--- title: "Draft proposals from service, proof, and discovery files so each one fits the buyer" description: "A proposal from a bare prompt reads like a template. Give the AI three files: your services, your proof, and the discovery notes. Compare the drafts." canonical: "https://scalewithsearch.com/articles/ai-memory-before-and-after-proposals" date: "2026-01-28" modified: "2026-09-25" --- ## Site navigation - [Scale With Search](https://scalewithsearch.com/) - Real estate - Real estate - [Real estate](https://scalewithsearch.com/for/real-estate) - Work - Start here - [Send your brief](https://scalewithsearch.com/work#send-your-brief) - [Prepare your six-question brief](https://scalewithsearch.com/work#prepare-your-six-question-brief) - Build - [Site build, content library with SEO, signal desk](https://scalewithsearch.com/work) - For your business - Trades and home services - [Auto body and collision shops](https://scalewithsearch.com/for/auto-body-and-collision-shops) - [Foundation and home repair contractors](https://scalewithsearch.com/for/foundation-and-home-repair) - [Garage door and fencing contractors](https://scalewithsearch.com/for/garage-door-and-fencing-contractors) - [HVAC contractors](https://scalewithsearch.com/for/hvac-contractors) - [Janitorial and commercial cleaning companies](https://scalewithsearch.com/for/janitorial-and-commercial-cleaning) - [Locksmiths](https://scalewithsearch.com/for/locksmiths) - [Moving companies](https://scalewithsearch.com/for/moving-companies) - [Pest control companies](https://scalewithsearch.com/for/pest-control-companies) - [Plumbing and electrical contractors](https://scalewithsearch.com/for/plumbing-and-electrical-contractors) - [Restoration and water or fire damage companies](https://scalewithsearch.com/for/restoration-and-water-fire-damage) - [Roofing companies](https://scalewithsearch.com/for/roofing-companies) - [Towing companies](https://scalewithsearch.com/for/towing-companies) - [Tree services and landscaping companies](https://scalewithsearch.com/for/tree-services-and-landscaping) - [Solar installers](https://scalewithsearch.com/for/solar-installation) - [General contractors](https://scalewithsearch.com/for/general-contractors-and-construction) - [Paving, concrete, and flooring contractors](https://scalewithsearch.com/for/paving) - Practices and professional services - [Bookkeeping and tax practices](https://scalewithsearch.com/for/bookkeeping-and-tax-practices) - [Dental practices](https://scalewithsearch.com/for/dental-practices) - [Family and criminal defense law firms](https://scalewithsearch.com/for/family-and-criminal-defense-law-firms) - [Med spas and aesthetics practices](https://scalewithsearch.com/for/med-spas-and-aesthetics) - [Personal injury law firms](https://scalewithsearch.com/for/personal-injury-law-firms) - [Veterinary clinics](https://scalewithsearch.com/for/veterinary-clinics) - [Gyms and fitness studios](https://scalewithsearch.com/for/fitness) - [Therapy and outpatient health practices](https://scalewithsearch.com/for/therapy-and-outpatient-health) - [Medical billing companies](https://scalewithsearch.com/for/medical-billing) - [Insurance agencies](https://scalewithsearch.com/for/insurance-agencies) - [Financial advisors](https://scalewithsearch.com/for/financial-advisors) - [Property management companies](https://scalewithsearch.com/for/property-management) - [Recruiting and staffing agencies](https://scalewithsearch.com/for/recruiting-and-staffing) - [Architects and interior designers](https://scalewithsearch.com/for/architects-and-interior-designers) - [Logistics and supply chain companies](https://scalewithsearch.com/for/logistics-and-supply-chain) - Agencies, MSPs, and manufacturing - [IT and managed service providers](https://scalewithsearch.com/for/it-and-managed-service-providers) - [Machine shops and precision manufacturers](https://scalewithsearch.com/for/machine-shops-and-precision-manufacturing) - [Marketing agencies and freelancers](https://scalewithsearch.com/for/marketing-agencies-and-freelancers) - [SEO agencies and consultants](https://scalewithsearch.com/for/seo-agencies-and-consultants) - [Small manufacturers and fabricators](https://scalewithsearch.com/for/small-manufacturers-and-fabricators) - Restaurants, shops, studios, and nonprofits - [Restaurants and hospitality businesses](https://scalewithsearch.com/for/restaurants-and-hospitality) - [Retail stores and ecommerce sellers](https://scalewithsearch.com/for/retail-and-ecommerce) - [Photographers, event planners, and travel agents](https://scalewithsearch.com/for/photographers) - [Churches and nonprofits](https://scalewithsearch.com/for/churches-and-nonprofits) - [All