Re-reads scope, price, and what has already been said in the thread
Quote Chaser
installed in 72 hours.
Each quote you send becomes a tracked object with its own timer. On day 2, 5, and 10 the system wakes itself, re-reads the quote and anything that changed, and sends the right touch. Replies are classified before they reach you.
Quote #2231, roof repair, $3,850, sent Tuesday. Day-2 timer fires Thursday 9:00 AM with no reply on the thread.
Hi Luis, following up on the $3,850 repair quote for the north slope. One thing worth knowing: the flashing work we included is what usually fails first on that roof type, so it is in the price on purpose. Happy to walk through it on a ten-minute call, or we can hold Monday for the crew. — Sam
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 Two ways it fires
One event-driven, one time-driven. The timers are the point: nothing has to remember to follow up.
- New quote detected by forwarding rule or integration
- Its own day-2 / day-5 / day-10 schedule
- Inbound reply on any tracked quote
In parallel On each wake, two agents at once
Both read fresh state before a word is written, so a touch never references stale facts.
Quote reader Signal watcher Checks for anything that changed: a reply, a site visit, a competing bid mentioned
In series Then, in order
Touch choice depends on state, and drafting depends on touch choice.
Sequencer Picks which of the three touches is due, or stops the sequence entirely
Writer Drafts that touch with one genuinely useful detail from the actual quote
Reply classifier On inbound, sorts into: question, objection, price negotiation, or no
Approval gate Where it meets you
The chase runs itself. The conversation does not.
- Auto-send: the three scheduled touches from your approved templates
- Hold and route to you: anything mentioning price, scope, timing, or a competitor
- Hard stop: any clear no, marked lost, never contacted about that quote again
Hands off Then it closes the loop
Every quote reaches a terminal state, which is what makes the weekly report real.
- Writes won / lost / no-response and the reason
- Hands won jobs to Review Engine if installed
- Weekly won-lost report with the objection breakdown
What fires it.
- A quote leaves your outbox or quoting tool
- The day-2, day-5, and day-10 timers fire on their own
- A prospect replies at any hour
Your tools, not ours.
- Your quoting tool or PDF quotes
- CRM or a spreadsheet
- Calendar
Where it stops and asks.
Follow-ups auto-send from your approved template set. The reply classifier never answers a pricing or scope question itself; it routes to you with a suggested answer. It never changes a number.
Best for
- Contractors
- HVAC, plumbing, roofing
- Agencies
- Printers and sign shops
- Event vendors
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
- 25 open quotes a month × 8-point lift in close rate × $2,400 average quote
What you receive.
- Quote intake by forwarding rule or integration
- The three-touch sequence in your voice
- Objection playbook built from your real past quotes
- Pipeline sheet with stage and reason
- Weekly won-lost 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. Quote Chaser 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.
Will it hound people?
Three touches over ten days, then it stops and closes the loop. Anyone who says no is marked lost by the classifier and never contacted again about that quote.
Can it negotiate?
No. That is a hard routing rule, not a prompt instruction. Price, scope, and timing replies never reach the writer.
What if I quote by phone?
You forward a one-line summary or log it in the sheet. The trigger fires on that.
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