> For the complete documentation index, see [llms.txt](https://thecontentforge.gitbook.io/thecontentforge-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://thecontentforge.gitbook.io/thecontentforge-docs/feature-glossary/glossary/telegram.md). # Telegram *Last updated: 2026-08-07.* TheContentForge runs two Telegram bots: a content bot that lives in your team group chats and turns conversation into on-brand posts, and an Investor Intel bot for market briefs, alerts, and token charts. Both are locked to chats an admin has explicitly connected. ## Content bot in your team chat A bot that lives in the group chats an admin has connected, turns what the team is already discussing into on-brand posts, and hands them back for a decision in the same chat. * **Content bot for group chats** - The bot works only in the group chats your admin has added to the workspace, and it ignores direct messages entirely. If someone runs a command in an unknown chat, it replies with that chat's ID and how to add it, so an admin can connect it without hunting for the number. * **/generate** - Creates a post from a topic, an article link, or a link to an X post. The reply carries whichever platform versions came back, with suggested hooks and a warning when the post looks close to something you published in the last day or two. The result is saved to your workspace history so anyone can finish it on the web. * **/rewrite** - Reply to any message with it, or paste a draft after it, and the bot returns an on-brand rewrite. You can set the platform, goal, and tone inline. * **/news** - Turns a breaking story into a post from a link, pasted article text, or even an image you replied to, with an urgency setting for fast-moving news. * **/whatsworking** - Reports what is actually performing for your accounts: recent engagement and impression benchmarks, the hook styles that are landing, and any notable shift in results. Add a platform name to narrow it to X, Instagram, or Facebook. * **/brand** - Shows the active brand voice at a glance: tone rules, what to do more of, what to avoid, and your signature moves. * **/experiment** - Returns a standard two-variant test outline for a topic, covering the variants to try, the metric, and the window. It is a fixed template to structure a test, not an analysis of your specific draft. * **/help** - Lists every command with examples and the optional platform, tone, and length settings, and points at the button menu. * **/cancel and busy protection** - The bot runs one long generation per chat at a time, tells you when it is still working, and stops what it is working on when you ask, so a chat is never stuck waiting. * **Button menu** - Opens a tap-through menu covering post creation, trending reactions, the daily brief, what is working, pending drafts, tracked tokens, and help, with the options tailored to the kind of workspace you run. Where the button interface is not switched on, the bot falls back to the written command list. * **Post creation flows** - The post creation menu offers the formats that suit your workspace: a general post helper for most teams, a project post for Web3 project workspaces, and meme post, chart reaction, and weekly recap for meme workspaces. Pick one, send your topic as a normal message, and the bot takes it from there. * **Trending reactions** - Meme workspaces get a reaction menu that builds a post from an X link you paste, the latest news, a token contract address, or an automatic pick from what is currently trending for your workspace. * **Daily brief** - Assembles one message covering fresh token intelligence, recent wallet alerts, what is currently trending, what is working this week, and suggested angles. Buttons turn that brief straight into an X post, a thread, a Telegram update, or a newsletter section. * **What's working button** - Shows this week's dashboard read-out in the chat: what is working, what is not, priority actions, a hidden gem, and platform opportunities. It reads the analysis the web dashboard already produced, so it asks you to refresh in the product when that analysis has gone stale. * **Draft or publish from the chat** - After generating in the button flow you can save the result as a draft or publish it, with a confirmation step first. Only the person who created the post can publish it, and only if that chat is allowed to publish. * **Rework in place** - A generated post can be regenerated up to five times, pushed toward more hype, more information, or a shorter version, expanded into a thread, or opened in Content Forge for deeper editing. Only the person who created it can rework it. * **Headline images** - Before you generate, one button decides whether the bot also makes a headline image. Once the image exists, a second button decides whether it goes out with the post when you draft or publish, and it is attached unless you switch it off. * **Link and address reactions** - When someone drops an X link, an article, a chart link, or a token contract address into a connected chat, the bot offers to turn it into a post, a thread, or a summary on the spot. It stays quiet if the same link was already offered in that chat a short while before. * **Tracked tokens** - Lists the tokens the workspace follows, adds a new one by pasting its contract address, turns alerts on or off per token, and removes tokens you no longer watch after a confirmation step. * **Pending drafts** - Shows the queue of drafts waiting on a decision, five at a time, and lets you approve or reject each one from the chat. The edit button hands back a link that opens that draft in Content Forge. * **Stalled work recovery** - If a generation stalls, the waiting message is replaced with either the finished result or a plain explanation of what went wrong, so the chat is never left hanging on a message that