Parses the request into job type, urgency, address, and constraints
Inbound Lead Responder
installed in 72 hours.
A watcher fires the moment a form, email, or missed-call text lands. Intake, research, and capacity agents run at the same time, a drafting agent merges their work, and your policy decides whether it sends itself or waits for your tap.
Website form, 8:47 PM: "Need a quote for a water heater replacement, 50 gal gas, Folsom. How soon can someone come out?"
Hi Dana, thanks for reaching out. A 50-gallon gas water heater replacement in Folsom typically runs $1,900 to $2,600 installed, depending on venting and code updates. We can have a tech out tomorrow at 9:00 AM or 1:30 PM to confirm the exact price on site. Which works? — Mike, Northside Plumbing
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 Fires on the event
No human starts this. The watcher runs 24/7 and the clock starts the second the inquiry lands.
- Form webhook
- Inbox filter
- Missed-call SMS
- Nightly reconciliation sweep
In parallel Three agents, at once
They run concurrently, so the whole stage costs one agent's worth of wall-clock time, not three.
Intake Research Checks whether this is an existing customer and what you did for them before
Capacity Reads the calendar, service area, and price rules for this job type
In series Then, in order
The drafting agent cannot start until all three have reported, and the policy agent cannot start until the draft exists.
Reply writer Merges the three inputs into one specific answer in your voice
Policy check Tests the draft against your rules: area, price ceiling, tone, promises
Approval gate Where it meets you
Routine work sends itself. Everything else waits, with the draft ready to approve in one tap.
- Auto-send: in area, inside your price band, standard job type
- Hold: out of area, above your dollar threshold, complaint or emotional tone, anything the research agent flagged
Hands off Then it arms the next run
The system schedules its own future work rather than waiting to be asked again.
- Writes the lead to your sheet or CRM
- Schedules a 48-hour follow-up agent if no reply
- Hands won leads to Quote Chaser if installed
What fires it.
- A form submission hits the webhook
- An email arrives matching your inbound filter
- A missed call produces a text
- Nightly sweep for anything the watchers missed
Your tools, not ours.
- Website forms
- Gmail or Outlook
- Missed-call SMS
- Google Calendar or Calendly
- Your price ranges and service area
Where it stops and asks.
You set the policy: auto-reply for routine requests inside your price rules; hold for review on anything out of area, over a dollar threshold, or emotionally loaded. The policy agent is a separate agent from the writer on purpose, so the thing checking the work is not the thing that produced it.
Best for
- Home services
- Clinics and practices
- Agencies
- Law firms
- IT providers
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
- 40 inquiries a month × 15-point lift in booked rate × $600 average job
What you receive.
- Trigger watchers on forms, inbox, and SMS
- All five agents configured on your real past inquiries
- Auto-send policy and hold rules
- Lead log in your sheet or CRM
- Weekly speed-to-lead report
$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. Inbound Lead Responder 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.
Why five agents instead of one prompt?
Because they fail differently. A single prompt that reads the calendar, recalls the customer, and writes the reply will quietly get one of the three wrong. Separate agents produce separate, checkable outputs, and the policy agent audits the result.
Does it pretend to be a person?
No. It signs as your business and says it is an assistant if asked. Most customers just want a fast, useful answer.
What happens when it does not know?
The policy agent holds it. The customer gets an honest acknowledgment with a real timeframe, and you get the draft.
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