Quarterly refresh, with faster updates if a model change affects prompt safety.

The paid prompt pack should be refreshed quarterly. If a vendor changes a product name, data-protection rule, model behavior, or workplace AI feature in a way that affects L&D use, the public model register should be updated sooner.

The current catalog includes 33 prompts. Public sample pages show complete prompts. Paid catalog entries show what is included in the founding edition.

ChatGPT Verified 2026-05-15

ChatGPT GPT-5.5

Use an outcome-first structure. Give ChatGPT the role, goal, approved source notes, constraints, and exact output you want back.

OpenAI source

Claude Verified 2026-05-15

Claude Sonnet 4.6

Use labeled sections so context, source material, task, constraints, and output format stay separate.

Anthropic source

Copilot Verified 2026-05-15

Microsoft 365 Copilot

Use goal, source, expectations, and output. For Obsidian context, use approved excerpts, Word summaries, OneDrive files, SharePoint pages, Teams context, or Outlook threads.

Microsoft source

Gemini Verified 2026-05-15

Gemini 3

Use a task-first structure with clear input labels, one example pattern, rules, and a concise output format. For Obsidian context, use approved excerpts, Drive exports, Google Docs, or NotebookLM source sets.

Google source

v0.1 public preview 2026-05-19

Public model-aware prompt vault preview

  • Added the public prompt vault catalog.
  • Added model-specific prompt rendering for ChatGPT, Claude, Microsoft 365 Copilot, and Gemini.
  • Opened the first set of free sample prompts.
  • Prepared the founding-edition product surface for the full paid vault.