Atomic Blocks (now closed in the WordPress directory but still live on many sites that migrated to Genesis Blocks) shipped 22 blocks including Container, Accordion, Pricing, Pricing Column, Profile Box, Testimonial, CTA, Drop Cap, Sharing, and Advanced Columns. They serialise into wp_posts.post_content as wp:atomic-blocks/* markup that resolves to real HTML at render time. SleekAI reads the rendered page, so a Pricing block becomes plan rows with values, an Accordion becomes Q&A pairs, and a Profile Box becomes a person bio with role and bio text.

Many Atomic Blocks sites have since migrated to Genesis Blocks or kept the legacy block markup in place. SleekAI reads post-render HTML, so the bot works for both: a Pricing block looks the same to the parser whether the underlying block name is atomic-blocks/ab-pricing or a later equivalent. The wizard also pulls ACF fields and any postmeta referenced from a block.

Display conditions scope different bots by post type, taxonomy term, user role, or URL pattern. Conversations log inside WordPress with model name, token usage, and page URL. The JS API and PHP embed open the bot from a custom CTA or Sharing block click.

A lot of sites built on Atomic Blocks haven't moved off the original plugin even after the directory closure. Genesis Blocks took over the maintained line, but legacy installs keep ticking, often with substantial pricing, about, and landing-page content built in the original block markup. A generic chatbot doesn't read any of that.

It hallucinates plan names, invents team bios, and quotes refund policies that don't match the FAQ on the page. SleekAI reads the rendered HTML, so the bot lifts the Pricing block exactly, surfaces the right person from a Profile Box, and answers refund questions from the Accordion FAQ. Because the read happens at request time, the bot keeps working through plugin migrations, theme changes, or content edits.

Multibot mode lets a pricing bot, an about bot, and a marketing bot share the install with separate prompts and scopes. Conversation logging surfaces what visitors actually struggle with, so you can either tighten the prompt or update the page copy. The result is a chatbot that respects the work already in the legacy install instead of demanding a migration.