industries](https://scalewithsearch.com/for/) - Learn - For your office - [Office job guides](https://scalewithsearch.com/guides/) - [Browser calculators](https://scalewithsearch.com/tools/) - Start here - [How it works](https://scalewithsearch.com/how-it-works) - [Free Starter Kit](https://scalewithsearch.com/kit/business-memory-starter-kit.zip) - [Synthetic specimen](https://scalewithsearch.com/specimen/working-session-specimen.zip) - Guides - [The Complete Guide to Business Memory for AI Agents](https://scalewithsearch.com/articles/business-memory-for-ai-agents-guide) - [The Complete Small-Business Guide to AI Agent Governance](https://scalewithsearch.com/articles/ai-agent-governance-guide-small-business) - [The Complete Guide to Leaving Vendor AI Memory](https://scalewithsearch.com/articles/leaving-vendor-ai-memory-guide) - Articles by cluster - [Business memory](https://scalewithsearch.com/articles/business-memory-for-ai-agents-guide) - [Agent governance](https://scalewithsearch.com/articles/ai-agent-governance-guide-small-business) - [Migration and ownership](https://scalewithsearch.com/articles/leaving-vendor-ai-memory-guide) - For machines - [llms.txt](https://scalewithsearch.com/llms.txt) - [llms-full.txt](https://scalewithsearch.com/llms-full.txt) - [Machine view](https://scalewithsearch.com/?view=machine) - Company - Evidence - [Proof](https://scalewithsearch.com/proof) - Company - [About](https://scalewithsearch.com/about) # Draft proposals from service, proof, and discovery files so each one fits the buyer. You ask an AI to write a proposal for a new client. The result looks professional: clean sections, a list of deliverables, a pricing table. Then you read it. It is generic. The case studies do not match the client's industry. The timeline is wrong. The price structure makes no sense for this kind of project. You spend the rest of the morning on a rewrite of the draft that was supposed to save you time. The comparison below uses a fictional firm and a fictional prospect to show what changes when the AI reads your files first. ## Before: the template problem Without context, the AI returns something like this: > **Proposal for Marketing Services** > > We're excited to partner with your organization to help you achieve your marketing goals. Our comprehensive approach includes: > > - Strategic planning and consultation > - Content creation and management > - Social media marketing > - Email campaigns > - Performance analytics and reporting > > **Timeline:** 3-6 months > > **Investment:** [a monthly price range so wide it means nothing] It could be for anyone: a plumber, a software company, a nonprofit. The deliverables are vague. The timeline is a guess. The price range is too wide to use. Worse, nothing in it speaks to this client. You know their pain point. You know why they called. You know what they need. The AI does not. ## After: the AI reads three files Same prompt: "Write a proposal for the new client." This time the AI first reads three files: your services and standard timelines, your case studies, and the discovery notes for this prospect. The draft: > **SEO Content Strategy for Riverside Physical Therapy** > > On our call last Tuesday, you said you rank on page 2 or 3 for your main service terms ("physical therapy [city]," "sports injury rehab"), and the patient volume does not justify your current ad spend. > > The issue isn't awareness. It's authority. Patients find competitors with deeper content, especially for injury-specific searches. > > **What we'll build:** > > - 16 condition-specific pages (rotator cuff injury, ACL rehab, and others) for high-intent searches > - A topic cluster that links your service pages to the new content > - An internal link structure that points authority at your booking page > > **Timeline:** 12 weeks, with 4 pages delivered every 3 weeks > > **Relevant work:** [case study from the proof file: client type, problem, measured result, source, and date] > > **Investment:** [standard price from the service file] > > If you want to reduce ad spend without losing patient flow, this plan gets you there. The problem, the solution, the proof, and the price, each drawn from a file. No filler and no vague promises. ## The three files behind the draft The service file: ```markdown ## SEO content strategy - 16 pages, condition-specific targeting - Topic cluster structure - 12-week delivery, 4 pages every 3 weeks - Price: see offers.md (the offer sheet is the authority) ``` The case study file: ```markdown ## Case: physical therapy clinic (fictional structure) industry:: healthcare, physical therapy problem:: page 2 rankings, high ad spend solution:: condition-specific content