The open starting points, free to use
The public, not-for-profit starting points for knowledge-first Agentic AI: the research pieces, the standards and conventions, the adoption practice, the blog, and the agent surface that lets agent engines find and use knowledge reliably. All of it is free to read and free to use.
What is free on this site
Everything on this site is free to read and free to use. The research pieces, the standards and conventions, the adoption practice, the blog, the internship page, the training page, and this page — all of it is the open, not-for-profit side of Knowledge Sidekick.
What is here
The free resources on this site are the public-facing pieces of the open work. They are not a teaser for a paid product. They are the work itself, in the open.
The research pieces
Short, self-contained position pieces on why knowledge is a first-class layer in agentic systems, how it behaves in enterprise and personal contexts, why context windows are a knowledge-delivery problem, and where token cost and grounding really come from. These are the ideas the rest of the work is built on.
The standards and conventions
The conventions and starting points for knowledge representation, lifecycle, grounding, the agent interface, and discoverability. The goal is a usable set of starting points, kept free to read. It is expected to grow: open standards, commercial platforms and proprietary formats all belong in it.
The adoption practice
How to put knowledge-first practice into place: maturity evaluation, lifecycle adoption, knowledge audits and benchmarks, advisory, and training.
The blog
Short, current, opinionated pieces on what is happening in the field and what it means for knowledge. Each piece is written to be read in a couple of screens. Published in chronological order, newest first.
The internship
A chance to work on the research, standards, and adoption of knowledge-first practice in the open, on the public site, with the work visible to the people who will use it.
The agent surface and the discoverability layer
The free resources also include the public-facing agent surface — the clean, documented surface that agent engines can rely on to find and use knowledge, as opposed to scraping whatever is easy. This is where things like llms.txt and the discoverability layer live.
The idea is simple: if an agent engine cannot find your knowledge, it cannot act on it. The agent surface and the discoverability layer are the free, open counterpart to the search and SEO work that already exists for human readers. They are part of the standards work, and they are part of the free resources.
The full standard is still a working draft. The public site itself is the first version of the surface — a small, flat, documented site that an agent engine can read and use. The conventions are refined through use, in the open, by the people doing the work.
How to use these resources
These resources are not a checklist to consume in order. They are a map of the work and a set of starting points. The usual entry points are:
- Why Knowledge — if you are picking up the argument for the first time.
- Research — if you want the ideas developed across several angles.
- Standards — if you want the conventions anyone can adopt.
- Adoption — if you want the practice of putting the ideas into place.
- Articles — if you want the current, opinionated view of what is happening in the field.
- Internship — if you want to work on the ideas in the open, as an individual entry point.
- Training — if you want the ideas taught in a form your team can run.
The goal is not to make you read everything. Everything here is free to read, and each page is written to stand on its own.
Page updated .