Step01
Photograph Your Physical Items
Photograph one shelf, cupboard, or group of related items at a time. Include readable labels and enough surrounding context to identify the location. Name each photo set with the room and storage area.
BeginnerPersonal
Create an AI-Powered Inventory of Your Physical Items
Photograph the books, toys, and learning materials hidden in your cupboards. A vision agent turns the images into a searchable inventory, connects owned items to lesson plans, and can print a photographed worksheet by voice.
Source episode · 36:30
How I AI: Jesse Genet’s 5 OpenClaw Agents for Homeschooling, App Building, and Physical Inventorieswith Claire Vo
Jesse photographs her educational supplies, Sylvie identifies each item and age range, links the inventory to lesson plans, and prints a photographed worksheet on request.
Before you start
What you need
- Photos of physical items grouped by room, cupboard, or category
- A vision capable agent
- A Markdown or Obsidian inventory
- Optional printer access for the agent
What you’ll make
A searchable inventory with item identity, category, age range, description, location, and links to relevant plans or activities.
Tools used
Step by step
The workflow
Follow the sequence once, then adapt the prompts, checks, and handoffs to your own setup.
5 steps
Step02
Task the Agent to Create an Inventory
Send the photos to a vision capable agent and ask it to create inventory records. Jesse gave Sylvie only the images and a short request, then received names, types, age ranges, and descriptions.
Example prompt
Create an inventory of the learning supplies in these photos. For each distinct item, record its name, category, suggested age range, short description, quantity, physical location from the photo set name, source photo, and confidence. Mark uncertain identifications for confirmation instead of guessing.
Step03
Review the AI-Generated Inventory
Review uncertain records and correct names, ages, quantities, or locations. Merge duplicates while preserving the number owned and every place the item is stored. Keep the source photo linked to each record.
Example prompt
Create a structured inventory in markdown from the attached photos of my learning supplies. For each item, list the following: - Item Name - Item Type (e.g., Book, Toy, Art Supply) - Suggested Age Range - Description Photos are here: [upload or link to photos]
Step04
Connect Inventory to Daily Plans
Connect the inventory to planning. Ask the agent to recommend things you already own for a lesson, topic, child, or skill, and require it to include the storage location so the suggestion is immediately usable.
Example prompt
For the next lesson on [topic or skill], search the physical inventory and suggest up to five materials we already own. Explain how each supports the lesson, include its age fit and exact storage location, and do not recommend unconfirmed items.
Step05
Establish a Hands-Free Printing Loop
For a hands free print loop, give the agent access to a local printer command. From a phone, photograph a worksheet and ask the agent to crop, straighten, improve contrast, fit it to the paper, and print one copy.
Example prompt
Prepare the attached worksheet photo for printing. Crop to the page edges, deskew it, improve readability, fit it to US Letter with safe margins, and print one copy on the configured printer. Report the printer and job status.
This simple automation removes multiple small steps (scanning, emailing, downloading) and significantly reduces friction for day-to-day tasks.
What good looks like
- Every record points to a source photo and physical location.
- Uncertain identifications are marked for confirmation.
- The agent can retrieve useful items by topic, child, or activity.
- A photographed worksheet can be prepared and printed with one request.
Build your next product with ChatPRD
Turn an idea into a PRD, user stories, and a plan.
After the steps
Runbook notes
How to recover when the loop fails and where human judgment helps.
Recover
If it goes sideways
- The agent confidently misidentifies an item
- Require confidence or an uncertainty note, preserve the source photo, and confirm ambiguous products before relying on age or usage guidance.
- The same item appears more than once
- Use location, visible labels, and source photo references to merge duplicate records while preserving quantity.
- The inventory knows the item but not where to find it
- Photograph one cupboard or shelf at a time and attach a stable location label to every image and record.
- The printer receives a cropped or unreadable page
- Ask the agent to deskew, crop, increase contrast, fit the page to printable margins, and show the prepared file before sending it to the printer.
Keep building
Related workflows
advancedPersonalClaude
Create a Meta-Workflow to Continuously Improve Your AI Assistant's Performance
Design a weekly meta-workflow that analyzes your interactions with your AI assistant to make it smarter. This system learns your writing style from edits, suggests new automations for repetitive tasks, and helps you filter valuable AI techniques from hype.
Open
intermediateProductClaudeGranola
Build a Self-Improving AI Morning Brief to Capture Action Items and Learn Company Jargon
Create a daily AI workflow that summarizes yesterday's meetings, identifies urgent tasks, and proactively learns internal company terms it doesn't understand. This keeps your AI assistant's knowledge current and highly relevant to your work.
Open
intermediateProductClaudeNotion+1
Automate Your Weekly Planning with an AI-Powered PM Assistant
Build a recurring AI task that automatically gathers updates from your calendar, Slack, and notes to suggest weekly priorities and prepare you for upcoming meetings. Start every Monday with a clear, comprehensive plan without the manual effort.
Open
Start shipping
better products.
Join 100,000+ product managers who use ChatPRD to write better docs, align teams faster, and build products users love.
Free to start
No credit card
SOC 2 certified
Enterprise ready