Questions, answered.

AI Reply Assistant is a Singapore-built iOS app that connects to WhatsApp and Telegram directly from your device, bringing them into one secure inbox. Messages go straight from your phone to the network — they never touch our servers. Apple Intelligence is built in through on-device processing. With Claude, you get even more expertise to handle more complex requests — bring your own API key.

WhatsApp and Telegram today, both via on-device connections. Messages go straight from your device to the network — preserving end-to-end encryption and never touching our servers. WhatsApp connects via Whatsmeow; Telegram via TDLib. AI Reply Assistant is a messaging app — voice and video calls are not supported. More platforms are on the roadmap.

iOS 26 or later, on an Apple Intelligence-capable device (iPhone 15 Pro and later). AI Reply Assistant is iOS-only — no Android, no web.

A Skill is a modular capability that packages instructions, context, and best practices to transform AI Reply Assistant into a specialist for any relationship or domain. Each Skill has its own voice, tone, system prompt, and Knowledge Base — giving you domain-specific expertise that loads on demand. AI Reply Assistant ships with nine built-in Skills — General Assistant, Family Circle, Best Friend, Work Team, Concierge, Event Planner, Travel Buddy, Social Group, and Dating. You can also create your own or import community Skills from the built-in Skills Marketplace.

Tap the + button in your Skill library. Give it a name, write a system prompt describing the personality you want, and adjust the tone sliders. You can also pick a category, choose an AI model, and optionally attach a Knowledge Base. Your custom Skill is ready to use immediately.

Every Skill has five tone sliders — creativity, formality, directness, empathy, and length — plus sampling controls (Consistent / Balanced / Varied). You can edit the system prompt directly, switch between Apple Intelligence (built in) and Claude (even more expertise) per Skill, attach a Knowledge Base with your own documents, and enable Extended Thinking for enhanced reasoning with Claude.

The Skills Marketplace is a built-in browser powered by SkillsMP that gives you access to over a million community-created Skills. Browse by category — Business, Content, Documentation, Lifestyle, Research, and more — preview any Skill, and import it into your library with one tap. You can then customise it to fit your needs.

A Knowledge Base lets you attach documents, URLs, and custom instructions to a Skill. When drafting replies, the AI references this material to give more informed, contextual responses. For example, a "Brand Voice" Skill could include your company's tone guidelines, or a "Legal" Skill could reference compliance documents. You can attach up to 10 documents and 20 URLs per Skill.

PDFs, Word documents (DOCX), rich text (RTF), Markdown, HTML, plain text, and common code files (Swift, JavaScript, Python, JSON, CSV, and more). You can also add images — AI Reply Assistant extracts text from those too. Each file can be up to 50 MB, with a total limit of 100 MB per Skill.

RAG stands for Retrieval-Augmented Generation. Instead of relying solely on the AI model's built-in knowledge, RAG lets AI Reply Assistant search your Knowledge Base documents for relevant information and include it in the prompt before generating a reply. This means the AI's responses are grounded in your actual documents — your company guidelines, reference material, or personal notes — rather than generic training data.

When you add a document to a Knowledge Base, AI Reply Assistant breaks it into small chunks, generates a mathematical representation (embedding) of each chunk, and stores them on-device. When you ask for a reply, AI Reply Assistant converts your conversation into a query, finds the most relevant chunks using similarity search, and feeds them to the AI alongside the conversation. The AI then drafts a reply informed by both the thread and your documents — all on your device.

RAG works with both. On iOS 26, Apple Intelligence powers the document processing pipeline — chunking, embedding, query optimisation, and retrieval all run on-device using Apple Foundation Models. The retrieved context is then passed to whichever AI provider your Skill uses (Apple Intelligence or Claude) for the final reply.

Yes. All document processing — text extraction, chunking, embedding, and similarity search — happens entirely on your device. Your documents are never uploaded to any server. The only time Knowledge Base content leaves your phone is if your Skill uses Claude, in which case the relevant retrieved chunks (not the full documents) are sent to Anthropic as part of the prompt.

Creativity sets how inventive or predictable the AI's language is (higher means more varied word choices). Formality shifts between casual and professional tone. Directness controls whether replies are blunt and to-the-point or softer and more diplomatic. Empathy adjusts how much emotional awareness and warmth the AI shows. Length determines how brief or detailed the reply is. Each slider works together with the system prompt to shape the Skill's overall voice.

Sampling controls how the AI picks its next word. Consistent (greedy) always picks the most likely word — great for factual, predictable replies. Balanced (top-K) samples from a curated set of likely words — good for natural-sounding conversation. Varied (top-P) samples from a wider probability range — best for creative or playful replies. You can set this per Skill.

Extended Thinking gives Claude enhanced reasoning capabilities for complex tasks. It is not a different model — it is allowing the very same model to give itself more time and expend more effort in coming to an answer. When enabled, Claude reasons step-by-step through the conversation context, your Knowledge Base material, and the right tone before writing its reply. AI Reply Assistant has decided to make its thought process visible in raw form — being able to observe the way Claude thinks makes it easier to understand and check its answers. You can set a thinking budget to control precisely how long Claude spends on a problem. Larger budgets can improve response quality by enabling more thorough analysis.

Yes. Apple Intelligence is built in through on-device processing. With Claude, you get even more expertise — choose between three models: Haiku 4.5 is the fastest, most cost-efficient model with near-frontier intelligence. Sonnet 4.6 is a hybrid reasoning model with the best combination of speed and intelligence — it can produce near-instant responses or extended, step-by-step thinking. Opus 4.6 is the most capable generally available model for complex reasoning and agentic coding. You can also enable Extended Thinking on any model for enhanced reasoning capabilities.

Apple Intelligence is integrated into AI Reply Assistant through on-device processing — free, fast, and private. Its on-device model has a 4,096-token context window (~3,000 words), supports text only (no images or PDFs), and is best for focused, everyday tasks. With Claude, you get even more expertise to handle more complex requests: up to 1M tokens of context, extended thinking for complex reasoning, multimodal understanding (images, charts, PDFs), 22 tools with agentic iteration, and document creation (PPTX, XLSX, PDF, DOCX). You control when Claude is used — bring your own Anthropic API key and switch per chat or per Skill.

Smart Reply gives you Apple's native quick suggestions. AI Reply drafts a full reply using your active Skill. Analyze summarises the day's thread so you can catch up in seconds.

Use a built-in Skill when the relationship fits — family, work, dating, etc. Create a custom Skill when you have a specific context that repeats: a particular client, a community with its own jargon, a professional domain like legal or medical, or any situation where you want the AI to follow particular guidelines every time.

