Skip to content
Guide

What to feed an AI agent before you launch it

A checklist for the content that changes answer quality, and the pages that only add noise.

Joshua Janse van Rensburg3 min read

Feed your agent the pages that answer questions, not the pages that describe you. Twenty well-written answers outperform two hundred marketing pages, because retrieval rewards specificity and punishes repetition.

Every business we onboard arrives with the same instinct: point the crawler at the whole site and let it sort itself out. It is a reasonable instinct, and it is usually wrong. The knowledge base is not an archive. It is the set of things you want said out loud, to a stranger, without you in the room.

What follows is the audit we run before a single agent goes live. It takes about forty minutes for a typical small business site, and it is the difference between an assistant that sounds informed and one that sounds like a brochure.

What actually changes answer quality

Retrieval works by finding the chunk of text closest in meaning to what the visitor asked. That means the useful unit is not the page, it is the paragraph that contains a fact. A page titled "Our Services" that lists nine services in nine sentences will lose to a page that explains one service in six paragraphs, every time.

Three properties predict whether a page will earn its place:

  1. It states facts, not positioning. "We deliver within 3 to 5 working days to main centres" is retrievable. "Fast, reliable delivery you can count on" is not.
  2. It is written the way people ask. If customers say "how long does shipping take", a heading that reads "Fulfilment SLA" costs you the match.
  3. It is current. Stale facts do more damage than missing ones, because the agent will state them with the same confidence as everything else.

What to leave out

Subtraction is the underrated half of this job. Every page you add competes with every other page for retrieval, so noise is not neutral. It actively displaces good answers.

Dated pages

Press releases, event announcements, and "our new office" posts age badly. They teach the agent to cite things that stopped being true, and because nothing in the text says "this expired", it has no way to know.

Near-duplicates

Landing page variants built for ad campaigns are usually 80% identical. When five chunks say nearly the same thing, retrieval returns five copies of a mediocre answer instead of one good one.

ContentIndex itWhy
FAQ pageYesAlready question-shaped, highest hit rate per word
Pricing pageYesMost-asked question on almost every site
Terms, returns, deliveryYesFactual, stable, and what people actually need
Blog announcementsNoAges badly, no expiry signal in the text
Scanned PDFsNoNo extractable text layer to chunk
Team biosMaybeUseful for trust questions, noise for everything else

The pre-launch checklist

Run this before you deploy to a live surface. Each item takes a minute or two, and skipping them is where almost every disappointing first week comes from.

  • Pricing is on a page, in text, not only in an image or a downloadable rate card.
  • Contact details appear somewhere the crawler can reach without a form submission.
  • The five questions from your inbox each have a paragraph that answers them plainly.
  • Anything seasonal or dated has been excluded or updated.
  • You have asked the agent those five questions yourself, and read the answers as a customer would.

That last one is the only test that matters. Everything above is a way of making it more likely to pass. For the mechanics of adding and excluding sources, see adding sources in the docs.

In short

What to remember

  • The useful unit is the paragraph that contains a fact, not the page.
  • Write the way customers ask, not the way your industry writes.
  • Noise displaces good answers, so subtract as deliberately as you add.
  • Test with your own five most-asked questions before you go live.

Questions people ask

How many pages does an AI agent need to be useful?

Far fewer than most people expect. Twenty pages that answer real questions beat two hundred that repeat your positioning. Coverage of intent matters more than page count.

Should I add my blog to the knowledge base?

Only the evergreen posts. Dated announcements teach the agent to cite things that are no longer true, which is one of the most common causes of a confidently wrong answer.

Do PDFs work as well as web pages?

Text-based PDFs index cleanly. Scanned documents and image-heavy brochures do not, because there is no extractable text layer for the pipeline to chunk.

Keep reading

Your new hire
is one link away.

Connect your content and see it working in minutes.

Free to start. No card required.

See plans and pricing
PricingPrivacyTerms© 2026 Lorito.