[EW] Agent: extract content from screenshot

Open
#1,246 0 comments 0 reactions 0 assignees View on GitHub

Maintainers usually reply within 1 day

Nobody has claimed this yet.

Assessment

Difficulty
5/5
Estimated time
Over a week
Newbie friendliness
30/100
Issue type
Feature
Clarity
Needs clarification
Activity status
Quiet
Tech stack
javascript
Domain
ai, content

Research direction

Start with the linked chat trace and investigate whether other authors have tried uploading screenshots for content extraction. Define the feature scope, including block selection and capability messaging, before identifying the implementation entry points. Done means the scope is agreed and the screenshot-to-block workflow is implemented; no files or tests are named in the issue.

Written by the indexing model from the issue text.

Description

customer-feedback ew

Chat session analysis: https://mystique-langfuse-prod.corp.ethos117-prod-va6.ethos.adobe.net/project/cmn60m68c00088702ko6novs5/traces/de13e5ee60136b23c201f929fe0d259b?timestamp=2026-08-03T12:35:47.715Z

Author tried 3x to upload a screenshot to get content extracted and inserted into a block - they give the name of the block.

  • Investigate if more authors tried to use screenshots - maybe it is just a one of (intuitively, this feels very useful)
  • Define the scope of a potential feature (extract content, understand which blocks to use ?, inform user of capabilities if limited...)
  • Implement
Dominant language
JavaScript
Stars
36
Forks
74
Avg merge
2d 21h
Merged PRs (30d)
48

Getting set up

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from adobe/da-live

All issues in adobe/da-live

Similar issues

More JavaScript issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.