Claude Haiku 4.5 by default — the fastest, most cost-efficient model with near-frontier intelligence. You can switch to Sonnet 4.6, a hybrid reasoning model with the best combination of speed and intelligence that can compress multi-day tasks into hours. Or choose Opus 4.6, the most capable generally available model for complex reasoning and agentic coding — it handles complex, long-running tasks with rigor and consistency. All three support Extended Thinking. Switch in Chat Settings at any time.

Open your Skill library and tap the Marketplace button. Browse or search for a Skill, tap to preview it, then tap Import. The Skill is added to your library instantly. From there you can customise the tone, system prompt, and other settings before using it.

The marketplace hosts over a million Skills across categories including Business (sales, marketing, finance), Content & Media (writing, design), Documentation (knowledge bases, technical docs), Data & AI, Lifestyle (wellness, writing, arts), and Research (academic, scientific). Whether you need a brand-voice enforcer, a customer-service persona, or a creative writing coach — there is likely a community Skill for it.

Yes. The marketplace is only used for browsing and downloading the Skill definition (a text-based instruction set). Once imported, the Skill runs locally in AI Reply Assistant just like any built-in Skill. No message data is ever shared with the marketplace.

Absolutely. An imported Skill is fully editable — you can change its name, rewrite the system prompt, adjust tone sliders, switch its AI model, or attach your own Knowledge Base. Think of it as a starting point you can make your own.

No. AI Reply Assistant uses on-device connections for WhatsApp and Telegram — messages go straight from your device to the network, never through our servers. Apple Intelligence is integrated through on-device processing — nothing leaves your phone. You control when Claude is used, and even then it goes directly to Anthropic, not through Flowbie.

On-device connections mean messages are sent directly from your device to the network — they never sit on our servers or any third-party server. Your Skills, settings, and message history live only on your device. Apple Intelligence sessions are isolated and capped per Apple's privacy guarantees.

The minimum needed for the app to run — basic crash diagnostics and your subscription state if applicable. We do not collect message contents. Full details in the Privacy policy.

Yes. Your API key is stored in the iOS Keychain, never sent to Flowbie, and used only by your device when you trigger a Claude reply.

No. Cloud Model is per-conversation. You explicitly grant Claude access to a chat before it can search or draft for that thread. Untouched conversations stay on-device only — Claude never sees them.

Any AI that reads untrusted text is exposed to prompt injection. AI Reply Assistant's Cloud Model only acts on chats you have explicitly granted access to, and never sends messages or files automatically — every reply is reviewed and sent by you. We treat incoming text as untrusted input and do not let it issue commands to the model.

The Claude Agent is a built-in agentic AI assistant that dynamically directs its own processes and tool usage, maintaining control over how it accomplishes tasks. It uses tool use — Claude decides when to call a tool based on your request and the tool's description, then AI Reply Assistant executes it natively on your device. Search your messages, check your calendar, create reminders, look up contacts, browse the web, generate images, and more. Tool access is one of the highest-leverage capabilities you can give an agent — it grounds Claude's responses in real-time context, not just the chat thread.

You are always in control. When Claude drafts a message, it appears as a card in your chat. You choose which conversations to send it to, review the content, and confirm with a final prompt before anything is sent. This human-in-the-loop design ensures every outgoing message reflects your intent.

Yes. Before using message-related tools, you select which conversations Claude can access using the scope picker. Claude can only search and read messages within those specific conversations — everything else remains invisible to the AI. You can change or clear this selection at any time.

Tool use lets Claude call functions that AI Reply Assistant defines. Claude decides when to call a tool based on your request and the tool's description, then AI Reply Assistant executes it natively on your device. The agent has access to 22 tools across categories you can toggle on or off: Calendar (view and create events), Reminders (view and create tasks), Contacts (search your address book), Web Search (browse the internet), Image Generation (create images on-device via Apple Intelligence), Message Search (find messages in scoped conversations), Files (with Files API for cloud-based file management), Document Creation (Word, Markdown, CSV, JSON, HTML), Agent Skills (pre-built server-side skills for PowerPoint, Excel, PDF, and Word generation), Location, Weather, Memory, and more. Tool access is one of the highest-leverage capabilities you can give an agent — it grounds Claude's responses in real-time context, not just the chat thread.

The context window refers to all the text a language model can reference when generating a response, including the response itself — a working memory for the model. A larger context window allows the model to handle more complex and lengthy prompts, but more context isn't automatically better. AI Reply Assistant actively manages this for you: compaction extends the effective context length by automatically summarising older context when approaching the limit, keeping the active context focused and performant. Prompt caching optimises API usage by resuming from specific prefixes, significantly reducing processing time and costs for repetitive tasks. Tool definitions are loaded on-demand rather than all at once to preserve working memory. Attachments are deduplicated to avoid waste. When a conversation approaches its context limit, AI Reply Assistant prompts you to compact or start a fresh topic.

MCP (Model Context Protocol) is an open standard for connecting AI assistants to the systems where data lives, including content repositories, business tools, and development environments. It provides a universal, open standard for connecting AI systems with data sources, replacing fragmented integrations with a single protocol. Think of MCP like a USB-C port for AI applications: just as USB-C provides a standardised way to connect electronic devices, MCP provides a standardised way to connect AI applications to external systems. MCP is designed primarily for desktop and server environments. AI Reply Assistant takes a complementary approach: instead of connecting to external MCP servers, the agent runs natively on iOS and executes tools directly through Apple's own frameworks (EventKit, Contacts, and others) within the iOS app sandbox. Your data benefits from iOS-level permissions, every action requires your explicit approval, and tools run with the same security guarantees as any native app.

Yes. Every tool call is shown as a step in your conversation — you can see what tool was used, what parameters were passed, whether it succeeded or failed, and what it returned. Extended Thinking is also visible when enabled, so you can follow Claude's reasoning before it responds.

AI Reply Assistant tracks your context usage and shows a suggestion when the conversation approaches its limit. You can compact the conversation to keep only recent context, or start a new topic. Each topic has its own isolated conversation history, so switching topics gives you a fresh context window without losing previous work.

Three models are available. Haiku 4.5 is the fastest, most cost-efficient model, delivering near-frontier intelligence at a fraction of the cost — ideal for quick drafting. Sonnet 4.6 is a hybrid reasoning model with the best combination of speed and intelligence — it can produce near-instant responses or extended, step-by-step thinking, and compress multi-day tasks into hours. Opus 4.6 is the most capable generally available model for complex reasoning and agentic coding — it handles complex, long-running tasks with rigor and consistency. You can switch models mid-conversation and the next response uses your selection. Opus and Sonnet support up to 1 million tokens of context; Haiku supports 200K.

Extended Thinking gives Claude enhanced reasoning capabilities for complex tasks, while providing transparency into its step-by-step thought process before it delivers its final answer. It is not a different model — it is allowing the very same model to give itself more time and expend more effort in coming to an answer. You can set a thinking budget to control precisely how long Claude spends on a problem: low, medium, or high. Larger budgets can improve response quality by enabling more thorough analysis. AI Reply Assistant makes Claude's thought process visible in raw form — you see the step-by-step reasoning in real-time as a collapsible "Thinking" block with an elapsed timer. Being able to observe the way Claude thinks makes it easier to understand and check its answers. Opus and Sonnet use adaptive thinking that automatically adjusts effort to the task; Haiku uses a fixed thinking budget.

Yes. Five response styles are available: Normal (balanced), Learning (patient, step-by-step explanations), Concise (short bullet points, no elaboration), Explanatory (detailed and educational), and Formal (professional and structured). Pick a style before sending your message — it shapes how Claude formats its reply.

Yes. Claude's vision capabilities allow it to understand and analyse images, opening up exciting possibilities for multimodal interaction. Claude can process a wide range of visual formats, including photos, charts, graphs, and technical diagrams. You can attach up to 5 images (from your photo library or camera) and up to 5 PDFs per message. Multiple images can be included in a single request, which Claude will analyse jointly when formulating its response. For PDFs, you can ask Claude about any text, pictures, charts, and tables in the documents you provide — from analysing financial reports to extracting key information from legal documents. The Files API lets you upload files once and reference them across multiple conversations without re-uploading.

Claude is capable of providing detailed citations when answering questions about documents, helping you track and verify information sources in responses. Citations are guaranteed to contain valid pointers to the provided documents — significantly more reliable and more likely to cite the most relevant quotes compared to purely prompt-based approaches. When Claude uses web search or references documents, inline citation markers (superscript numbers) appear in the response text. Tap the "Sources" pill to see a full list with favicons, titles, domains, and the cited text from each source. Web sources are tappable to open the original page.

Action cards are structured outputs Claude creates when it wants to take an action on your behalf. Each card appears visually in the chat with a preview of what will be sent or created. There are two categories: **Messaging cards** — send content to WhatsApp, Telegram, or iMessage. You pick recipients and confirm before anything is sent: • Draft Message — text message • Image Message — photo with caption • Video Message — video with caption • Audio Message — voice or audio file • File Message — document or PDF • Contact Message — share a contact card (vCard) • Event Message — share a calendar event (ICS) • Location Message — share a map pin • Poll Message — create an interactive poll **OS cards** — create items on your device with a single tap: • Event — add to Calendar • Reminder — add to Reminders • Contact — add to Contacts • Note — save to Notes • Link — open a URL • Image — save a generated image to Photos **Agent Skills cards** — documents generated server-side by Claude: • Skill File — preview, share, or save PowerPoint, Excel, PDF, and Word documents created by pre-built Agent Skills Every card shows real-time status: working, done, sent (with recipient count), or failed with a retry option.

AI Reply Assistant tracks delivery per recipient. If some sends fail, you see a summary — "Sent to 2 of 3 chats" with the failure reason for the first error. The retry flow pre-selects only the failed recipients so you can resend without duplicating to those that succeeded.

Yes. A stop button appears while Claude is generating a response. Tap it to cancel immediately. You can also regenerate the last response if you want Claude to try again with a different approach.

Each completed response has action buttons: Copy (to clipboard), Share (via the iOS share sheet), and Speak (reads the response aloud, with a stop toggle). In overlay mode, a "Use as Reply" button lets you send the response directly back to your messaging conversation. You can also select any text natively for Look Up, Translate, or Writing Tools.

Topics let you organise separate conversations within the agent. Each topic has its own message history, context window, and persona. You can create named topics, pin important ones, close finished ones, reorder them, and customise their icons. Switching topics gives you a fresh context without losing previous work.

Overlay mode launches the Claude Agent from within a messaging conversation. The agent is pre-scoped to that chat and pre-loaded with the active Skill. When Claude drafts a response you like, tap "Use as Reply" to send it directly back to the conversation you came from. It is a quick way to get AI help without leaving your thread.

Yes. Multi-agent orchestration lets one agent coordinate with others to complete complex work. Agents can act in parallel with their own isolated context, which helps improve output quality and time to completion. For example, one sub-agent can search the web while another analyses your messages. Each sub-agent has its own conversation history and restricted tool access — no message sending or further delegation. Only one level of delegation is supported: the coordinator can call other agents, but those agents cannot call agents of their own. Sub-agents are capped at 15 turns per task.

Managed Agents provides the harness and infrastructure for running Claude as an autonomous agent. Instead of building and running the agent loop on your device, you get a fully managed environment where Claude dynamically directs its own processes and tool usage — orchestrating tool calls, maintaining persistent conversation history, and handling multi-step workflows server-side while your device executes tools locally and streams results back. Managed sessions, persistent history, and frontier models mean you get the agent, not the infrastructure. You can toggle this per topic from the model picker — available for Opus and Sonnet.

Yes. The agent supports VoiceOver with labels and hints on every interactive element, Dynamic Type for scalable text, native text selection with Look Up, Translate, and Writing Tools, and haptic feedback on key actions. It also adapts fully to dark mode.

AI Tools give your Skill real-time access to information on your device and the web. Instead of relying only on what is in the chat thread, a Skill with tools enabled can search the web, check your calendar, look up contacts, fetch the weather, read files, generate images, and more — all while drafting a reply.

Each Skill can have up to five tools enabled at a time. Some tools — like Knowledge Base and URL Fetcher — auto-enable based on your Skill's configuration and do not count toward the five-tool limit.

AI Reply Assistant offers 22 tools across six categories: Research and Knowledge (Web Search, Knowledge Base, URL Fetcher), People and Messages (Contacts, Platform Contacts, Messages, Message Context, Unread Summary, Chat Discovery, Forum Topics, Group Members, Mutual Chats), Schedule and Tasks (Calendar, Reminders), Location and Weather (Location, Weather), Files and Creation (Files, Image Generation, Document Creation, Agent Skills), and Agent Intelligence (Memory, Sub-agent).

The web search tool gives Claude direct access to real-time web content, allowing it to answer questions with up-to-date information beyond its knowledge cutoff. It uses a four-stage pipeline: (1) search for results, (2) intelligently select the most relevant results, (3) fetch pages concurrently, and (4) summarise each page within a token budget. The response includes citations for sources drawn from search results. Only the search query is sent — your messages never leave your device.

When you attach documents (PDF, DOCX, TXT) or URLs to a Skill, the Knowledge Base tool uses a hybrid search combining 80% semantic similarity with 20% keyword matching. Results are then reranked by an AI model for relevance. The tool auto-enables when you add documents — no manual toggle needed.

Only if you grant Calendar permission and enable the Calendar tool on a Skill. It can search events by title, date, or location — up to 90 days back and a year ahead. It reads events but never creates or modifies them. All calendar data stays on your device.

The Weather tool uses Apple WeatherKit to provide current conditions, a 12-hour hourly forecast, and a 7-day daily forecast — including alerts, sunrise and sunset times, and automatic metric or imperial conversion based on your locale. Only a location coordinate is sent to Apple; no message data is shared.

Yes — with Image Playground, you can create fun, original images entirely on-device. Choose from three styles: Animation, Illustration, and Sketch. All images are created on device, giving you the freedom to experiment with as many images as you want. The tool supports multiple concepts per image.

Agent Skills are modular capabilities that extend Claude's functionality. Each Skill packages instructions, metadata, and optional resources that Claude uses automatically when relevant. The code execution tool allows Claude to run code in a secure, sandboxed environment to analyse data, create visualisations, perform complex calculations, and generate files. The following pre-built Agent Skills are available for immediate use: PowerPoint (.pptx) — create presentations, edit slides, analyse presentation content. Excel (.xlsx) — create spreadsheets, analyse data, generate reports with charts. Word (.docx) — create documents, edit content, format text. PDF (.pdf) — generate formatted PDF documents and reports. Files are downloaded automatically and presented as previewable, shareable file cards in your conversation. You can preview with QuickLook, share via the iOS share sheet, or save to Files. Agent Skills use your Anthropic API key directly — no Flowbie servers are involved.

Document Creation is a local tool — Claude writes content and AI Reply Assistant creates the file on your device. It supports TXT, Markdown, CSV, JSON, HTML, and Word (.docx) with full formatting. Agent Skills, on the other hand, use Claude's server-side code execution to generate more complex documents like PowerPoint presentations and Excel spreadsheets with charts. Use Document Creation for quick text-based files that stay on-device; use Agent Skills when you need richer formats like .pptx or .xlsx.

The Memory tool enables Claude to store and retrieve information across conversations, allowing it to build knowledge over time without keeping everything in the context window. Claude automatically checks its memory before starting tasks and can create, read, update, and delete facts — like "my wife's name is Sarah" or "I prefer window seats". Memories are stored locally on your device, eliminating the need to re-explain context.

The Messages tool searches your local message database with 15+ filters — sender, platform, date range, message type, starred, forwarded, media type, and more. When exact matches are not found, it automatically falls back to semantic search to find relevant results by meaning rather than keywords.

Most tools run entirely on-device — Calendar, Contacts, Reminders, Location, Files, Photos, Messages, Memory, and Image Generation never send your data anywhere. Web Search sends only the search query (not your messages) to DuckDuckGo. Weather sends a location coordinate to Apple WeatherKit. URL Fetcher fetches only the configured URL. Tool permissions are managed per Skill.

Knowledge Base and URL Fetcher turn on automatically when you add documents or URLs to a Skill. They do not count toward the five-tool limit. This ensures your Skill always has access to the context you have given it, without needing manual configuration.

Yes. Every tool invocation appears inline in your chat as a tappable pill showing the tool name and status. Tap it to see the full details — what parameters were used, whether it succeeded or failed, and what results it returned, including any citations or sources.

Tools are designed with graceful fallbacks. If a web page cannot be fetched, cached content is used. If a tool encounters an error, the AI continues without that data and notes the limitation. Errors are shown inline so you always know what happened.

Yes. The tool system is provider-agnostic — the same tools are available regardless of whether your Skill uses Apple Intelligence or Claude. This means you get calendar access, web search, and everything else with either AI provider.

Yes. You choose which tools each Skill can use in the Skill editor — toggle them on or off individually, up to five at a time. Knowledge Base and URL Fetcher auto-enable based on your configuration but can be overridden. Tools that require iOS permissions (Calendar, Contacts, Location, Photos, Reminders) will prompt for access the first time they are used.

No. Each tool operates independently within the context of the active conversation. The Calendar tool cannot see your Contacts data, and the Web Search tool cannot read your Files. The AI model may use the results from one tool to inform a query to another — for example, checking your calendar after looking up a contact — but the tools themselves do not exchange data directly.

Both platforms use phone number authentication. Enter your phone number, receive a verification code, and confirm — AI Reply Assistant registers as a linked device on your account. WhatsApp connects via the Multi-Device protocol; Telegram via the Client API (TDLib). Both are on-device connections — messages go straight from your device to the network and never touch our servers.

AI Reply Assistant supports both **WhatsApp Personal** (for individuals) and **WhatsApp Business App** (for small businesses) accounts. When you connect, you enter your phone number and a pairing code to link AI Reply Assistant as a companion device using WhatsApp's Multi-Device protocol. Any account that supports linked devices works with AI Reply Assistant. AI Reply Assistant **does not** use the WhatsApp Business API/Platform (also known as WhatsApp Cloud API). That is a separate, server-side product designed for medium and large enterprises to send automated messages at scale through third-party providers. Here is how they compare: **AI Reply Assistant (Multi-Device protocol)** • Connects from your iPhone as a linked device • Works with both WhatsApp Personal and WhatsApp Business App accounts • Messages go directly from your device to WhatsApp's network • End-to-end encryption preserved • No per-message charges **WhatsApp Business API/Platform** • Server-side integration for medium/large enterprises — not an app • Requires developer setup or a Business Messaging Partner • Messages route through third-party servers • Per-conversation charges apply • Designed for automated, high-volume messaging In short: if you use the WhatsApp or WhatsApp Business app on your iPhone, AI Reply Assistant works with your account.

AI Reply Assistant supports all Telegram user accounts — **Personal**, **Premium**, **Business**, and **Anonymous/Numberless**. When you connect, you enter your phone number and a verification code to authenticate via Telegram's Client API (TDLib), the same technology behind Telegram Desktop and other official clients. • **Personal accounts (free)** — Full support. The standard user account linked to a phone number for personal messaging. • **Telegram Premium** — Full support. A paid subscription with enhanced features like faster downloads, exclusive stickers, and increased limits — all carry over to AI Reply Assistant. • **Telegram Business** — Full support. A specialised account for companies, with features like operating hours, location sharing, automated greetings, quick replies, and chatbot support. Business tools work alongside AI Reply Assistant's own features. • **Anonymous/Numberless accounts** — Full support. Accounts created using blockchain-based numbers (e.g. via Fragment) rather than a physical SIM card. Enter the Fragment number the same way — AI Reply Assistant does not distinguish between SIM-based and Fragment-based numbers. **Bot accounts are not supported.** Telegram bots are specialised accounts designed for automated tasks like managing groups or providing customer support. They are created via @BotFather, do not have a phone number, and cannot authenticate through TDLib. You can still receive and reply to messages from bots in your AI Reply Assistant inbox — you just cannot log in as a bot. AI Reply Assistant does not use the Telegram Bot API. Your messages are sent directly from your device to Telegram's network using the same protocol as the official Telegram app.

Yes — AI Reply Assistant supports all major Telegram bot features: • **Bot commands** — Type / in a bot’s private chat to see its available commands in a scrollable autocomplete menu. Tap a command to send it instantly. In non-bot chats, typing / triggers Quick Reply instead (see the Quick Reply section below). • **Inline keyboards** — Interactive buttons below bot messages (URL, callback, login auth, switch inline, payment, and more) • **Reply keyboards** — Custom keyboards with bot-defined answer options (one-time, persistent, resizable) • **Mini Apps (Web Apps)** — Full Telegram Web App JS bridge with theme sync, haptic feedback, native popups, and data exchange • **Inline mode** — Type @botname to query inline bots and send results (articles, photos, GIFs, videos, stickers) • **HTML5 games** — Play button opens games in a WebView with score tracking • **Dice and emoji rolls** — Dedicated dice bubble for 🎲🎯🏀🎳⚽🎰 • **Invoices and payments** — Pay with Telegram Stars directly from invoice bubbles • **Paid media** — Unlock photos and videos behind a Stars paywall • **Deep linking** — Open t.me/botname?start=param links to launch bots with parameters • **Bot description panel** — See the bot’s description and Start button in empty chats • **Peer selection** — Share users, groups, or channels with bots via filtered picker • **Attachment menu bots** — Add approved bots to the attachment menu for quick access You interact with bots as a regular Telegram user — you cannot log in as a bot account.

Yes — AI Reply Assistant exposes 22 Shortcuts actions across four categories: Send (messages, media, polls, locations, contacts, events), Create (groups, quick replies, scheduled messages, Skills), Find (conversations, messages, contacts, and more with Reminders-style filtering), and Open (jump to any conversation, contact, or message). Every action also works with Siri. See the Apple Shortcuts and Siri section below for details.

Yes. Writing Tools are available right in AI Reply Assistant's input bar — proofread your text, rewrite different versions until the tone and wording are just right, and summarize selected text with a tap. Available nearly everywhere you write.

Quick Reply presets are available as a Home Screen widget and in Control Center — so you can fire off "On my way" or "Got it" without opening the app.

Email support@flowbie.sg or drop a note via the Support page. We read every one.

Quick Replies let you save and send the messages you use most frequently — like WhatsApp Business's quick replies for providing fast answers to common questions, but with more power. Beyond simple text templates, AI Reply Assistant Quick Replies support variables like {recipientName} or {currentDate} for automatic personalisation, media attachments (photos, videos, files), and can be sent from your Home Screen widget or Control Center without opening the app. No character limits, no keyword restrictions, unlimited saved replies.

Open the Quick Reply Library in AI Reply Assistant and tap the + button. Type your message, optionally add media attachments and variables, choose a folder, and save. You can also create Quick Replies via Siri or the "Create quick reply" Apple Shortcut.

Yes. Each Quick Reply supports up to 10 media attachments — images, videos, audio, documents, voice notes, and GIFs. Each file can be up to 25 MB. You can add a caption with variable placeholders to each attachment.

Variables let you send personalised messages without editing each one by hand. Write a template once — "Hi {recipientFirstName}, thanks for reaching out to {businessName}" — and AI Reply Assistant fills in the right values for every recipient at send time. Six variables are available: {recipientName} (full name), {recipientFirstName}, {currentDate}, {currentTime}, {recipientPhone}, and {businessName}. They work in both message text and media captions.

Quick Reply sends to WhatsApp, Telegram, iMessage, and SMS. Text and variables work on all four. Media attachments work on WhatsApp, Telegram, and iMessage. SMS is text-only.

On iOS 26, Apple Intelligence can generate Quick Reply suggestions based on a topic or context you describe. It analyses your existing replies and messaging style to match your voice. Adjust the creativity level, choose how many suggestions to generate (1–10), and toggle context sources like your sent message history.

Use folders to group related replies, add tags for cross-cutting labels, and star your most-used replies as favourites. You can also enable or disable individual replies without deleting them, and add emoji icons with colour coding for quick visual scanning.

Add a Quick Reply widget to your Home Screen in a 2×2, 3×2, or 3×3 grid layout. Each cell shows one saved reply — tap it to send instantly to the conversation you choose. Widgets refresh every 30 minutes or when your Quick Reply library changes.

Yes — 2,000 characters per reply, with a warning at 1,800. Media attachments are limited to 10 per reply, with a maximum of 25 MB per file.

Yes. The "Create quick reply" Shortcut intent lets you build and save Quick Replies programmatically — useful for importing templates or generating them in bulk. Quick Replies also support deep linking for triggering a specific reply from any automation.

Type / in the message input to see your saved Quick Replies as autocomplete suggestions. Tap one to insert its content. You can also tap the + attachment menu and select Quick Reply to start the same flow. **Note:** In Telegram bot private chats, typing / shows the bot’s own commands instead. Quick Reply is available in all other chats — WhatsApp, Telegram groups, non-bot Telegram private chats, and more.

Twenty-two, organised into four categories. Send (7 actions) delivers messages, media, polls, locations, contacts, and events. Create (5) builds groups, quick replies, scheduled messages, and Skills. Find (7) searches and filters your conversations, messages, contacts, quick replies, scheduled messages, and Skills with Reminders-style Add Filter, Sort by, and Limit controls. Open (3) navigates directly to any conversation, contact, or message.

Find actions use Apple's EntityPropertyQuery API — the same system that powers the Reminders and Calendar "Find" actions in Shortcuts. You get an Add Filter button with property-specific comparators (contains, equals, greater than, less than, between), a Sort by picker, and a Limit toggle. For example, Find Conversations lets you filter by platform, conversation type, unread status, pinned, archived, favourite, last message date, and participant count — then sort by date, title, or unread count.

