Reading a long PDF to find one clause is slow, and most chat tools just summarize the first page. Drop a document into this Telegram bot and it indexes the whole file, then answers your questions inside the chat.
Reading a long PDF to find one clause is slow, and most chat tools just summarize the first page. Drop a document into this Telegram bot and it indexes the whole file, then answers your questions inside the chat.
Every answer comes with a page citation, so you can verify it instead of trusting a guess. The document stays loaded per user, so follow-up questions about the same file keep their context.
How it runs
Used at step 01 to kick off the pipeline.
Write
Used at step 01 to kick off the pipeline.
WebFetch
Used at step 01 to kick off the pipeline.
WebSearch
Used at step 01 to kick off the pipeline.
Split the document into chunks, embed them, and index the vectors for retrieval.
pending
On each question, fetch the most relevant chunks and answer with page citations.
pending
Keep the indexed document per user so follow-up questions stay grounded in that file.
pending
Sample output
json
// Sample output
// (generated when the pipeline finishes)
Answer the question using only the retrieved PDF chunks; cite the page number and say so if the answer is absent.
Unlock the rest
The full agent definition, install snippet, and starter task are gated for community members.
Members get the full `.md` agent file, the npm / pnpm install one-liners, a starter prompt that we've tuned against real runs, and the open-source repo when this automation ships there. One email, magic link, done.