Case Study

From Handwritten Notes to Client-Ready Proposal

An AI Document Automation Build

A portfolio build by Finlay Systems — this documents an advanced-tier portfolio project built on a fictional-but-realistic scenario, not a paid client engagement. The client context, quote, and outcomes below are illustrative of the pattern, not a real business's figures.
AirtableZapierOpenAI GPT-4o (Vision)Google Docs

Client context

A fictional-but-realistic scenario, built for an advanced-tier portfolio project, not a paid engagement: a mid-sized general contracting business, 4 to 10 employees, closing nearly 100 jobs a year. The owner writes every estimate personally. Site visits happen during business hours; admin, invoicing, and estimate writing happen at night and on weekends.

The challenge

Only the owner produces estimates, and estimates are the single most important document in the sales pipeline, but writing one from scratch competes with every other demand on the owner’s evenings and weekends. Site visits generate handwritten notes; turning those notes into a polished, client-ready proposal is a manual, repetitive task that has to happen after hours, and jobs get lost when the follow-up that should happen a few days later slips through the cracks entirely.

Only the owner produces estimates, and estimates are the single most important document in the sales pipeline.

The cost of the problem

A single proposal took 30 to 60 minutes of focused evening work: reading back handwritten notes, typing them up, writing the client-facing narrative, and remembering to schedule a follow-up. The course framework this build was created for estimated $8,000–$16,000 in annual ROI for a business like this from the core workflow alone, driven by faster response time on estimates, reduced admin fatigue, and fewer forgotten follow-ups.

The goal

Remove the manual step entirely between a jobsite visit and a client-ready proposal: a photo of handwritten notes should become a formatted document and a scheduled follow-up without the owner typing anything, while keeping a human review step before anything reaches a client.

The existing workflow

Before
30–60 min per proposal
  1. 1Site visit, notes written by hand
  2. 2Owner sits down at night or on a weekend
  3. 3Types up the notes from scratch
  4. 4Writes the full proposal narrative manually
  5. 5Sometimes forgets to schedule the follow-up
After
~2 min per proposal
  1. 1Photo of handwritten notes, uploaded from the field
  2. 2AI transcribes and extracts the details
  3. 3AI drafts the proposal narrative and a follow-up message
  4. 4Owner reviews the finished Google Doc
  5. 5Follow-up is already queued, nothing forgotten

The AI system

Field notes written by hand during a site visit → photographed and submitted through a mobile form → the system transcribes the handwriting, extracts customer details, writes a polished project narrative, and drafts a follow-up message → a formatted Google Doc is generated and the link, plus the follow-up draft, is written back to the source record — a client-ready proposal minutes after the site visit ends, with a prewritten follow-up message saved and ready to send.

Implementation

Five layers, in order:

1
Input layer
A public Airtable form accepting photo uploads from the field.
2
Data layer
An Airtable base storing every submission and its status.
3
Orchestration layer
A seven-step Zap watching Airtable, polling every two minutes and filtering on status to avoid reruns on unrelated edits.
4
AI layer
Multiple GPT-4o calls, one per subtask: handwriting transcription, structured data extraction, narrative generation, follow-up drafting — each independently debuggable.
5
Output layer
A formatted Google Doc, with the link and follow-up draft written back to Airtable and status set to complete.
  • Airtable over Google Sheets for native attachment handling, structured fields, and production-ready mobile forms without custom front-end work.
  • Zapier for orchestration, trading some cost-at-scale for zero custom API plumbing (Make or n8n become more attractive as run volume grows).
  • Multiple small GPT calls instead of one giant call — each subtask gets its own prompt, costing slightly more in tokens but making every step debuggable in isolation.
  • HTML tags for Google Doc formatting — wrapping section titles in <h1>/<h2> tags produces properly styled headings with no template files.

Human oversight and safeguards

  • Explicit fallback instructions in the extraction prompts prevent the model from hallucinating customer details it can’t confidently read.
  • The finished document is reviewed before it reaches a client — the automation removes the repetitive first draft, formatting, and data-entry work, not the human judgment call on what actually gets sent.
  • Status-based triggering, not view-based, so the workflow only fires on genuinely new submissions and doesn’t rerun on unrelated edits later.
  • Memory tied to the Airtable record ID, so the AI never mixes details between two different projects.

