Claude usage up to 1,000 agent runs a month
- Rule, prompt, and routing changes whenever you ask
- A 30-minute tuning call every month
- Weekly report: what ran, what it decided, what it escalated
- Cancel anytime; the bots run to the end of the paid month
It hands off to these.
Bots chain. Outbound Researcher finishes its run by handing the result to the next system, so one trigger can carry a customer from first contact to a paid, reviewed job with no one retyping anything.
Plain answers.
Is this spam?
No. Low volume, human approval on every message, published business routes only, honest unsubscribe, and a full stop after one follow-up.
Where does it get emails?
Only from what the company publishes: contact pages, team pages, press contacts. The compliance agent rejects anything else.
Which triggers?
You pick from a menu on kickoff: hiring, funding, expansion, leadership, reviews, pricing, tech changes, events.
Buy the system.
Keep the desk.
One install for one business. The managed desk starts after 30 days, so the first month has one job: prove this system deserves to stay.
- Live within 72 hours of kickoff
- All 5 agents tuned on your history
- Triggers wired to your tools
- Approval desk on your phone
- Monthly tuning call
- Direct founder support