Eleven filterable properties: title (contains, equals), platform (WhatsApp or Telegram), conversation type (private, group, channel, etc.), group chat (yes/no), has unread (yes/no), is pinned, is archived, is favourite, unread count (equals, greater than, less than), last message date (before, after), and participant count (equals, greater than, less than). You can combine multiple filters and sort by last message date, title, unread count, or participant count.

Yes — that is where AI Reply Assistant really shines. The output of a Find action can feed directly into a Send or Open action. For example: Find Conversations where "is pinned" is true, then Send Message to each result. Or: Find Text Messages where "is from me" is false and "timestamp is after" yesterday, then count them for a daily digest.

Yes. Every one of the 22 actions is available to Siri. You can say things like "Send a message with AI Reply Assistant", "Schedule a message in AI Reply Assistant", or run any saved Shortcut by name. Siri also surfaces AI Reply Assistant actions as suggestions based on your usage patterns.

Yes. Use the Automations tab in the Shortcuts app to trigger any AI Reply Assistant action based on time of day, location, Focus mode, NFC tag, or app events. For example: send a check-in message every weekday at 9 am, or fire a quick reply when you arrive at the office.

A few ideas: (1) Morning briefing — Find unread text messages from today and get a summary. (2) Weekly team poll — triggered every Monday, send a check-in poll to your team group. (3) Birthday greeting — tied to a Calendar event, send a message when the day starts. (4) Quick broadcast — find all pinned conversations and send the same announcement to each. (5) Auto-reply while driving — triggered by Driving Focus, send "I'll reply when I arrive" to your most recent chat. (6) Daily standup reminder — every weekday at 9:45 am, send a reminder to your team group.

WhatsApp offers no native Shortcuts actions on iOS. Telegram exposes only basic "Send Message" and "Open Chat" actions. AI Reply Assistant provides 22 actions — including 7 Find queries with full filter, sort, and limit controls — making it the most comprehensive Shortcuts integration for any messaging app on iOS.

Telegram scheduled messages are sent server-side. When you schedule a message, AI Reply Assistant sends it to Telegram's servers with the target date and time. Telegram delivers it at the exact scheduled time — even if your phone is off, the app is closed, or you have no internet at that moment. This is the most reliable scheduling method.

WhatsApp scheduled messages are handled on-device because WhatsApp does not offer a server-side scheduling API. AI Reply Assistant stores the message locally and uses iOS background tasks to send it when the scheduled time arrives. For the best reliability, keep AI Reply Assistant in the background (do not force-quit it from the app switcher). You will also receive a notification at the scheduled time with a "Send Now" button as a fallback.

Three things help: (1) Keep AI Reply Assistant in the background — do not swipe it away in the app switcher. (2) Make sure your phone has an internet connection around the scheduled time. (3) Leave notifications enabled so you get the on-time reminder with a "Send Now" action if the background task hasn't fired yet. Disabling Low Power Mode also helps iOS run background tasks on schedule.

The message stays in your pending queue. As soon as AI Reply Assistant runs its next background check or you open the app, it will detect the overdue message and send it immediately. You will also see a notification prompting you to send it manually.

You can schedule text messages, photos, videos, documents, voice messages, polls, events, and checklists. You can also schedule rich text with formatting and link previews. Broadcasts (sending to multiple recipients at once) and recurring messages are supported too.

Yes. AI Reply Assistant supports broadcast scheduling — pick multiple recipients and schedule one message to go out to all of them at the same time. Each recipient's delivery is tracked individually.

Yes. When creating a scheduled message you can set a recurrence pattern — daily, weekly (with specific days), or at a custom interval. AI Reply Assistant automatically creates the next occurrence after each one is sent.

Yes. You can use placeholders like {recipientName}, {recipientFirstName}, {currentDate}, {currentTime}, {recipientPhone}, and {businessName} in your message text. Variables auto-fill with real contact data when the message is sent — perfect for personalised broadcast messages. AI Reply Assistant validates all variables before scheduling and warns you if any cannot be resolved for a particular recipient.

"Server Scheduled" means the message lives on Telegram's servers and will be delivered at the exact time ��� no device involvement needed. "Pending" means the message is stored locally and depends on iOS background execution to send it (used for WhatsApp and as a fallback for Telegram). Server Scheduled is more reliable.

Yes. Lock any conversation behind Face ID, Touch ID, or Optic ID. Locked chats are hidden from the main conversation list and moved to a dedicated Locked Chats folder that requires biometric authentication to access. Notifications for locked chats hide message previews automatically.

Yes. AI Reply Assistant gives you granular control over platform-specific privacy — last seen, profile photo visibility, read receipts, typing indicators, online status, group add permissions, and more. You can manage exception lists (allowlists and blocklists) for each setting, all without leaving the app.

Open Appearance settings to access the theme gallery with preset colour schemes, or create a fully custom theme — pick bubble colours, gradients, shadows, corner radius, and opacity. You can also set a wallpaper from solid colours, gradients, your photo library, or AI-generated art. A live chat preview updates in real time as you make changes.

Yes. Choose between Light, Dark, or Automatic (follows your device setting). You can also enable Auto-Night Mode to schedule dark mode for specific hours or switch automatically at sunset based on your location.

Yes. Appearance settings let you choose from a range of font families with a live pangram preview, and set text size across five levels from Extra Small to Extra Large. You can also toggle "Use System Text Size" to follow your device accessibility setting, and enable High Contrast for better readability.

In Chat settings you can independently enable or disable Smart Replies (quick AI suggestions), AI Reply (full message drafts), and Analyze (thread summarisation). Apple Intelligence is the built-in default through on-device processing. With Claude, you get even more expertise — pick between Haiku 4.5 and Sonnet 4.6 to handle more complex requests.

You get a master toggle plus granular controls for message previews, sounds, badge count, and alert style. In-app notifications have separate settings for sounds, haptics, and preview banners. Quiet Hours lets you silence everything on a schedule while still allowing critical alerts.

Quiet Hours silences all AI Reply Assistant notifications during a time window you set — for example, 10 pm to 7 am. You can allow critical alerts to break through, and optionally enable an automatic mode that adjusts based on your device location.

Data Management settings show a visual breakdown of your storage usage. You can set media retention periods (1 week to forever), configure auto-download rules per media type (photos, audio, video, documents) and per network (Wi-Fi only or always), set a cache size limit, and enable Auto-Clean to clear the cache automatically when storage runs low.

