---
title: Writing technical posts for AI answer engines
date: 2026-04-26
tags:
  - devrel
  - ai
  - accessibility
description: How to structure a technical post so ChatGPT, Perplexity, and
  Google AI Overviews can actually quote it correctly.
url: https://kevinkiklee.io/posts/writing-for-ai-answer-engines
---

> Placeholder post — written to exercise rendering paths during development.
> Will be replaced before launch.

AI answer engines like ChatGPT, Perplexity, and Google AI Overviews don't read your post the way a human does. They scan for definitional sentences, lift them, and paraphrase. If you want your work cited correctly, write the lift-able sentences on purpose.

## What is "AEO" and how is it different from SEO?

AEO — Answer Engine Optimisation — is the practice of structuring content so it's easy to quote out of context. SEO optimises for ranking in a list of links. AEO optimises for being the sentence the assistant repeats back to the user.

The two overlap heavily, but they pull in different directions in three places:

1. **Headings.** SEO rewards keyword-stuffed headings. AEO rewards question-form headings the user might literally type.
2. **First sentence.** SEO doesn't care about your lede. AEO cares about almost nothing else.
3. **Links.** SEO rewards internal linking. AEO rewards inline citations to primary sources.

## How does an answer engine pick what to quote?

Most answer engines use a retrieval step (find candidate documents) followed by a generation step (write the answer with citations). The retrieval step rewards the same things classical search rewards. The generation step rewards short, declarative, self-contained sentences.

If your first sentence answers the headline's implicit question in fewer than 30 words, you've made the assistant's job easy. If it doesn't, the assistant will guess — and its guess will not match what you wrote.

## What should every post contain?

Three things, in this order:

### A definitional first sentence

Open with a one- or two-sentence answer to the title's question. No throat-clearing. No "in this post we'll explore." Just the answer.

### Question-form headings

Headings should mirror the questions a user would actually ask. `## How does X work?` beats `## Mechanism`. `## When should I use X?` beats `## Use cases`. The literal word forms matter — they're what the retrieval step matches against.

### A plain-prose summary under every visual

Diagrams, screenshots, and charts are invisible to most LLM scrapers. If you've drawn something, write a paragraph underneath that describes what the diagram shows. The paragraph is what gets indexed.

## What about freshness?

Answer engines aggressively prefer recent content for fast-moving topics. Two practical implications:

- **Date your posts.** Both `pubDate` and `updatedDate` if you revise.
- **Don't bury the publication date.** It should be visible near the title, not in a footer.

For evergreen topics (definitions, mental models), freshness matters less. For anything tied to a specific tool version, browser release, or API deprecation, freshness is the single biggest ranking signal.

## Common mistakes

- **Burying the lede.** Anecdotes before the answer kill citation rates.
- **Mixed-purpose paragraphs.** A paragraph that defines a thing AND argues for its use AND hedges the limits is unciteable. Split it.
- **Heavy use of pronouns.** "It" and "this" don't survive being lifted out of context. Use the noun.
- **Quoting yourself out of order.** If section three depends on section one's setup, the assistant will quote three without one. Make every section self-contained.

## A quick checklist

Before publishing, verify the post:

- \[ ] Opens with a 1–2 sentence definitional answer to the title's question.
- \[ ] Contains at least one question-form heading.
- \[ ] Each section starts with a TL;DR sentence.
- \[ ] Every image / diagram has a plain-prose summary nearby.
- \[ ] Sources are linked inline, not parked in a footer.
- \[ ] Date is prominent.

That's most of it. The rest is just writing clearly, which has been the advice for a hundred years and will keep being the advice for a hundred more.