What llms.txt is for
A good llms.txt file points AI systems toward the most useful pages: product overview, docs, pricing, policies, use cases, support, and canonical explanations.
It should be an index and guide, not a replacement for your site. The best version helps an AI decide which pages to read next.
What to include
Include stable public information, important URLs, a short description of the product or organization, and links to deeper documentation.
Keep private pages, outdated campaigns, duplicate landing pages, and thin content out of it.
How Riflet helps prepare it
Riflet can gather candidate source pages from websites, sitemaps, Notion exports, docs folders, or local notes. You can then filter down to the canonical material.
The resulting bundle can be used to draft or refresh llms.txt and llms-full.txt without manually copying every source.
Maintenance
Review llms.txt when product positioning, docs structure, pricing, or core URLs change. Like SEO metadata, it is only useful when it reflects the current source of truth.
Build better AI context with Riflet
Collect the files, notes, websites, and docs that matter. Export one portable bundle for any AI.
Download Riflet freeFrequently asked questions
Is the llms.txt standard explained only useful for developers?
No. The same context principles apply to research, writing, legal review, client work, product planning, and any workflow where the AI needs project-specific source material.
Does more context always produce better AI output?
No. Relevant, well-structured context usually beats a large dump of loosely related files. Large context windows make preparation more important, not less important.
Where does Riflet fit in this workflow?
Riflet is the assembly step. It helps gather source material, filter it, estimate the token budget, and export one portable file for the AI tool you choose.
Does Riflet replace RAG or AI project features?
Not always. RAG is useful for large retrieval systems. AI project features are useful inside one platform. Riflet is best when you want explicit, portable context you can inspect before using.