Part 1 The problemWhy teams need this
01 · THE PROBLEM
A single site visit can produce hundreds of photos, and someone has to label every one before the report can be written. It's slow, dull work that nobody does well at photo number 300.
Part 2 How it worksWhat it does, step by step
02 · WHAT IT DOES
For the same reserve-study firm. Point it at a property and it works through every uncategorised photo: AI identifies the component in each image, the record is updated, and the property's photo stats are recalculated at the end.
03 · HOW IT RUNS
Step by step, as built.
Pick the property
A form starts the run and loads the property's details.
Find unsorted photos
Lists every photo for that property that hasn't been categorised.
Categorise one by one
Each image is downloaded and Gemini assigns its component category against a fixed schema.
Update the totals
Photo records are updated, then the property's category stats are recalculated.
04 · TOOLS AND APPS
Built around the systems already in the process.
05 · 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
06 · 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.
07 · 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
- 0.3 people
- Gross value
- $18,000
- Running cost
- −$480
- Return per $1 of running cost
- $37.5
The math: 5,000 site photos × 0.5 min × 12 months × 90% ÷ 60 = 450 hours a year × $40/hour = $18,000. Net value = gross value − $480 running cost a year.
08 · 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.