Yes. Data Management offers two export options: Export All Data saves your full SwiftData store as a JSON file, and Export Messages CSV exports your message history as a spreadsheet. Both can be shared via the system share sheet for backup or review.

You can customise emoji behaviour — skin tone, large emoji mode, auto-convert emoticons, animated stickers — toggle auto-play for GIFs and inline videos, choose a default messaging platform, and control Apple Intelligence content actions like inline translation prompts on foreign-language messages, summary indicators, transcription buttons (for voice messages, videos, video notes, and audio files), and Visual Intelligence.

Yes. Alongside solid colours, gradients, and photos from your library, AI Reply Assistant lets you create fun, original wallpapers with Image Playground — entirely on-device. Pick a style and concept, and the image is created on device without any data leaving your phone.

Yes. In Appearance settings, tap Accent Color to open a colour picker and choose any colour for buttons, links, and highlights throughout the app. It applies instantly across the entire interface.

Yes. Enable Contact Sync in Privacy settings to import contacts from your device address book. This makes it easier to find recipients when sending messages. AI Reply Assistant requests the standard iOS Contacts permission and shows the current authorisation status so you always know what access has been granted.

Yes. Enable Low Data Mode in Data Management to automatically compress media before uploading on cellular. You can also set Upload Quality (High, Standard, or Compressed) and configure per-media-type auto-download rules — choosing between Never, Wi-Fi Only, or Always for photos, audio, videos, and documents separately.

Yes. Each settings section — Privacy, Chat, Appearance, Notifications, and Data Management — has its own Reset button at the bottom. Resetting one section restores its defaults without affecting the others, so you can experiment freely.

Yes. In Account settings you can change your display name and upload a new profile picture from your photo library. Your profile is stored locally on your device.

Use the search bar at the top of the Settings screen. Every option across all sections is indexed, so you can type a keyword — like "emoji", "badge", or "wallpaper" — and jump straight to the right setting without scrolling through menus.

Yes. AI Reply Assistant can classify every incoming message with a sentiment (positive, negative, neutral, mixed, or question) and an intent (informational, request, social, urgent, or transactional). It also scores urgency and formality on a scale, assigns a priority level (1–3), and extracts topics automatically. Tap any message to see a compact badge, or expand it for the full breakdown.

Yes. When someone mentions a date, time, or event in a message — "dinner tomorrow at 7" or "team standup Monday 10 am" — AI Reply Assistant extracts the event details (title, location, date range, notes) and shows an inline card. Tap "Add to Calendar" to save it in one step. Past events are highlighted so you can tell at a glance which ones have already happened.

Yes. AI Reply Assistant scans messages for action items and shows them as inline cards with status tracking (pending, in progress, completed, delegated), owner assignment, deadline indicators, and blocker flags. Overdue items are highlighted. Tap "Add to Reminders" to send any action item straight to Apple Reminders with the deadline pre-filled.

Day Summary is an AI-generated digest of the day’s conversation. It condenses the thread into key points and surfaces any events, reminders, and action items mentioned throughout the day — all in a collapsible card you can drag to resize. Extracted events and reminders appear as tappable inline cards so you can add them to your calendar or reminders without scrolling back through the chat.

Yes. When someone shares a phone number, email, company name, or job title in a message, AI Reply Assistant extracts the contact details and shows an inline card. Tap "Add to Contacts" to save the person to your address book with all the extracted fields pre-filled.

Yes. AI Reply Assistant detects foreign-language messages automatically and shows a compact translate icon on the message bubble. Tap it to open the iOS translation sheet, then tap "Replace with Translation" to swap the original text with the translated version directly inside the bubble. The original text is shown below in a smaller font, and a "Translated · Show Original" indicator lets you switch back at any time. Translation works on text messages, link messages, media captions (photos, videos, GIFs, documents), voice message transcripts, audio file transcripts, video transcripts, video note transcripts, and interactive messages (button, list, template, and interactive) — any bubble with text content. Translations are persisted to your device, so they remain visible when you navigate away and return to the chat.

Translation is powered by Apple’s on-device Translation framework. All processing happens locally on your device — no text is sent to external servers. Over 20 languages are supported, including Arabic, Bengali, Chinese (Simplified and Traditional), Czech, Danish, Dutch, English (UK and US), Finnish, French, German, Greek, Hebrew, Hindi, Hungarian, Indonesian, Italian, Japanese, Korean, Malay, Norwegian (Bokmål), Persian, Polish, Portuguese (Brazil), Romanian, Russian, Slovak, Spanish, Swedish, Tagalog (Filipino), Thai, Turkish, Ukrainian, and Vietnamese. Availability depends on your iOS version — newer releases add more languages. You can download additional language packs in Settings → Apps → Translate → Downloaded Languages for offline use.

Yes. AI Reply Assistant transcribes four media types on-device: voice messages, videos, video notes (Telegram’s circular videos), and audio files. All processing happens locally — nothing is sent to external servers. Tap the transcription button on any voice, audio, or video bubble to start. The transcript streams in as it’s recognised and is cached to your device so it loads instantly the next time you open the chat. You can set a per-chat transcript language from the long-press context menu, and if the transcript is in a foreign language, a translate button appears inline so you can view the translation without leaving the bubble. Translations are also persisted.

Yes. Long-press any message to see a quick reaction bar with six default emoji (👍 ❤️ 😂 😮 😢 🙏), or tap the + button to pick any emoji. Reactions sync with the platform — recipients see them in their native WhatsApp or Telegram app.

Pin important messages to keep them at the top of a chat. A glass-effect banner appears at the top of the conversation showing the pinned message — tap it to scroll to the original. If multiple messages are pinned, you can navigate between them with arrows. Pins support expiry durations (24 hours, 7 days, or 30 days) and can be unpinned with a quick action.

Star any message to save it for later. The Starred Messages view gives you a searchable, scrollable list of everything you have starred — with sender avatars, timestamps, and "Starred by you" labels. You can swipe to unstar, or enter bulk edit mode to multi-select and unstar in batch.

Yes. Quick filter chips at the top of the chat list let you show All, Unread, Groups, or Favourites in one tap. You can also create custom folders (Telegram-style) for more granular organisation. Pin your most important chats, archive ones you want out of the way, and lock sensitive conversations behind Face ID.

