Where settings live

In your WordPress admin: ReplyMind — a top-level sidebar item just below Comments. Five tabs switch instantly without a page reload: Settings, Reply Rules, Analytics, Logs, and Batch Process. This page documents the Settings tab, which has two sections: Core Settings and Advanced Settings. Hover the ⓘ icon next to any advanced option for an inline explanation.


AI provider credentials

ReplyMind 1.1+ does not use a plugin-stored API key; the field is hidden whenever the AI Client is active (a legacy replymind_api_key option is kept only for backward compatibility). Credentials are managed by WordPress core under Settings → Connectors and used through the built-in AI Client (wp_ai_client_prompt(), WordPress 7.0+). Configure a provider there once and every AI-aware plugin on the site, including ReplyMind, uses it. The Core Settings panel shows whether the AI Client was detected.


AI Provider

Which provider the AI Client should route ReplyMind's requests to. The provider must also be configured in Settings → Connectors.

Value Model prefix
openai (default)gpt-
claudeclaude-
geminigemini-

Internally claude maps to core's anthropic provider and gemini to google. If the selected model's prefix doesn't match the provider, the plugin shows a mismatch warning on the Settings screen.


Model

Which model to call within the selected provider. The dropdown filters automatically based on Provider.

OpenAI models

ValueNotes
gpt-5-mini (default)Best value for most blogs
gpt-5-nanoCheapest, fastest
gpt-5Highest quality
gpt-4o, gpt-4o-miniPrevious generation
gpt-4-turbo, gpt-4, gpt-3.5-turboLegacy

Anthropic Claude models

ValueNotes
claude-haiku-4-5-20251001Fastest, cheapest
claude-sonnet-4-6 (default)Recommended balance
claude-opus-4-8Highest quality
claude-opus-4-7, claude-opus-4-6Previous Opus releases

Google Gemini models

ValueNotes
gemini-2.5-flash-liteCheapest, fastest
gemini-2.5-flash (default)Recommended balance
gemini-2.5-proHigher quality
gemini-3-proHighest quality

Enable Plugin

A single checkbox. When unchecked the plugin still loads but does not generate replies for new comments. Default: unchecked.

Value Behaviour
1 (checked) New comments are queued for AI reply
0 (unchecked, default) New comments are ignored

Reply Mode

Controls what happens after a draft is generated.

Value Behaviour
suggestion (default) Save the AI reply as a draft. You review and publish manually.
auto Post the AI reply automatically when generated.

In suggestion mode the AI Reply column shows Draft Ready with an inline preview. In auto mode it shows Published.


Reply Tone

6 options. Sets the tone instruction sent to the AI. Can be overridden per post, by a Reply Rule, or by Sentiment detection.

Value Default tone instruction
professional (default) Use a professional and respectful tone.
friendly Use a friendly and welcoming tone.
casual Use a casual and approachable tone.
empathetic Use an empathetic and understanding tone, acknowledging the commenter's perspective and feelings.
formal Use a formal and authoritative tone suitable for academic or corporate audiences.
concise Reply in one or two sentences only, with no padding.

Response Length

3 options. Controls the AI's length instruction.

Value Length instruction
short (default) 2–3 sentences maximum.
medium One paragraph of 4–5 sentences.
detailed 2–3 paragraphs.

Reply Language

11 options. Controls what language the AI replies in.

Value Behaviour
auto (default) Detect the commenter's language and reply in the same one
en Always reply in English
es Always reply in Spanish
fr Always reply in French
de Always reply in German
it Always reply in Italian
pt Always reply in Portuguese
hi Always reply in Hindi
ar Always reply in Arabic
ja Always reply in Japanese
zh Always reply in Chinese

System Prompt

Free-form textarea. Included with every AI generation as the system message.

Detail Value
Type Textarea (5 rows)
Default Reply professionally and helpfully to blog comments.
Sanitization sanitize_textarea_field
Storage replymind_settings['prompt']

The system prompt is combined with the tone instruction, response length instruction, language instruction, post context, any per-post or rule-appended instructions, and the prompt-injection guard before being sent to the AI.


Advanced Settings

Everything below is optional and off by default. Each option has its own page:

OptionSummary
Sentiment DetectionLocal keyword scoring; flag, skip, or switch to Empathetic for negative comments.
Email ApprovalOne-click Approve / Reject links emailed to the post author (Suggestion mode). Fallback recipient defaults to the admin email.
Reply SchedulingDelay Auto-mode replies by 1–168 hours (default 1).
Multi-Provider by TaxonomyMap any taxonomy term to a provider + model.
WooCommerce ReviewsAI replies for product reviews with product context.

Advanced settings are stored in the replymind_pro_settings option. Reply Rules and the Analytics dashboard have their own tabs. Per-post settings live in the post editor meta box. Multisite options are under Network Admin.


Hidden constants and filters

Some behaviour isn't exposed in the UI but can be changed in code:

Daily reply cap

add_filter( 'replymind_daily_limit', fn() => 500 );
// Set to 0 to disable the cap entirely.
Detail Value
Default cap 100 successful API calls per day
Counter storage Transient replymind_daily_YYYYMMDD
Reset Daily, server timezone

Skip specific comments

add_filter( 'replymind_send_comment_data', function ( $allow, $comment ) {
    if ( /* your condition */ ) {
        return false;
    }
    return $allow;
}, 10, 2 );

See Developer reference for the full list of filters and hooks.


All settings at a glance

Setting Default Allowed
Provider openai openai, claude, gemini
Model gpt-5-mini one of the model lists above
Enable Plugin off on, off
Reply Mode suggestion suggestion, auto
Tone professional 6 tones
Response Length short short, medium, detailed
Language auto 11 codes
System Prompt translated default any textarea content