webgptorg

webgptorg/promptbook

Agent

Agent that update models and LLM providers.

webgptorg/promptbook

Instructions file GitHub Copilot

Copilot instructions for webgptorg/promptbook, covering copilot instructions for promptbook, project overview, architecture & key concepts, book language & commitments and monorepo structure.

webgptorg/promptbook

Instructions file CodexOpenCode

AGENTS.md instructions for webgptorg/promptbook, covering how to contribute, code style, emoji in [brackets], generated code and dictionary.

webgptorg/promptbook

Command

Actions influences from the pipeline or task into external world. Like turning on a light, sending an email, etc.

webgptorg/promptbook

Command

Which version of the Book language is the .book.md using.

webgptorg/promptbook

Command

Expect command describes the desired output of the task (after post-processing).

webgptorg/promptbook

Command

Command "FOREACH" from webgptorg/promptbook, covering foreach command, example usage and 🍭 itterations and foreach command.

webgptorg/promptbook

Command

Format command describes the desired output of the task (after post-processing).

webgptorg/promptbook

Command

Specifies the application type and interface requirements that this promptbook should conform to.

webgptorg/promptbook

Command

Instrument command is used to specify the instrument to be used in the pipeline or task like search, calculate, etc.

webgptorg/promptbook

Command

Joker parameter is used instead of executing the task result if jokers value meets the expectations requirements.

webgptorg/promptbook

Command

Tells promptbook which external knowledge to use.

webgptorg/promptbook

Command

Tells which modelRequirements (for example which model) to use for the prompt task execution.

webgptorg/promptbook

Command

Command "PARAMETER" from webgptorg/promptbook, covering parameter command, example usage and ⭕ parameters.

webgptorg/promptbook

Command

Persona command is used to specify who the system is, it will be transformed into system message, topt,...

webgptorg/promptbook

Command

Defines the postprocess function to be used on the result from LLM and before the result is validated.

webgptorg/promptbook

Command

Defines the purpose of the markdown section - if its a task and which type or something else.

webgptorg/promptbook

Command

Command "URL" from webgptorg/promptbook, covering url command, example usage and 🆔 pipeline urls and identification.

webgptorg/promptbook

Agent

Every agent has a visual identity used across the UI (directory cards, chat header, manifest icons, social previews). It is resolved from the agent's book with deterministic fallbacks, so an agent always has an avatar.

webgptorg/promptbook

Agent

Federation lets one Agents Server instance see and reuse agents hosted on other Agents Servers. It is configuration-driven and read-only: a federated server is never written to; its agents are referenced by URL or copied on demand.

webgptorg/promptbook

Agent

Agents are organized in a folder tree per server instance. Folders group agents in the directory (homepage, header menu, dashboard) and drive bulk operations (visibility, export). State lives in prefixAgentFolder plus Agent.folderId/Agent.sortOrder (Data model).

webgptorg/promptbook

Agent

How one stored agent source becomes the effective (resolved) source that is actually compiled and executed. Resolution expands FROM (inheritance) and IMPORT (textual inclusion) commitments, rewrites compact agent references into canonical URLs, and degrades gracefully when references cannot be loaded.

webgptorg/promptbook

Agent

Compiling an agent (resolving inheritance, building model requirements, indexing KNOWLEDGE into provider-side vector stores) is expensive. The server therefore prepares agents in the background ahead of chat time and caches every derived artifact by content hash, so the first user message does not pay the indexing…

webgptorg/promptbook

Agent

Agents whose book is open learn from their conversations: after a turn, the executing agent may append new content to its own source (samples of the exchange, teacher-suggested commitments). The server persists these changes append-only, so learning can never rewrite or corrupt the authored book.