FAQ: JakBot Chatbot
Questions about the JakBot AI chatbot plugin — features, capabilities, and how it works.
-
JakBot is a business growth and revenue recovery platform designed to help small and mid-sized businesses capture more leads, respond faster, automate follow-up, and recover opportunities that may otherwise be delayed, ignored, or lost. Rather than simply selling software tools, JakBot focuses on improving responsiveness, lead handling, customer engagement, and operational consistency so businesses can convert more of the opportunities they are already generating.
-
The JakBot package is a suite of three WordPress plugins designed to grow your business online:
JakBot — An AI chatbot that answers visitor questions, captures leads, books appointments, and collects structured data through conversations.
Jay’s SEO Checklist — A comprehensive site health tool covering PageSpeed testing, accessibility audits, broken link checking, WebP image conversion, lazy loading, FAQ management with schema markup, and more.
Jay’s Post Amplifier — An AI-powered content creation tool that generates social media summaries, featured images, article ideas, and full blog posts from a single click.
Together, these plugins help you attract visitors (SEO), engage them (chatbot), capture leads, and keep your content pipeline flowing (content creation).
-
JakBot indexes your website content — pages, posts, and custom post types — by generating embedding vectors (a mathematical representation of your content’s meaning). When a visitor asks a question, JakBot converts their question into the same kind of vector and uses cosine similarity to find the most relevant content from your site. That content is then provided to the AI as context so it can generate an accurate, grounded answer. You can also configure tags, categories, and custom meta fields to enrich the embeddings and improve search quality for vague or category-level questions.
-
Yes. JakBot supports multiple bots on a single WordPress installation. Each bot can have its own system prompt, personality, template design, search mode, similarity threshold, and feature configuration. For example, you could have a general FAQ bot on your homepage and a specialized scheduling bot on your contact page. Each bot is placed using the
-
JakBot supports two AI providers: Google Gemini and OpenAI. Both are fully functional for chat responses and embedding generation. The active provider is configured per-bot through the admin interface. Gemini uses the gemini-2.5-flash model by default (with 2.5-pro also available), and OpenAI supports configurable chat models with text-embedding-3-small for embeddings. You can switch providers at any time, but the embedding index must be rebuilt when changing providers since each produces vectors in a different format.
-
JakBot offers three search modes, configurable per bot:
Always — Searches your indexed content on every visitor message (minimum 3 words). Best for FAQ-style bots where every question should pull from your knowledge base.
Confirmation — Searches after the AI has asked qualifying questions and the visitor confirms their answers. Good for guided conversations where context matters.
Disabled — No embedding search. The bot responds only from its system prompt. Useful for bots that handle structured flows like scheduling or data collection.
Each bot also has a configurable similarity threshold (default 0.35) that controls how closely a visitor’s question must match your content before results are returned.
-
A Conversation Contract is a structured, multi-step data-collection mode for JakBot bots. Instead of free-form conversation, the bot guides the visitor through a defined set of steps — collecting specific information like name, email, project details, or preferences — in a natural conversational flow. The contract definition is configured as JSON and controls the steps, fields, validation rules, and status progression (collecting, confirming, complete). On completion, JakBot can optionally run a search against your indexed content and present relevant results, then send a lead notification email. It’s ideal for intake forms, quote requests, or any scenario where you need structured data from a visitor.
-
JakBot comes with several built-in chat interface templates: Default, Standard, Modern, Modern Bar, and Test. Each template controls the look and feel of the chat widget on your site. Templates are assigned per bot, so different bots can have different visual styles. Each template can include its own CSS and JavaScript for full customization. The JakBot team can also help you create a custom template that matches your brand.
-
Yes. JakBot includes an SMS webhook handler that integrates with Twilio. It receives inbound text messages and can route them to scheduling flows or generate AI-powered responses. The system also handles standard carrier keywords — visitors can text STOP to opt out, START to opt back in, and HELP for contact information. SMS is especially useful for appointment reminders and follow-ups.
-
JakBot maintains conversation history within a single session. If a visitor returns to the same page, their previous conversation is loaded and displayed. However, conversations are identified by IP address (for guests) or WordPress user ID (for logged-in users), and conversation logs are periodically cleaned up by a scheduled cron job. JakBot does not use cookies or localStorage for session tracking. Each new session after cleanup starts fresh.
-
Yes. JakBot automatically extracts contact details — names, email addresses, and phone numbers — from visitor messages using pattern matching. When a conversation ends (detected by session-end keywords), JakBot sends a lead notification email to the site admin with the full conversation and any extracted contact information. This works in both standard chat mode and Conversation Contract mode.