For AI agents: see the documentation index. Request public content pages with Accept: text/markdown.
Cover image for How to teach a support bot from your own documents, and what makes it answer correctly

How to teach a support bot from your own documents, and what makes it answer correctly

Uploading a PDF is the easy part. What decides whether a support bot answers correctly is how your documents are written, whether it can find exact codes, and which documents you let in.

·7 min read

What grounding actually is

When a customer asks a question, the bot searches your documents, finds the passages that match, and answers from them. It is not remembering your return policy, it is reading it, at the moment of the question.

That distinction matters for two reasons. Your policy can change on Tuesday and be correct in answers on Tuesday. And when an answer is wrong, the cause is almost always that the bot found the wrong passage, or missed the right one, rather than a flaw in the AI itself.

Searching by meaning alone is not enough

Most bots search by meaning, which handles paraphrase well. Someone asking “can I send this back” finds a passage about returns without sharing a single word with it.

It handles exact codes badly. A part number like RX-4410-B, an order number, a specific error code: these are exactly the questions where searching by meaning is least useful, because the code that matters has no meaning to match.

The fix is to do hybrid search: search both ways at once, by meaning and by the exact words. ProxyAI does this by default, so a question containing a product code works as well as one written as a sentence.

If you are comparing platforms, ask this directly. “We use AI search” says nothing about whether a customer quoting a part number will get an answer.

How your documents are written matters more than any setting

When you import a document, ProxyAI’s document importer splits it into short passages by itself, so there is nothing for you to set up. What you control is how clearly each document is laid out. A document with clear headings, lists and tables is split in sensible places. A wall of plain text is not, and a passage can end up without the context that made it meaningful, such as a price with no sign of which product it belongs to.

ProxyAI’s AI formatter does the tidying for you. After you upload a document, press Clean convert markdown (AI powered) on the review screen. It restores headings, lists and tables, and removes page numbers and repeated headers, without rewriting or dropping anything. It uses a little of your credit.

Rewriting your top ten support documents with real headings, or running them through the AI formatter, is usually a bigger accuracy win than any tuning.

The discipline that matters most: what you do not upload

The instinct is to upload everything. It is the wrong instinct.

The bot finds what best matches the question, not what is most current. Leave last year’s shipping policy next to this year’s, under a different filename, and a customer will eventually be told the wrong thing, confidently, with the outdated passage as the reason. The bot did not hallucinate, it read a document you gave it.

Three rules that prevent most of this:

One current version of each thing. Delete superseded documents rather than keeping them “for reference”. The bot has no concept of reference.

Keep the same filename when you update. In ProxyAI, uploading a document with the same filename replaces the old version, so the policy updates instead of piling up as two contradictory copies. A new name, such as shipping-2026.pdf next to shipping-2025.pdf, keeps both.

Review before you publish. Reading text out of PDFs is imperfect. A table that turned into a wall of numbers is worse than no table, and you can only see that by looking.

Scanned PDFs need a decision, not a default

A scanned or photographed PDF has no readable text, so the bot sees nothing. Text recognition (OCR) fixes this, but it adds cost and is never perfect.

So decide per document: turn it on for documents that really are scans, and leave it off for the rest. ProxyAI does this on your own computer, so scanned documents are not sent to a third-party service, worth knowing if the scans are contracts.

Each bot should only see its own documents

If you run more than one bot, each one needs its own separate set of documents.

Keeping them separate protects you in two ways. The first is privacy: one client’s bot can never see another client’s documents. The second is getting the right answer: if two brands with different return windows shared one set of documents, the bot could answer with the wrong company’s policy. With separate sets, each bot only knows its own.

How to tell whether it is working

Test in both directions, and the second one is the one people skip.

Ask what is covered. Questions your documents answer directly. Check the answer matches the source rather than a plausible paraphrase of it.

Ask what is not covered. Questions near your documents but not in them. The correct behaviour is admitting it does not know. A bot that confidently improvises here will do the same thing to a customer, and you will not find out until they act on it.

