adobe / adobe/da-live

[EW] Agent: extract content from screenshot

Open
#1,246 0 comments 0 reactions 0 assignees View on GitHub
customer-feedback ew
Dominant language
JavaScript
Stars
34
Forks
71
Avg merge
2d 11h
Merged PRs (30d)
29

Description

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

Contributor guide

Open the contributing guide

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.

Assessment

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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.