Part 1 The problemWhy teams need this
01 · THE PROBLEM
Every reserve study starts with a site visit and ends with days of desk work: sorting photos, typing up notes, describing each component. At 1,200 reports a year, that write-up time is the whole business's bottleneck. Moving it from days to minutes changes how many studies the same team can deliver.
Part 2 How it worksWhat it does, step by step
02 · WHAT IT DOES
Built for a reserve-study firm that produces over 1,200 reports a year. An inspector uploads the site-visit photos and their handwritten notes. AI analyses every photo, reads the measurements off the notes, builds the component records, writes the report narratives and assembles an HTML report ready for review.
03 · HOW IT RUNS
Step by step, as built.
Upload the visit
One form takes the property details, the photos and photos of the handwritten notes.
Analyse every photo
Each photo is uploaded, analysed by Gemini against a fixed schema, and saved with its findings.
Read the notes
Measurements and observations are read off the handwritten notes with OCR and stored against the property.
Build the components
Photo findings and note data are combined into component records, and AI writes the narrative for each.
Assemble the report
The narratives and photos are pulled together into an HTML report, ready for the analyst to review.
04 · WHERE A PERSON STAYS IN
The machine drafts. A person decides.
An analyst reviews and signs off every report. The workflow removes the typing, not the professional judgement.
05 · TOOLS AND APPS
Built around the systems already in the process.
06 · WHEN SOMETHING BREAKS
Failure is designed in.
Standard on every build
- Schema validation before downstream writes
- Retry and error routes for external API failures
- Duplicate-safe processing and idempotent updates
- Human approval where the action carries business risk
- Execution logging for support and audit review
Part 3 The impactWhat it's worth, and how we'd build yours
07 · PROJECTED IMPACT
What it should change in the business.
Projections for a typical deployment. The calculation below shows the math, and you can put in your own numbers.
08 · ROI CALCULATION
How it pays back in your business.
The starting numbers are a hypothetical deployment sized to the projections above. Change any of them to your own volumes and costs, and the math updates underneath.
- Full-time equivalent freed
- 1.6 people
- Gross value
- $115,200
- Running cost
- −$1,800
- Return per $1 of running cost
- $64
The math: 100 reserve-study reports × 240 min × 12 months × 60% ÷ 60 = 2,880 hours a year × $40/hour = $115,200. Net value = gross value − $1,800 running cost a year.
09 · HOW WE'D BUILD YOURS
How we'd build yours.
- Discover: map the current process, systems, volumes, owners and exceptions.
- Design: define the canonical data model, approvals, retries and system boundaries.
- Build: implement credentials, nodes, validation and observable error routes.
- Prove: run controlled data through success, duplicate and failure scenarios.
- Operate: publish runbooks, ownership and measurable service levels.