Then look at the questions the bot could not answer. Those are your content gaps, stated as questions real people asked, a better list of what to write next than anything you would produce in a planning meeting.

rag · knowledge-base · retrieval

FAQ

Frequently asked questions

What does it mean to ground a chatbot in your own documents?

It means the bot looks up the answer in your documents when a question arrives, instead of answering from general knowledge. Updating a document updates the answers immediately.

What is hybrid search and why does it matter for support bots?

Hybrid search looks for answers two ways at once: by meaning and by exact words. It matters because searching by meaning alone handles paraphrased questions well but struggles with exact codes such as product numbers, order numbers and error codes, which are common in support.

Why does my grounded chatbot give outdated answers?

Almost always because an outdated document is still among the bot’s documents. The bot returns the closest match to the question, not the most recent document, so a superseded policy will be quoted whenever it fits better. Uploading the new version under the same filename replaces the old one, and deleting old versions fixes it. Keeping them “for reference” does not work, because the bot has no concept of reference.

How many documents should I upload to a support chatbot?

Fewer than instinct suggests. Every added document is another possible source for an answer, so duplicates and superseded versions actively reduce accuracy. One current version of each topic, with clear headings, outperforms a large unmanaged corpus.

Do scanned PDFs work in a chatbot knowledge base?

Only with text recognition (OCR), since a scan has no readable text. Turn it on per document rather than for everything, because it adds cost and is never perfect. ProxyAI does this on your own computer, so scanned files are not sent to an outside service.

Can one chatbot retrieve another chatbot’s documents?

Not when each bot has its own separate set of documents. That keeps one client’s documents private and stops policies from getting mixed up: if two brands shared one set of documents, the bot could answer with the wrong company’s policy.

How do I test whether a grounded chatbot is working?

Ask questions your documents cover and check the answer against the source, then ask questions near your documents but not in them and confirm the bot says it does not know. The second test is the one that predicts real-world failures.


The details, supported file types, size limits and storage billing, are in the Bot Knowledge Guide.

More from the blog

The Best AI Customer Service Software in 2027: A Buyer’s GuideThe Best Ecommerce Customer Service Software in 2027The Best Help Desk Software in 2027: A Practical Buyer’s GuideBest Knowledge Base Tools for Return Policy QuestionsThe Best Knowledge Base Software in 2027: Choose for Your TeamThe Best Live Chat Software in 2027: What to CompareWhich Ecommerce Platforms Support Both Web Chat and WhatsApp?eDesk Alternatives in 2027: Ecommerce Support Tools ComparedGorgias Alternatives in 2027: Options for Ecommerce SupportHelp Center Software for a One-Person Online StoreIntercom Alternatives in 2027: Pick by Team and Pricing ModelLive Chat Software vs Regular Help Desk Tools: Which Fits?ProxyAI vs eDesk: An Honest Comparison for Ecommerce SupportProxyAI vs Gorgias: An Honest Comparison for Shopify SupportProxyAI vs Intercom: An Honest Comparison for Ecommerce TeamsProxyAI vs Tidio: An Honest Comparison for Storefront ChatProxyAI vs Zendesk: An Honest Comparison for Small Online StoresTidio Alternatives in 2027: Live Chat, AI, and Ecommerce FitZendesk Alternatives in 2027: How to Choose the Right Support StackHow to Add an AI Chatbot to Your Website: A Beginner’s GuideHow to Add an AI Chatbot to WordPress and WooCommerce (Free Plugin, No Coding)AI Chatbot Features Compared: Channels, Handoff, Store Integrations and More (2026)AI Chatbot Pricing Compared: Intercom, Zendesk, Gorgias, Tidio, Crisp, Chatbase and More (2026)The question to ask an AI agent vendor, what happens before it sendsWhat an AI agent actually costs to run, priced line by lineOne bot, every channel, what multi-channel support actually requiresWhatsApp for support, the bridge route and the official route, honestly comparedAI chatbot pricing models explained, seats, conversations, credits and metered usageHow to add an AI chatbot to a Shopify store