This document holds the internal structure and reference notes that support Prompthon Agentic Labs. It is intentionally separate from the top-level README so the front door can stay lightweight.Documentation Index
Fetch the complete documentation index at: https://labs.prompthon.io/llms.txt
Use this file to discover all available pages before exploring further.
Current status
- The top-level lab lanes are now scaffolded in the repository.
- Imported reference material is kept outside the published docs surface.
- Audience guides and contributor templates are in place for future content work.
- The first public lab article wave is drafted.
- Public contributor guidance now covers articles, radar notes, source projects, and curated reference notes.
What this lab covers
- Agent system fundamentals and terminology
- Reusable agent patterns and workflow mechanisms
- Systems concerns such as context, protocols, evaluation, and reliability
- Ecosystem comparisons across global and Chinese agent tooling
- Story-led case studies for major agent product categories
- Fast-moving radar and publication extensions
Repository structure
| Path | Purpose |
|---|---|
foundations/ | Core concepts, terminology, and mental models |
patterns/ | Reusable agent design patterns and mechanisms |
systems/ | Production-minded systems topics such as evaluation and interoperability |
ecosystem/ | Topic-first comparisons of tools, models, and platforms |
case-studies/ | Story-led examples for major agent archetypes |
radar/ | Fast-moving market and protocol tracking |
reading-paths/ | Audience-first entry points into the lab |
publications/ | Metadata and structure for external reading extensions |
contributor-kit/ | Templates and editorial scaffolding for contributions |
| local reference archive | Imported source material and planning documents kept outside the published docs surface |
patterns/examples/systems/examples/ecosystem/examples/case-studies/examples/
contributor-kit/reference-notes/.
Editorial direction
- Path-first, not chapter-first
- Story-led pages that move from problem to architecture to tradeoffs
- Topic-first ecosystem coverage with explicit global and Chinese lanes
- Repo-native content outside
references/, with source-aware adaptation