Yes — animated emoji are a first-class feature throughout the app. Send a single emoji and it plays as a full Telegram-style Lottie animation with a fullscreen overlay effect and haptic feedback — tap it to replay. Long-press any message and the reaction bar shows animated emoji that play as the bar appears. Reaction bubbles below messages, the reaction detail overlay, sticker pack thumbnails, emoji category tabs in the sticker picker, and forum topic icons all render animated Lottie emoji when available, falling back gracefully to static text. AI Reply Assistant supports TGS (Lottie), animated WebP, and WEBM sticker formats along with static PNG and JPEG stickers. Your Telegram sticker packs and premium custom emoji sync automatically and are available in the unified sticker picker — send them in both Telegram and WhatsApp chats. Telegram mask sticker packs also sync automatically and are available in the photo editor — Vision-powered face detection auto-positions masks on detected faces, with support for multiple faces and manual drag, scale, and rotate adjustments. For WhatsApp, there is no automatic sticker sync, but you can import sticker packs shared in WhatsApp chats and then use them across both platforms. Animations are rendered off the main thread for smooth scrolling and can be toggled on or off in Chat settings.

Mask stickers are a special Telegram sticker type designed to be placed on faces in photos — think sunglasses, hats, moustaches, and other face accessories. Your installed Telegram mask packs sync automatically to AI Reply Assistant and appear in the photo editor when you tap the Sticker tool. Select a mask sticker and AI Reply Assistant uses the Vision framework to detect faces in your photo. If one face is found, the mask auto-positions using the sticker’s anchor point (forehead, eyes, mouth, or chin). If multiple faces are found, you’ll see a numbered overlay — tap the face you want. After placement, drag, pinch, and rotate to fine-tune. Mask stickers are separate from regular stickers and don’t appear in the chat sticker picker.

Yes. Videos can play in a draggable picture-in-picture window that persists as you navigate between chats. It snaps to screen corners, supports tap-to-expand, and auto-hides controls after 3 seconds. Circular video notes (Telegram-style) are supported too.

AI Reply Assistant generates rich link previews with adaptive layouts. Social media and photo links get a large top thumbnail. Articles get a compact side thumbnail. YouTube and Vimeo links show a video card with a play overlay. Thumbnails are cached and space is reserved during loading so the chat does not jump.

Yes. Long-press a message, tap Forward, and pick multiple recipients from your contacts or chats. You can add an optional message before forwarding. AI Reply Assistant tracks each recipient’s delivery individually. For Telegram, you can also toggle Hide Sender (sends as a copy without the “Forwarded from” attribution) and Remove Caption (strips media captions) before forwarding.

Yes. Edited messages show an "edited" label. Tap it to see the edit count and when the last edit was made.

Open any conversation’s info panel to browse all media shared in that chat — photos, videos, documents, voice messages, and more — organised by category with lazy-loaded thumbnails. It is a fast way to find that photo or PDF someone sent weeks ago.

Yes. Open a contact’s info panel and scroll to "Groups in Common" to see every group you both belong to, with member counts and avatars. Tap any group to jump straight to it.

Birthday sync matches contacts across Telegram, WhatsApp, and your device contacts by phone number (last 8 digits). If one platform has a birthday for a contact and another does not, tapping Sync Birthday in the contacts list populates it automatically. The sync also pulls the latest birthdays from your iOS Contacts app first, so any birthday you add in the Contacts app is picked up. Edits you make to a device contact’s birthday or name in AI Reply Assistant are written back to the iOS Contacts app, keeping both in sync. You can also pull to refresh the contacts list to re-sync device contacts at any time.

When it’s a contact’s birthday, a celebration banner appears at the top of your chat. Tap it and AI Reply Assistant drafts a birthday greeting placed in your input field — you can review and edit before sending. You can also filter your contacts list by upcoming birthdays to see who is celebrating soon.

Yes. When a contact shares their live location, you can set a distance threshold. AI Reply Assistant monitors in the background and sends you a local notification when that person comes within range — useful for knowing when a friend is nearby or a delivery is approaching.

Yes. When a contact’s security code changes (for example, after reinstalling the app on a new device), AI Reply Assistant shows a highlighted inline notification in the chat — similar to WhatsApp’s native security alert. Tap it for details about the identity change.

Yes. When you delete a message, a 5-second undo toast appears at the bottom of the screen. Tap "Undo" to restore the message instantly before the deletion syncs to the server. If you navigate away or the timer expires, the delete is committed permanently.

Long-press the send button to see send options. Tap "Send Silently" to deliver the message without triggering a notification on the recipient’s device. This is ideal for late-night messages or non-urgent updates. The option appears only in Telegram chats (WhatsApp does not support silent delivery).

Yes. If you are a group admin on Telegram, long-press any member’s message and tap "Moderate User" in the context menu. From there you can delete the message, delete all messages from that user, restrict them (mute for 1 hour, 1 day, 1 week, or permanently), or ban them from the group. On WhatsApp groups you can remove the member.

When you open a private or secret chat with someone who isn’t in your contacts, a contextual action bar appears at the top of the chat. Depending on the situation, it offers quick actions like Report Spam, Block, Add Contact, Share Phone Number, or Unarchive. For new contacts, it also shows account information such as when the user registered and their phone number’s country. The bar updates in real-time and disappears automatically after you take an action.

The context menu includes entity-specific actions when the message contains tappable content. For URLs you get Copy Link and Open in Safari. For phone numbers you get Call and Copy Number. For email addresses you get Copy Email. These appear alongside the standard message actions like Reply, Forward, and Copy.

No. If your recording is longer than 1 second, AI Reply Assistant shows a confirmation dialog asking whether to discard or keep the recording. This applies to voice messages, video notes, and the advanced voice recorder with trimming. Recordings under 1 second are discarded immediately since they are likely accidental.

Yes. Disappearing messages are fully supported on WhatsApp. On Telegram, disappearing messages work in regular chats, but secret-chat support is limited.

In Telegram supergroups with slow mode enabled, a countdown badge appears on the send button showing when you can send your next message. This matches the native Telegram behaviour for rate-limited groups.

No. AI Reply Assistant is a messaging app — voice and video calls are not supported on either WhatsApp or Telegram. Use the official WhatsApp or Telegram app for calls.

AI Reply Assistant provides comprehensive Telegram bot support: bot commands menu with autocomplete, inline keyboards (URL links, callback buttons, login auth, switch-to-inline, copy text, payment, and more), reply keyboards with one-time, persistent, resize, and placeholder text options, full callback query round-trips, Mini Apps (Web Apps) with the complete Telegram Web App JavaScript bridge, bot menu buttons, inline mode (@bot queries) with real-time results, HTML5 games with score tracking, dice and emoji rolls, invoice and payments with Telegram Stars, peer selection buttons, deep linking (bot start parameters), bot description panels, paid media behind a Stars paywall, and attachment menu bots.