Results

0–0 min → ~0 min

Time from jobsite notes to a formatted, client-ready draft

$0k–$0k/yr

Estimated annual ROI from the core workflow, per the course framework this build follows

<$0

Typical run cost per document generated

~0 hrs

Time to build this portfolio version end to end

Business impact

The Power-Up version removes the data-entry step entirely: a proposal that used to take 30 to 60 minutes of focused evening work becomes a two-minute background process that starts from a jobsite photo. For a business where the owner is the only person who can write an estimate, that’s evenings and weekends back, faster turnaround on the document that actually closes jobs, and a follow-up that no longer depends on someone remembering to send it.

Client quote

This is a portfolio-demo scenario built on a fictional-but-realistic business, not a real client engagement, so there’s no real client quote to include here honestly.

What happened next

This is a completed portfolio build documenting the advanced tier of a course framework, not a live production system with an ongoing rollout to report on. The same architecture — photo in, structured extraction, drafted narrative, human review, document out — is what a real NYC real estate team would build on for listing write-ups, buyer recaps, and transaction follow-ups; that build is available on request.

What this means for NYC real estate teams

The same architecture applies directly to listing write-ups, buyer tour recaps, property briefings, offer summaries, and transaction follow-ups. A high-volume team lead managing 20 active listings is constantly context-switching between showings and write-ups — the opportunity is the same as the contractor scenario: automate everything between raw field notes and the finished client-facing document.

This is the kind of practical AI workflow Finlay Systems builds for real estate teams and service businesses. If your team is losing hours each week to repetitive work, I can help identify what is worth automating.

Book an Intro Call

Frequently Asked Questions

What is AI document automation?

AI document automation is the process of using AI to turn raw inputs, such as notes, forms, emails, or uploaded files, into structured documents like proposals, recaps, reports, briefs, or follow-up messages.

What does this AI document automation workflow do?

This workflow turns a photo of handwritten jobsite notes into a formatted, client-ready Google Doc proposal. It also extracts key details, creates a polished project narrative, drafts a follow-up message, and writes the final document link back into Airtable.

What tools were used in this build?

The workflow used Airtable, Zapier, OpenAI GPT-4o with Vision, and Google Docs. Airtable handled the form and database, Zapier orchestrated the workflow, GPT-4o processed the handwritten notes, and Google Docs generated the final proposal.

Can this workflow read handwritten notes?

Yes. The workflow uses GPT-4o with Vision to read a photo of handwritten notes and convert the content into clean text that can be used for document generation.

Does the user have to type anything?

No. The user writes notes by hand, uploads a photo through a mobile form, and the automation handles the transcription, data extraction, narrative writing, document creation, and follow-up draft.

Why use Airtable instead of Google Sheets?

Airtable handles attachments, structured fields, and mobile-friendly forms more easily than Google Sheets. For this workflow, Airtable made it easier to accept a photo upload, store project details, and track the automation status in one place.

Why use multiple GPT calls instead of one large prompt?

Multiple smaller GPT calls make the workflow easier to test, debug, and control. Each step has one job, such as transcription, customer detail extraction, project narrative writing, or follow-up drafting. This reduces the risk of messy or unreliable output.

How can this apply to real estate teams?

The same workflow pattern can help real estate teams turn raw notes into polished client-facing documents, including listing write-ups, buyer tour recaps, property briefings, offer summaries, transaction updates, and follow-up emails.

What types of real estate documents could be automated?

Examples include listing descriptions, property feature sheets, showing recaps, buyer tour summaries, internal team briefings, open house follow-ups, offer summaries, seller updates, and transaction status reports.

Does AI replace the need for human review?

No. The output should still be reviewed before being sent to a client. The goal is to remove the repetitive first draft, formatting, and data-entry work, not to remove human judgment.

How much does this type of automation cost to run?

In this build, the ongoing run cost was typically well under a dollar per document generated, using free tiers of Airtable and Google with small pay-per-use costs for OpenAI API calls.

How long did this build take?

This portfolio build took approximately three hours to create. A client version may take longer depending on the tools, document requirements, review steps, formatting needs, and integrations involved.

What is the main benefit of this workflow?

The main benefit is speed. A document that might normally take 30 to 60 minutes of focused admin work can become a short background process that starts from a simple phone photo.

What does Finlay Systems do?

Finlay Systems provides AI consulting for high-volume NYC real estate teams, including AI training, workflow automation, strategy, implementation, and practical AI systems that reduce manual admin work.