Bot configuration

Every setting on the Aimogen Pro chatbot configuration and API parameter screens, with what each one actually controls.

AI Chatbot › Bot Configuration and AI Chatbot › API Parameters.

Identity#

SettingWhat it controls
Bot NameDisplayed name, and how the bot refers to itself. Stored as ai_message_preppend
Bot DescriptionA short role description, shown in the header on some designs. Stored as ai_role
Bot ContextThe system prompt. Who the bot is, what it knows, what it must not do
Bot Initial Messages (One Per Line)Opening messages. Several lines means one is chosen at random
Bot Avatar ImageAvatar URL
User NameHow the visitor is labelled
User Avatar ImageDefault visitor avatar
Use User Avatar If A Logged In User Using The ChatbotUse the WordPress avatar for logged-in visitors

Bot Context#

This single field determines most of the bot behaviour. It supports placeholders, which makes it dynamic:

You are the assistant for %%blog_title%%.

The visitor is %%user_display_name%% (role: %%user_role%%).
They are currently reading: %%post_title%%
Page content: %%post_content_plain_text%%

Answer questions about this page. If the question is not about it, say so and
suggest they use the site search.

Useful placeholders here: %%post_title%%, %%post_content%%, %%post_content_plain_text%%, %%post_excerpt%%, %%post_cats%%, %%post_tags%%, %%post_link%%, %%user_name%%, %%user_display_name%%, %%user_firstname%%, %%user_lastname%%, %%user_email%%, %%user_role%%, %%user_id%%, %%user_language%%, %%blog_title%%, %%author_name%%, %%current_date_time%%, %%privacy_policy_url%%.

Model and capabilities#

SettingWhat it controls
Bot ModelWhich model answers. Latency matters more than eloquence here
Bot Assistant NameUse an AI Assistant instead. Doing so disables personas
Enable Bot VisionVisitors can send images. Requires a vision-capable model
Enable File Uploads To The BotGeneral file uploads. See Files and PDF chat
Enable Chatbot Instant ResponsesReply from a cache or a scripted answer where possible, without a model call
Allow Users To Stop Response Creation When StreamingA stop button during streaming
Default Chat Modetext or image — whether the bot writes or generates images by default

API parameters#

AI Chatbot › API Parameters

SettingDefaultWhat it controls
Chatbot Max Token CountOutput cap per reply. Keep it modest; long chat replies are rarely wanted
Chatbot Temperature1Lower is more consistent, higher more varied. For support bots, 0.3–0.7
Chatbot Top_p1Adjust this or temperature, not both
Presence Penalty0Discourages returning to topics already covered
Frequency Penalty0Discourages repeating words
Store AI Prompts On OpenAI's PartWhether the provider may retain the request

Conversation context#

SettingWhat it controls
Max Chat Messages To Send As API ContextHow many previous turns are resent with each message
Max Chat Context Size (Characters)A character cap on that history
Single Message Max Input Length (Characters)Longest message a visitor may send
Disable Sending Of Empty Chat MessagesRejects empty submissions

Prompt modifiers#

SettingWhat it controls
Prepend Text To All Textual AI Prompts From AI ChatbotsAdded before every message
Append Text To All Textual AI Prompts From AI ChatbotsAdded after every message
Conversation StartersSuggested questions shown to the visitor
Prompt TemplatesPredefined prompts the visitor can select
Prompts Editable By UsersWhether visitors can edit a selected template
Text For Prompt Templates SelectionThe label on the selector

The append field is a good place for a persistent formatting instruction, such as "always answer in at most three short paragraphs".

Response processing#

SettingWhat it controls
Convert Markdown To HTML In AI Generated ContentRenders markdown. Usually wanted
Enable Katex (Mathematical Expressions Rendering)Renders LaTeX maths
Enable Chatbot Full HTML Response ProcessingAllows HTML in replies
Strip JavaScript From Chatbot HTML ResponsesRemoves scripts. Leave this on
Disable Chatbot Modern Response ProcessingFalls back to the older rendering path
Chatbot Response Delay (ms)Artificial delay before the reply appears
Typewriter Delay (ms)Speed of the typing effect

Interaction#

SettingWhat it controls
Enable Message Copying By Clicking ItClick to copy a message
Enable Chat Message Editing By Clicking ItVisitors can edit and resend
Scroll To Bottom Of The Form On New MessagesAuto-scroll
Up/Down Keys Show Older Messages In ChatShell-style history
Download Chat Conversation To File AsExport format for the download button

Retry behaviour#

Chat End of Conversation Retry Count (Settings › General Settings) retries when the model produces a reply the plugin reads as ending the conversation. Each retry is another paid request — 1 or 2 is enough.

Still stuck? Open a support ticket and include the diagnostics from Aimogen Pro › System & Logs › System Info.