DJ Moore

I've been a Shadow user for well over a year now and find it a major part of my workflow.

I was first drawn to Shadow due to its offline transcription. This is a considerable plus in highly regulated industries. The automation of skills is also another great time saver, such as exporting Markdown meeting notes to a folder for synchronization or connecting with Obsidian and other note-taking apps.

Now they've introduced screen recording, which gives the models much more context about what you were doing. This should be a significant boost in productivity and recall.

It would be difficult to keep up with work without it. I don't know how I—or anyone else—got by without it before it existed.

I know this is something the team is actively working on, but speaker attribution could stand to be more accurate. To be fair to the team, no one else has figured this out yet, either. When they do, it will represent a computer science breakthrough.

With Shadow, you can just set it and forget it. It does all the heavy lifting. It detects meetings reliably and does not need manual coercion like some of its alternatives. It runs very reliably as a background process and does not consume many resources. One of its biggest features is its ability to capture screenshots as it records and transcribes, providing additional context. I had not seen this since rewind.ai, which has now been acquired by Meta.

Shadow is one of the best in its class for capturing audio reliably and clearly.

I'm not sure what is on the horizon, but they have a feedback page that they use regularly. I'm always dropping different ideas there and often get feedback on those ideas from the developers or the CEO himself.

I've spoken directly with the CEO several times as a user, and they have a Slack channel in which they are highly active and will respond to anyone quickly.