Sometimes the fastest way to ask about something is to take a picture of it. Send a photo to this Telegram bot and it runs a vision model, then replies with a structured breakdown of what it sees.
sonnet3 daysTelegram Bot APIClaude VisionSupabase
Claude
65ROI
75Scale
$4.3k94Saved
ROI for
README.md
Why this subagent
Sometimes the fastest way to ask about something is to take a picture of it. Send a photo to this Telegram bot and it runs a vision model, then replies with a structured breakdown of what it sees.
You get back detected objects, any readable text, and a caption rather than a vague guess. The image and its analysis are saved, so you can search past photos instead of scrolling the chat to find that one screenshot.
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.
Pass the image to a vision model with a prompt for the kind of analysis you need.
pending
Return structured fields such as detected objects, text, and a short description.
pending
Store the image reference and its analysis so results can be looked up later.
pending
Sample output
json
// Sample output
// (generated when the pipeline finishes)
Analyze the attached image and return JSON with objects, any readable text, and a one-line caption.
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.