never arrives. ## Investor Intel bot A second bot for market work, running either in a private chat or in a connected group, with anything personal reserved for private chats. * **Investor Intel bot** - A separate bot for market work that runs in a private direct message or a connected group. Groups see intel shared across the workspace, and direct messages can additionally cover personal things like your holdings. A single switch in Investor Intel settings controls whether Telegram is used for notifications at all once a private link or a group exists. * **Linking your account** - Generate a code in Investor Intel settings and send it to the bot in a direct message. You can unlink from the chat or revoke the link in settings at any time, and you decide whether that private chat is allowed to receive personal alerts and briefs. * **Button menu** - The bot answers with a small keyboard for the brief, recent alerts, token charts, and help, with a portfolio button added in a linked direct message. * **/brief** - Returns the latest ready market brief for your workspace, with the private detail included only in a linked direct message. * **/alerts** - Shows the five most recent alerts with what fired and why. * **/chart and /token** - Renders a live price chart for a ticker, a contract address, or a chain and address pair, with buttons to switch between one hour, four hour, daily, and weekly views and a link into Investor Intel on the web. Use the overview command when you want the numbers without the chart. * **Type a ticker to get a chart** - In a connected chat you can send a ticker or paste a contract address on its own and get the chart back, with no command needed. * **/ask** - Answers a question by quoting back the recent signals, alerts, and briefs your workspace already holds that bear on it. It reports what your workspace already knows rather than researching live. * **Ask without the command** - In a linked direct message, any message longer than a few words that is not a command or a ticker is treated as a question and answered the same way. * **/portfolio** - Returns a private summary of your default portfolio with total value, day change, unrealised gain or loss, risk score, and your six largest holdings. Direct messages only, never in a group. * **/id** - Shows the current chat's ID. To connect a group you add the bot to it, ask it for that ID, then paste the ID and a name into settings. ## Alerts What the bots send into a chat without being asked, and the limits that stop a busy token or wallet from flooding it. * **Token alerts** - When a tracked token gets new intelligence or notable on-chain activity, the bot posts a short update to the chat you chose for that token. Updates are grouped so a busy token cannot flood the chat, and a chat that has since turned token alerts off is left alone. * **Wallet alerts** - When a watched wallet triggers one of your rules, the alert goes to the chat set on that rule or to your workspace default alert chat. Several events from the same rule close together are combined into one message, a chat with wallet alerts switched off is skipped, and an alert with no destination chat is never sent somewhere else. * **Daily watchlist digest** - An optional once-daily message summarising the biggest token moves, the most active wallets, and any newly labelled addresses from the last 24 hours, so a quiet day still gets one read rather than nothing. ## History, security, and settings The admin side: what the bots have done, who is allowed to use them, and what each chat is permitted to do. * **Bot History** - A full record of the commands the workspace has run through the bot, with the input, the status, how long it took, and any images produced. The view keeps itself current while something is still working, and admins can cancel a single stuck command or everything still running at once. * **History cleanup and unstick** - Admins can clear failed entries, completed entries, or everything that has finished from the bot history. A separate action gets the bot answering again when it has gone quiet. * **Security Log** - A record of bot access events: blocked direct messages, messages from chats that are not connected, blocked users, commands that ran, and errors. It is filterable by event type, and no message content is stored. * **Bot health check** - Confirms in one click that the bot is connected and working for your workspace, showing the bot's name, whether it has work waiting, and the most recent problem if there was one. * **Allowed chats** - The list of group chats permitted to use the content bot. Anywhere else it stays silent. Each connected chat counts against your plan's bot channel allowance, and the page shows how much of that allowance you have used. * **Allowed users** - An optional extra layer. When turned on, only the Telegram accounts you list can use the bot, even inside an allowed group. * **Per-chat controls for the Investor Intel bot** - Each connected group can have individual capabilities turned on or off, such as briefs, alerts, charts, token lookups, and questions, plus a minimum alert severity so a busy group is not buried in low-importance alerts, and a default chart timeframe. Groups can be paused and re-enabled without being removed, or removed outright. * **Per-chat limits for the content bot** - Every allowed chat carries its own permission set covering generating, drafting, publishing, the drafts queue, token alerts, wallet alerts, the daily brief, and the weekly recap, and the bot turns away anything a chat is not allowed to do. All of them are on unless they are explicitly switched off. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://thecontentforge.gitbook.io/thecontentforge-docs/feature-glossary/glossary/telegram.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.