Who it is forA frontend developer implementing a design or API from a screenshot or docs page.
The problemDescribing a visual or a doc in text loses detail.
The outcomeCode changes informed by the images and pages you added.
What you need first
- Python and pip
- An API key for the model you pick, such as DeepSeek or OpenAI, or a local model
- A git repository for your project
Steps
- Install Aider with
python -m pip install aider-installthenaider-install - Start Aider in your project with your model
- Add the image or web page to the chat as described in the Aider images and URLs docs
- Ask for the change and review the commit
Prompt for your agent
With Aider-AI/aider, add <screenshot or URL> to the chat in <my project> and implement <feature> to match it.
Caveat. Image support depends on the model you choose.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for Aider-AI/aider and "Add screenshots and web pages as context in Aider"
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer