Training Context
Give your AI assistants the knowledge they need to answer questions accurately — by uploading documents, crawling your website, writing FAQs, or adding custom text.
Why training context matters
Your assistant's persona tells it how to behave. Training context tells it what to say.
Without training context, your assistant can only rely on general knowledge from its underlying AI model — which means it won't know anything specific about your products, policies, pricing, or processes. Adding training context is what transforms a generic AI into an assistant that actually knows your business.
Go to AI Assistant > Training Context to manage your knowledge base.
The four types of training context
Website links
Provide a URL and Autoch.at will crawl the page and pull in its content. This is the fastest way to get your existing documentation, help center, or product pages into the system.
You can add individual pages or a root URL to crawl an entire site. After the initial crawl, you can re-crawl a link at any time to pick up changes.
If your website has a sitemap, use the sitemap URL for a more complete crawl. This ensures the system finds all your pages, not just the ones linked from the homepage.
Documents
Upload PDF or Word files containing your policies, product documentation, onboarding guides, or any other reference material. Autoch.at will extract the text and make it available to your assistant.
Supported formats include PDF, DOCX, and plain text files.
FAQs
FAQs are the most targeted type of training context. Each FAQ is a specific question-and-answer pair that you write directly in Autoch.at.
Use FAQs for:
- Questions that come up constantly and need a precise, consistent answer
- Topics where your documents are too long or too general
- Edge cases that your website doesn't cover
FAQs take priority over other context types when the customer's question closely matches the FAQ question.
Custom text
Custom text is a free-form field where you can paste in any content that doesn't fit the other formats — internal notes, product descriptions, pricing tables, or anything else. It's the most flexible option and works well for short, structured information.
Managing your knowledge base
Keeping context up to date
Stale training context leads to wrong answers. Make it a habit to review your knowledge base after major product releases, policy changes, or pricing updates.
- Go to AI Assistant > Training Context.
- Find the outdated item (document, link, FAQ, or custom text).
- Edit or re-crawl it to reflect the current information.
- Delete anything that's no longer accurate.
If a customer asks a question and gets a wrong answer, the first place to check is your training context. Outdated or conflicting information is the most common cause of AI errors.
Checking what's being used
You can see which pieces of training context your AI is using most frequently in Insights > Analytics under FAQ Analytics. If a document is rarely referenced, it might be outdated or too general. If a particular FAQ is being used constantly, consider expanding on that topic in your main documentation.
Training context vs. messaging directives
These two features are easy to confuse, but they serve different purposes:
| Feature | What it does |
|---|---|
| Training Context | Provides information — facts, policies, product details — that the AI uses to answer questions |
| Messaging Directives | Provides behavioral instructions — rules about how the AI should communicate, regardless of topic |
If you want your AI to know your return policy, add it to Training Context. If you want your AI to always end every response with a follow-up question, use a Messaging Directive.
Last updated 3 weeks ago
Built with Documentation.AI