Use Claude to map a garden from nursery photos
Emily Gransky and her partner photographed plants they liked during a nursery visit, ending with eighty-five images and no garden plan. Her linked article's accessible introduction explains that the choices had already been narrowed by shade needs and what they wanted the plants to attract or repel.
Suggested prompt
Suggested prompt written by Agents In Use, not the source author. Replace bracketed inputs and review tool permissions first.
Read these nursery plant photos and labels. Build a price spreadsheet by garden bed, a map organized by depth and bloom time, and an HTML plant guide. Update all outputs when I add basil.
Reach people exploring AI agents
See placements →What happened
Garden-bed spreadsheet, depth-and-bloom map and HTML plant guide from 85 photos, with updated totals and layout after basil was added.
Reported by Emily GranskyHow the agent did it
- Photograph nursery plants and provide the garden's constraints.
- Read tags, research prices and organize choices by bed and bloom timing.
- Re-run the outputs when the household adds another plant.
Where a person stepped in
Gransky supplied photos and requested the basil revision; no separate botanical validation checkpoint is described.
Emily Gransky and her partner photographed plants they liked during a nursery visit, ending with eighty-five images and no garden plan. Her linked article's accessible introduction explains that the choices had already been narrowed by shade needs and what they wanted the plants to attract or repel.
She used Claude Code to turn that collection into planning material. The agent read nursery tags from the images, looked up prices and produced a spreadsheet organized by garden bed. It also made a visual map arranged around depth and bloom time, plus an HTML plant guide. These were complementary outputs: cost information by bed, a layout and reference material for the selected plants.
When her partner suggested basil at the last minute, Gransky asked Claude to run the work again with that addition. She reports that the totals updated and the map changed without breaking the outputs. That revision is the concrete continuation of the initial planning task.
The account describes generated plans and the successful basil update. It does not report a planted garden, independently checked botanical recommendations or measured savings. No separate review checkpoint for each plant choice is described, so the evidence supports a planning package rather than a verified growing result.
Prompt
Suggested prompt (written by Agents In Use, not the author's)
Source: www.linkedin.com · Emily Gransky
Frequently asked questions
What did the photos contribute?
Claude read nursery labels rather than starting from an unspecified list of plant names.
How was the plan organized?
The spreadsheet used garden beds, while the visual map considered depth and bloom time.
What happened when basil was added?
Gransky asked for a rerun and reports that the totals and map updated without breaking.
More details
About this account
Claude read plant tags, researched prices and generated a spreadsheet, visual map and HTML guide.
Firsthand source opened and read. Suggested prompt written by us from the reported workflow; no original task prompt is quoted.
Credit: Emily Gransky
Source published 12 Apr 2026
Source checked 14 Oct 2026
Tools and topics
Claude Code · Plant photographs · Spreadsheet · HTML
Garden layout · Nursery plant tags · Bloom timing
Editorial completeness: 100/100. Measures documented fields, not agent performance or verified outcomes.