FAQ
FAQ
Frequently asked questions about WAM Agents
A quick tour of how the agent works, what it does out of the box, what it costs and what happens to your data. Can't find an answer — message @wamagentsbot.
Sections
01Basics→02Capabilities→03Models→04Pricing→05Data & privacy→06Support→ Basics
What is WAM Agents?
WAM Agents is a personal AI agent in Telegram under your name and avatar. You tune it through an ordinary chat and add it to groups: your team, friends and clients talk to it like any other participant. It works in DMs, groups and forum topics — no separate app.
Which model does the agent run on?
By default the agent runs on DeepSeek — included in the subscription, no OAuth or third-party keys required. If you want, attach your own model (Claude, Codex) with /claude — an optional upgrade on top of DeepSeek.
Capabilities
What can the agent do out of the box?
Out of the box on DeepSeek the agent handles text and code, runs bash, calls MCP tools, holds multi-turn dialogues, understands images and searches the web. All of it is included in the subscription, with no extra keys.
Does the agent understand voice, photos and documents?
Yes, natively. Voice is transcribed automatically (Deepgram Nova-3), the agent sees photos and screenshots, and PDFs are read end-to-end. Files come in and go out right inside Telegram — no manual unzip.
Can I add the agent to a group?
Yes. The agent works in DMs, groups and forum topics. In groups the /mention on|off command controls behaviour: reply only to @mentions and replies — or to every message from the owner.
What are forum topics?
An optional upgrade — a dedicated group workspace where each topic becomes an independent session with its own memory. Handy for running several projects in parallel without mixing contexts. The agent walks you through setup step by step; the step can be skipped and picked up later.
Does the agent remember past conversations?
Yes. The agent remembers your preferences, contacts and projects across chats. Memory lives inside your container and can be edited by conversation — just ask it to add, update or forget a fact. Nothing is shared with other people.
Models
What's the difference between DeepSeek and your own model?
DeepSeek is the default model, paid for inside the subscription; it handles text, code, bash, MCP tools, vision and web search well. Your own model (Claude, Codex) is an optional upgrade for the deepest reasoning and long-PDF reading (over 50 pages).
How do I attach my own model?
Send /claude in the chat with your agent. The bot replies with an OAuth link — sign in with the provider and send the code back to the chat. After that switch models with /model (legacy aliases /opus, /sonnet, /haiku still work). Refresh the token later with /login.
Is attaching my own model required?
No. On DeepSeek by default the agent already does all the essentials, including vision and web search. Your own model is optional — for when you need long PDFs or deeper reasoning.
Pricing
How much does it cost and what's included?
$9.99 per month. The subscription includes the infrastructure and a DeepSeek quota for everyday agent work, plus web search, vision, voice transcription, document handling, MCP tools, long-term memory and auto-updates. Nothing else to pay to get started.
How do I start and do I need a card?
Open @wamagentsbot in Telegram and hit Start — the bot walks you through onboarding. There are 30 days free with no card: when the trial ends you decide whether to pay the subscription or close it.
What if my DeepSeek quota runs out?
The agent tells you and offers options: wait for the quota to refresh at the start of the next subscription period, or attach your own model with /claude and continue on it. The quota refreshes every period.
How do I cancel the subscription?
Message @wamagentsbot — we turn it off at the end of the paid period. The agent container runs to the end of the period and then stops.
Who is the provider and how does payment work?
The provider is IE Artem Polyanskiy (Georgia, Small Business, tax ID 305603825). Payments are processed by Creem. Terms and the privacy policy are inside @wamagentsbot.
Data & privacy
Where does my data go?
By default requests go through DeepSeek infrastructure (PRC) — consent is confirmed during onboarding. If you attach your own model, chats go via your OAuth, and per the provider's BYOK policy content is not used to train models. Auxiliary services (Deepgram, Hetzner) are listed on the subprocessors page. We keep only billing metadata and the agent container.
How do I delete the agent and my data?
Send /delete in @wamagentsbot — it deletes the agent and withdraws your data-processing consent.
Support
Where do I report questions and bugs?
Questions and bugs go to @wamagentsbot. SLA and response time are described in the terms.