The docs nobody maintains, written and kept current by the AI.
This replaces the docs tool whose articles drift the week after launch. Your Knowledge Base has two faces: public articles your customers and search engines read, and an internal store only the AI reads when it answers questions and drafts content. The AI writes both from real questions and flags what has gone stale.
What it replaces
A docs tool hosts what you wrote. Here the AI writes it, notices when it goes stale, and reads it back on every surface.
A hosted docs tool | Giant Context | |
|---|---|---|
Writing it | You, in an editor, when you find the time. | The AI drafts articles from the questions customers ask and from your product docs. You approve each one. |
Keeping it current | Nobody, until a customer complains. | When product changes ship, the AI scans existing articles for language that has gone stale and proposes updates one at a time. |
Who reads it | Customers and search engines. | Customers and search engines, and the AI every time it answers a chat, drafts an email or writes a page. |
Internal notes | A separate wiki nobody connects to support. | An internal store in the same base: product internals, policies, pricing rationale, support playbooks. Only the AI reads it. |
Your domain, search, SEO | ||
Articles the AI drafts and keeps current
Articles carry images, code blocks and tables, with version history and rollback, authoring metadata, and links to related articles the AI maintains. The AI drafts them from common questions or your product docs. Titles stay plain: "How to send your first email," not "A Comprehensive Guide to Email."
Categories, tags, and order
Articles live in hierarchical categories, with tagging, featured articles, and custom ordering. Readers find things through clean navigation. The AI finds things through the same structure when it answers a question or links an article from a blog post.
How a support pattern becomes an article
A question asked often enough becomes an article. You approve it before it goes live.
- It notices
The same question, three weeks running
A customer asks the same thing in chat week after week. The AI sees the pattern.
- It proposes
A draft article answering it
The AI drafts an article that answers the question and brings it to you.
- You approve
It publishes
You read the draft and accept it. The article goes live under your domain.
- Chat uses it
The next visitor gets a direct answer
Next time the question comes in, the chat widget answers from the new article.
The base every surface reads
The Knowledge Base is what the chat widget answers from, what emails link to, and what renders inside your site.
Where the edges are
If one of these is a dealbreaker, better to know now.
Let the AI write the article you keep meaning to
Ask for early access. Point the AI at a question your customers keep asking, and read the article it drafts back. Approve it, and the chat widget answers from it next time.