For the small-batch ceramic artist, glaze testing is a critical, yet often chaotic, process. The key to perfecting your signature surfaces lies not just in mixing, but in meticulous documentation. Traditionally, this involves disorganized photos, scattered notes, and lost context. This is where a structured visual AI system transforms your practice from guesswork to precision science.
The Problem: Disconnected Data
Your current system likely suffers from disconnection. A beautiful test tile photo is divorced from its recipe, firing log, and measured outcomes. Images are inconsistent—shot on different backgrounds under varying light, making true comparison impossible. Descriptions are subjective (“cranberry red” vs. “burgundy”), and this data is ultimately unsearchable. You cannot query, “Show me all glazes with a gloss reading >70 GU that are stable on vertical surfaces.”
The Solution: A Structured Visual Log
The fix is a standardized, digital workflow. Your core tool is a free digital notebook like Obsidian or Notion, or even a dedicated album in Google or Apple Photos. Consistency is paramount. Always use a simple, non-reflective mid-grey matte backdrop for all photos.
Pre-Firing Protocol
Before a test even goes into the kiln, create a new log entry. Assign a unique Test ID (e.g., 250415-Shino01). Link it to your master recipe file. Document application notes: dip or brush? How many coats? Was it sieved? This creates an auditable trail.
Post-Firing Analysis & AI Tagging
After firing, photograph the tile on your standard background. In your log, fill in the critical data fields: Firing Log (cone, atmosphere, peak temp), Performance (did it run, craze, fit?), and objective measurements like gloss. Now, add comprehensive, objective tags. Move beyond “pretty.” Describe Color (“rutile blue breakout on iron amber base”), Texture (“bubbled,” “crystalline”), and key attributes (e.g., #carbon_trap, #cone10_reduction, #matte).
This structured tagging is your gateway to AI-powered insight. By using consistent, descriptive keywords, you enable powerful search across your entire glaze library. You can instantly recall all crystalline glazes or find that one stable, high-goss recipe. Before mixing a production batch, you can review the visual log and data. Did the last test show minor pinholes? Your note reminds you to sieve twice.
For a comprehensive guide with detailed workflows, templates, and additional strategies, see my e-book: AI for Small-Batch Ceramic Artists & Potters: How to Automate Glaze Recipe Calculation and Batch Consistency Tracking.