WordPress prospects sort agencies on stack proof before anything else. A buyer with a WooCommerce multisite needs a team who has shipped HPOS migrations, multisite networks, and a serious WooCommerce data layer; a buyer with a headless Next.js front-end needs a team comfortable with the REST or GraphQL API and a custom block library. The static portfolio rarely makes any of that obvious. SleekAI reads case studies tagged by stack components and project type, then answers "have you done WooCommerce multisite with HPOS" with specific projects and scope.

The bot pulls from wp_posts, postmeta, ACF fields, and custom taxonomies via the data-source wizard. Tag case studies by stack (WooCommerce, multisite, headless, ACF, custom plugin), project type (replatform, redesign, custom build, ongoing retainer), and industry. The bot filters answers on any combination, and display conditions route discipline-specific bots per landing page.

Pre-qualification keeps the new business team focused. The system prompt encodes the agency's minimum engagement, the stack components the team does and does not service, and rough ranges per project type. Off-fit prospects get a polite no; qualified leads book a discovery call with the transcript attached. Conversation logs include model name, token usage, and page URL so the agency can audit which clusters convert and tune the prompt over time.

Mid-market and enterprise WordPress RFPs are sorted on stack proof before anything else gets evaluated. A digital director at a publisher with 12 brand storefronts on a WooCommerce multisite needs a partner who has shipped recent multisite projects with HPOS, custom plugin work, and a serious editorial block library, all on production traffic. A generic agency site that lists "WordPress" as one of 14 capabilities does not give the prospect any way to confirm that, and the case-study grid usually does not surface stack tags.

Most prospects move to the next agency on the shortlist within a few minutes. A bot that reads every case study and filters by stack and project type closes that gap in two messages. Pre-qualification by engagement size is the second gate.

WordPress project ranges span an order of magnitude, from 15,000 USD redesigns to 300,000 USD multisite replatforms, and most agencies sit in a narrow band of that spectrum. Filtering out projects under the agency's minimum, or above the team's current capacity, before a call books, raises close rate on calls that do happen and keeps the new business team focused on engagements that match the agency's shape. The transcript is the compounding payoff: reading a week of conversations tells the agency which stack components inquire most, which project types recur, and which case studies actually pull weight on cluster pages.

That feedback loop is hard to get from contact form submissions, where the prospect's real architectural question gets compressed into a one-line subject before anyone reads it. Done well, the bot becomes both a top-of-funnel converter and a quiet feedback channel that informs pitch decks and case-study sequencing on the site itself.