depth result:: result_source:: approved_for_proposals:: yes, with client permission on file ``` The discovery notes: ```markdown ## Riverside PT: discovery call, 2026-01-22 current_rankings:: page 2-3 for main terms pain_point:: ad spend not converting to patient volume goal:: reduce ad dependency, increase organic bookings budget:: range stated on the call; see crm record ``` Three files, about 300 words in total. That is the difference between a template and a proposal that speaks to the buyer. ## Keep proof tied to evidence Proof is the section most likely to go wrong. A model asked for "a relevant case study" will write one if the file does not supply it. A proposal with an invented result is worse than one with no result at all. Put three rules in the root context file: 1. Use a result only if it appears in the case study file with a source and a date. 2. Use a case study only if the file marks it approved for proposals. 3. If no case study matches the prospect, say so and leave the section for review. The guide to [AI brand memory for content creation](/articles/ai-brand-memory-content-creation) applies the same control to any claim. Each claim gets one authority file, and the draft stops when the authority is missing. ## Where the quality gap comes from The "before" proposal is not wrong. It is generic. The "after" proposal is specific. It speaks to the client's situation. It cites a relevant case. It uses the client's language, "patient inquiries," not "leads." It also makes a business case: "If you want to reduce ad spend without losing patient flow, this plan gets you there." You did not write that line. The model drew the value statement from the discovery notes. Discovery notes carry that weight, so capture them well. The guide to [AI memory for meeting notes](/articles/ai-memory-meeting-notes-decisions) shows how to keep the decisions from a call separate from the raw transcript. ## Revise the scope without a restart Two weeks later, the prospect wants a smaller package to start. Without files, you type "Revise the proposal for a smaller scope." The model asks what the original proposal said and what the new scope should include. You find the original, paste it, and explain the cuts. With files, you type "Revise the Riverside PT proposal for an 8-page starter package." The model reads the original proposal and the service file, halves the scope, and adjusts the timeline: > **SEO Content Strategy for Riverside Physical Therapy (Starter Package)** > > If you'd rather test the approach before you commit to the full build, here's a smaller option: > > - 8 condition-specific pages for your highest-volume service terms > - Internal links from the new pages to your booking page > > **Timeline:** 6 weeks, with 4 pages delivered every 3 weeks > > **Investment:** [starter price from the service file] > > This gets you about halfway to the ranking work we discussed. It is enough to show whether the content drives the patient inquiries you want. If it works, we scale to the full 16-page build. In this example, the starter package costs a little over half the price of the full build. The draft framed the smaller scope as lower risk, and it kept the original goal and the proof point. You did not ask for that framing; the files supplied the facts that made it possible. Save the starter version as its own file next to the original, such as `riverside-pt-starter.md`. Add a line to the prospect file that names both versions and the one the client chose. The next revision then starts from the version the client saw last. ## Measure the time Take one example. A proposal from scratch takes two hours. A proposal drafted from the three files takes fifteen minutes to review and send. At two proposals a week, that saves 3.5 hours a week, or about 182 hours a year. Time is not the only return. A specific proposal shows the buyer that you understood the problem. Track your own win rate by proposal type for a quarter before and after the change. Do not borrow someone else's close rate; your market and offer decide yours. ## Build the three files Create these files once: 1. A service file: offerings, deliverables, timelines, and a pointer to the current offer sheet. 