Extracts deliverables, constraints, and explicit exclusions
Proposal Drafter
installed in 72 hours.
The trigger is your call ending. Scope, pricing, proof, and risk agents work the notes simultaneously, then a writer assembles them into your format with open questions listed at the top. You edit and send; it never sends.
45-minute discovery call ends; the transcript lands in the folder. 2,100 words: rebrand and website for a regional law firm, launch by March.
Draft proposal: three phases, $28,500, eleven-week plan, two matched case studies, four open questions (hosting, photography budget, stakeholder sign-off, content ownership).
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 when the call ends
The window where a proposal is worth most is the two hours after the call, which is exactly when nobody has time to write one.
- Transcript lands in the watched folder
- Tagged calendar event ends
- Notes forwarded to the intake address
In parallel Four agents dissect it at once
Each reads the same source for a different thing, which is why nothing gets flattened into generic agency prose.
Scope Pricing Prices each phase from your rate card, flagging anything the notes do not support
Proof Selects the two closest case studies from your library
Risk Lists what was said vaguely and what could blow the estimate
In series Then, in order
Assembly happens once, from four verified inputs, instead of one pass that invents the gaps.
Assembler Writes the proposal into your template with open questions at the top
Approval gate Where it meets you
This is the one template with no send capability at all. A proposal should leave with your name on it.
- Every proposal is a draft until you send it
- Nothing the notes did not cover gets priced; it becomes an open question
- Every number traces to a rate-card line
Hands off Then it hands off
The proposal becomes a tracked object rather than a file in a folder.
- Draft in your template within two hours of the call
- Registers the proposal with Quote Chaser if installed
- Logs which case studies get used and which never do
What fires it.
- A transcript or notes file lands in the watched folder
- A calendar event tagged as discovery ends
- You forward notes to the intake address
Your tools, not ours.
- Call notes or transcripts from Zoom, Fireflies, or Docs
- Your proposal template
- Rate card
- Case-study library
Where it stops and asks.
Every proposal is a draft until you send it. The system has no send capability for this template. Anything the notes did not cover appears as an open question, never as a guess.
Best for
- Agencies
- Consultants
- Architects and designers
- IT services
- Event companies
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
- 8 proposals a month × 3 hours saved × $150 an hour
What you receive.
- Template mapping
- Rate card and pricing rules
- Proof library indexed
- Open-questions checklist
- Draft-within-two-hours routine
$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. Proposal Drafter 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.
Does it sound like a template?
It uses your template and your past proposals as the voice model. The difference shows up in the specifics the four agents pull from the actual call.
What about pricing mistakes?
Every number traces to a rate-card line. The pricing agent flags anything the notes do not support rather than estimating it.
Can it send?
No. Not gated, not permitted, not built.
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