HappHapp Docs
Resources

FAQ

Common questions about AI assistants, channels, billing, voice calls, and integrations on Happ

General

What is Happ?

Happ is an AI assistant platform that automates customer communication across messaging channels (Telegram, Instagram, WhatsApp, Facebook, Viber) and voice calls. Your AI assistant responds to customers automatically using the knowledge and instructions you provide.

Do I need technical skills to use Happ?

No. Happ is designed for non-technical users. You can set up an AI assistant, connect channels, and manage conversations entirely through the web dashboard at my.happ.tools — no coding required. The API is available for developers who want to build custom integrations.

Which AI models can I use?

Happ supports multiple providers and models:

  • OpenAI — GPT-5.x family (gpt-5.1, gpt-5-mini, gpt-5.4, gpt-5.5), GPT-4.1, GPT-4o, GPT-4o Mini
  • Claude (Anthropic) — Sonnet 4.5
  • Gemini (Google) — 3.x Flash, Flash Lite, Pro
  • Groq — GPT-OSS 120B / 20B (ultra-fast inference)

See Assistants > AI Model Configuration for the full list.

Can I use multiple AI assistants?

Yes. You can create multiple assistants, each with its own prompt, knowledge base, tools, and AI model. Assign different assistants to different channels or use cases.

Channels

Which messengers are supported?

Telegram, Instagram, WhatsApp, Facebook Messenger, and Viber. See the Channels Overview for details on each.

Can one assistant work on multiple channels?

Yes. A single assistant can handle conversations on all connected channels simultaneously. Each channel creates separate conversations per customer.

What happens if I disconnect a channel?

Active conversations stop receiving AI responses. Historical conversation data is preserved. You can reconnect the channel at any time.

Do customers know they're talking to an AI?

That's up to you. Configure the assistant's prompt to identify itself as AI or present itself as a regular support agent.

AI & Conversations

How do I improve my assistant's responses?

  1. Refine the prompt — Add specific instructions, tone guidelines, and examples
  2. Add knowledge — Upload documents, FAQs, and website content to the Knowledge Base
  3. Use a better model — gpt-5.5 and claude-sonnet-4-5 produce higher quality responses
  4. Review conversations — Check the Chat Dashboard to identify patterns where the assistant struggles

Can the assistant perform actions (not just chat)?

Yes. Configure tools to let the assistant call external APIs — make bookings, update CRM records, check availability, look up data, and more.

What happens when the assistant can't answer?

The assistant responds based on its prompt instructions (e.g., "I don't have that information, let me connect you with a team member"). You can configure the turnOffAiMode built-in tool to automatically disable AI and alert your team via Telegram Push Notifications.

Can a manager take over a conversation?

Yes. Toggle AI off for any conversation — manually from the dashboard/mobile app, via the /bot command in Telegram, or automatically via the turnOffAiMode tool. When AI is off, you can respond manually. Set up Telegram Push Notifications to alert your team when handoff occurs. See AI Control & Human Handoff for full details.

How fast does the AI respond?

In chats the assistant waits about 12 seconds after the customer's last message (30 seconds at most) and answers the whole batch at once — so a customer who types in several short messages gets one coherent reply instead of three half-answers. In the playground the wait is 3 seconds.

What is the context window?

The assistant sees a rolling window of the conversation: the tail that fits the model's context budget, with everything before the last summary replaced by that summary. Older messages stay in the database and can be pulled back with the built-in searchPreviousConversations tool. See AI Control.

Does AI automatically turn back on after handoff?

Yes, but only after an automatic handoff: once the chat goes quiet the AI comes back by itself after the delay set on the assistant (30 minutes by default). A manual switch-off never resumes on its own — a human turns it back on.

Voice

How does the voice assistant work?

The voice assistant answers phone calls using AI. It converts speech to text (STT), generates a response using your configured AI model, and converts it back to speech (TTS) — all in real-time. It can also execute tools during calls. See Voice Assistant.

Which telephony providers are supported?

Binotel, Ringostat, Phonet, and Unitalk. Any SIP-compatible provider can potentially be used. See Telephony Providers.

Can I choose the voice?

Yes. Choose from 30 built-in voices or connect ElevenLabs for premium natural-sounding voices with multiple languages and accents.

Billing

What plans are available?

Happ has one plan line for the whole platform — chat and voice on the same subscription: Start ($49/mo), Business ($199/mo), Scale ($499/mo) and Enterprise (from $1,000/mo). The plan sets the included dialogue volume, the number of concurrent calls, and the per-unit rates for usage.

See Billing & Plans for full details.

How is usage charged?

On top of the subscription, each unit is deducted from the company balance: per message, per voice minute, per conversation analysis and per transcription minute — at the rates of your plan, plus the model's own cost. Longer conversations, more capable models, knowledge-base searches and tool calls all raise it. Watch it in Billing.

What happens when the balance runs out?

Assistants stop replying and the chat is marked with aiDisableReason: insufficient_balance. They resume by themselves once the balance is positive again.

Can I change my plan?

Yes. Moving down to a cheaper plan applies immediately and costs nothing. Moving up is a prorated charge for the rest of the period and applies once it is paid. Cancelling keeps access until the paid period ends.

Data & Security

Is my data secure?

Yes. Happ uses industry-standard security practices:

  • JWT-based authentication with access tokens
  • HTTPS encryption for all data in transit
  • Data isolation between companies
  • HMAC-SHA256 webhook request signing

Can I delete my data?

Yes. You can delete individual conversations, knowledge entries, or your entire company workspace. Data deletion is permanent.

Where is data stored?

Conversation data is stored in PostgreSQL databases. Files are stored in secure cloud storage. Vector embeddings for the knowledge base are stored in Qdrant.

Support

How do I get help?

  • Check this documentation for guides and answers
  • Visit the API Reference for endpoint details
  • Contact support through the platform dashboard at my.happ.tools

Help me solve it

Happ answers right away and hands over to a manager when needed.

On this page