2. A case study file: results by industry, client type, and problem, each with a source and a date. 3. A prospect file for each opportunity: discovery notes, pain points, and budget range. Each file takes 20 to 30 minutes to build. After that, every proposal draws on the same record. You stop rewriting the same case study five ways, and you stop forgetting what the prospect said on the call. Keep a person on the final step. Check the scope, the price, and every proof claim against its source before the proposal goes out. The guide to [who approves what an AI agent sends](/articles/who-approves-what-an-ai-agent-sends) shows how to bind that approval to the exact document. For recurring proposal work, write the job as a brief, not a one-line prompt; the article [a brief is not a prompt](/articles/brief-vs-prompt) shows the difference. ## Related: AI memory - [Build a proposal memory file so AI drafts proposals in your format](/articles/ai-memory-for-proposal-writing) - [Build an outreach file so AI writes cold emails from your prospect research](/articles/ai-memory-for-sales-outreach) ---- ```text .|########||. .|########||. .|########||. |##||. .||##|. |##||. .||##|. |##||. .||##|. |#|. .|#|. |#|. .|#|. |#|. .|#|. |#| |#| |#| |#| |#| |#| .#| |#. .#| |#. .#| |#. .#. .#| .#. .#| .#. .#| |#. .#| |#. .#| |#. .#| |# ...... #| |# ...... #| |# ...... #| .# ||#########| #| .# ||#########| #| .# ||#########| #| .#. |######||######|. .#. .#. |######||######|. .#. .#. |######||######|. .#. #. .##|###|##|#|######| .# #. .##|###|##|#|######| .# #. .##|###|##|#|######| .# || |##|#||||||||||||#||#| || || |##|#||||||||||||#||#| || || |##|#||||||||||||#||#| || # |#||||||||||||||||||||#| #. # |#||||||||||||||||||||#| #. # |#||||||||||||||||||||#| #. || |#||||||||||||||||||||||#| || || |#||||||||||||||||||||||#| || || |#||||||||||||||||||||||#| || # .#||||||||||||||||||||||||#| # # .#||||||||||||||||||||||||#| # # .#||||||||||||||||||||||||#| # || ....|||#||||||##|#|||#|#||##||||....|. || || ....|||#||||||##|#|||#|#||##||||....|. || || ....|||#||||||##|#|||#|#||##||||....|. || #. . ....|# ....#||| ||| .#||| ....#. .# #. . ....|# ....#||| ||| .#||| ....#. .# #. . ....|# ....#||| ||| .#||| ....#. .# # . ||||#| .#####|| . .#| .#||| ||||# #. # . ||||#| .#####|| . .#| .#||| ||||# #. # . ||||#| .#####|| . .#| .#||| ||||# #. .| ||||| #. |#|||||. || #. |#||. .||||| || .| ||||| #. |#|||||. || #. |#||. .||||| || .| ||||| #. |#|||||. || #. |#||. .||||| || || |.... #. ....|#. |. ...|. ....|| || || |.... #. ....|#. |. ...|. ....|| || || |.... #. ....|#. |. ...|. ....|| || #. .||||||##||||||##||####|||||||#||||||#| .# #. .||||||##||||||##||####|||||||#||||||#| .# #. .||||||##||||||##||####|||||||#||||||#| .# # .||####|###########################|. # # .||####|###########################|. # # .||####|###########################|. # # .#||||||.#.|| # |. ..# #| #|||||#| # # .#||||||.#.|| # |. ..# #| #|||||#| # # .#||||||.#.|| # |. ..# #| #|||||#| # # .#|||||| .. |# ## |#| ...#|#|||#| # # .#|||||| .. |# ## |#| ...#|#|||#| # # .#|||||| .. |# ## |#| ...#|#|||#| # # .#|||#|# .# .#| #| ##|.#..#|||||#| # # .#|||#|# .# .#| #| ##|.#..#|||||#| # # .#|||#|# .# .#| #| ##|.#..#|||||#| # # .#||||||############|######|||||#| # # .#||||||############|######|||||#| # # .#||||||############|######|||||#| # # |...||#||||||#||||#|#||||||#|||||#||| |.| # # |...||#||||||#||||#|#||||||#|||||#||| |.| # # |...||#||||||#||||#|#||||||#|||||#||| |.| # #. .. ||||# .|||##|. |#| .|| || .|||#. #| # .# #. .. ||||# .|||##|. |#| .|| || .|||#. #| # .# #. .. ||||# .|||##|. |#| .|| || .|||#. #| # .# || | ...|| ...##| | #| .|. |. ##### .. .| || || | ...|| ...##| | #| .|. |. ##### .. .| || || | ...|| ...##| | #| .|. |. ##### .. .| || || ||||| || ||||#| . |. |. |#. ||||| |#| || || || ||||| || ||||#| . |. |. |#. ||||| |#| || || || ||||| || ||||#| . |. |. |#. ||||| |#| || || .# |.....#|....|#.||||.|||##.|#|....||.#||.#. #. .# |.....#|....|#.||||.|||##.|#|....||.#||.#. #. .# |.....#|....|#.||||.|||##.|#|....||.#||.#. #. #.|||||||#############################| ||| .# #.|||||||#############################| ||| .# #.|||||||#############################| ||| .# || ##||#||#||||||#||#||#||#||##. || || ##||#||#||||||#||#||#||#||##. || || ##||#||#||||||#||#||#||#||##. || # .#|||||||||#||#|||||||||||#| # # .#|||||||||#||#|||||||||||#| # # .#|||||||||#||#|||||||||||#| # || |#||||||||||||||||||||||#| || || |#||||||||||||||||||||||#| || || |#||||||||||||||||||||||#| || .# |#||||||||||||||||||||#| #. .# |#||||||||||||||||||||#| #. .# |#||||||||||||||||||||#| #. || |#||||||||||||||||||#| || || |#||||||||||||||||||#| || || |#||||||||||||||||||#| || #. .######|#|#########| .# #. .######|#|#########| .# #. .######|#|#########| .# .#. |#####||||#####| .#. .#. |#####||||#####| .#. .#. |#####||||#####| .#. |# ||########|| #. |# ||########|| #. |# ||########|| #. |# ...... #| |# ...... #| |# ...... #| |#. .#| |#. .#| |#. .#| |#. .#. |#. .#. |#. .#. .#| |#. .#| |#. .#| |#. |#| |#| |#| |#| |#| |#| .|#|. .|#|. .|#|. .|#|. .|#|. .|#|. |##||. .||##| |##||. .||##| |##||. .||##| .||########||. .||########||. .||########||. Scale With Search 2026 [scalewithsearch.com](https://scalewithsearch.com) ```