Updated: 2026-07-24
To make a bot answer from your documents you need a knowledge base: you upload a price list, FAQ or policy, the service splits the text into fragments and indexes them, and for every question the bot receives the relevant pieces and answers from them. In Corpis this takes no code: the agent is created with a form, documents are added on the "Knowledge" tab, and the same agent connects to Telegram.
Create an agent. Open agent creation and fill in the name, personality and greeting — or describe what you need in words and the AI assistant will fill the form.
Open the "Knowledge" tab. In the agent settings go to "Knowledge" — this is where all its documents live.
Add documents. Paste text, upload a file (txt, md, pdf, docx, html, csv) or provide a URL. Indexing runs right away; the status is visible in the list.
Check the answers. Ask the agent a question about the document in the preview. Also ask something the documents do not cover — make sure it honestly says the answer is missing.
Connect Telegram. On the "Telegram" tab paste a bot token from @BotFather — the bot starts answering from the same documents in DMs and groups.
Short rules ("we are open 9 to 6", "be formal") can live right in the agent settings — they reach every reply. But a 40-item price list or a 20-page policy will not fit into a prompt: the model starts losing and mixing up details.
A knowledge base works differently: the document is indexed once, and only the fragments relevant to the current question are mixed into the reply. Search works by meaning, not by exact word match — "how much is delivery" will find the "shipping rates" section. Exact terms, codes and SKUs are still taken into account.
Along with the fragments the agent receives an instruction: rely on them, and if the context has no answer — say so honestly instead of inventing one. For a support bot this is the key property: "let me check with a manager" beats a made-up price.
The base turns on automatically as soon as the first document is uploaded, and works in both channels: in the on-platform chat and in the connected Telegram bot. No per-channel setup — it is the same agent.
No. The agent is created with a form, documents are uploaded with a button on the "Knowledge" tab, and Telegram connects by pasting a token. No step requires code.
Pasted text, files in txt, md, pdf, docx, html, csv, and fetching by URL. Only text is indexed — images and layout are ignored.
No, and that is the key difference from a bare LLM: together with the document fragments the agent receives an instruction to answer from them and to say honestly when the base has no answer.
Yes. The base belongs to the agent, not to a channel: the connected Telegram bot answers from the same documents as the on-platform chat.