Short answer: Feed a chat widget the content that answers customer questions — services, pricing, process, policies, coverage area, FAQs and booking rules. Leave out marketing filler, blog archives written for search engines, legal boilerplate and anything outdated. More content is not better content; a small, accurate, specific knowledge base beats a large vague one every time.
Why volume is the wrong instinct
It is tempting to index everything on the theory that more information means more coverage. Retrieval does not work that way.
Every answer is built from a handful of passages selected as most relevant to the question. If your index is full of near-duplicate marketing pages that all say "we deliver excellence with a personal touch," those pages compete for retrieval slots with the one page that actually states your call-out fee. Padding does not add coverage. It adds noise, and noise pushes the good passage out of the window.
The mental model to hold: you are not filling a library, you are curating a reference shelf.
The content that earns its place
Services, described concretely. Not "comprehensive solutions" — what you do, what it involves, what it does not include, how long it takes.
Pricing, in whatever form you can commit to. A real number is best. A range is fine. "Typical projects run between X and Y depending on Z" is enormously more useful than "contact us for a quote," because the widget can actually help the visitor decide. Price is the most-asked question in almost every business, and a widget that cannot address it will disappoint most of its visitors.
Process. What happens after someone gets in touch. First visit, timeline, what to prepare, who turns up. This is where anxiety lives, and it is often documented nowhere.
Coverage and availability. Areas served, hours, lead times, whether you do weekends and emergencies.
Policies. Cancellations, deposits, guarantees, returns, rescheduling. Boring, high-stakes, and the questions people are most reluctant to phone about.
Your real FAQ — not the invented one. Whatever your team actually gets asked. If nobody has written it down, an hour with the person who answers the phone will produce more useful content than a month of blogging.
Qualifying information. What you do not do, who you are not right for. A widget that can say "we do not handle commercial properties" saves everyone time and improves lead quality.
What to leave out
About-us prose about your journey and values. Nobody asks the chat widget about your journey.
SEO blog archives. Long, keyword-padded posts on general topics dilute your index and rarely contain a fact a customer needs. If a post does contain real specifics, extract those into a proper page.
Full legal documents. Terms and privacy policies are written to be defensible, not readable, and passages retrieved from them tend to produce answers that are technically correct and useless. Summarise the customer-relevant parts instead and link to the full document.
Anything superseded. Old pricing, discontinued services, expired campaigns. Delete rather than archive — an unlinked page is still crawlable.
Testimonials as a bulk dump. A few are fine as social proof. Hundreds crowd the index.
Where knowledge files fit
Some of your best content is not on your website and should not be. Internal FAQs, service specifications, policy documents, price sheets you send on request. Clerkzo takes ten file types at up to ten megabytes each, so this material can go straight into the knowledge base without publishing it.
Two rules make uploads work. Prefer clean text — a text-based document beats a scanned PDF, because a scan is an image and the text may not be extractable. And prefer one topic per file. A single mega-document covering everything retrieves badly, because chunking cuts it in places that split the meaning.
Keep an inventory of what you have uploaded. Files are the easiest thing to forget and the most likely source of a confidently outdated answer.
Corrections are content too
The highest-value content in your knowledge base is often the answer you wrote by hand after seeing a bad one. Flag the response, type the correct answer, and it becomes an authoritative override.
This is worth planning for rather than treating as cleanup. Some facts are inherently awkward to publish — a nuanced pricing exception, a policy that needs framing — and a correction lets the widget give the right answer without you having to write a public page about it. It is the practical core of chatbot training for retrieval systems.
How to find your gaps
Write down the last twenty questions your team was asked. Ask each one in the playground, which mirrors the live widget exactly. Anything answered thinly is a content gap, and it is a gap for your human readers too.
Then keep doing it with real conversations. Every conversation is saved with a thumbs up or down rating, and the down-votes plus the questions that end in a human handoff are your content backlog, written for you by your customers.
Fixing those gaps improves your website, not just your chat. That is the quiet benefit of this exercise: it forces you to write down the things you have been explaining verbally for years. If you are still weighing tools, our guide to choosing an AI receptionist covers what to look for.
Frequently asked questions
Do I need a big FAQ page before I start?
No. Start with what exists, go live, and let real questions tell you what to write. Guessing at an FAQ before launch usually produces the wrong twenty questions.
Should I upload my whole website as a file?
No. The crawler already reads your site. Upload only what is not published.
What if I genuinely cannot publish prices?
Publish the structure — what drives cost, typical ranges, what a quote includes. That is enough for the widget to be genuinely helpful without committing you to a number.
Does adding more content always improve answers?
No. Relevant content improves answers; irrelevant content competes with it during retrieval and makes answers worse.