Build a public-data source catalog
An organized catalog of relevant datasets with access, freshness, and licensing notes.
A little inspiration is on its way…
Workflows for research with Muse: finding sources, checking claims, building reading lists with notes. Plus a community Muse invite code pool.
Research is where an agent with a browser earns its keep: finding the primary source behind a claim, collecting what five articles agree on, and telling you where they disagree.
The workflows below insist on links. Every summary Muse produces should point back to where it came from, so you can check the parts that matter.
An organized catalog of relevant datasets with access, freshness, and licensing notes.
Treat it as a starting point. Sundog research workflows ask for links and quotes so you can verify anything you rely on, and they tell the agent to say when it could not find a source.
Sign in to Sundog, take one code from the community pool, redeem it under Redeem invite code in your Muse settings within 48 hours of joining, then add your own code for the next person. You and the person who shared the code each get 1 billion Muse tokens. One code per person, and codes never bypass Meta's availability or eligibility rules.
Starter workflows are original instructions written as starting points and are labelled untested. Community members report what worked, and those results appear on each workflow page as they come in.
A clear assessment of what a claim says and what its cited evidence supports.
A focused interview guide that makes good use of an expert's time.
A repeatable research checklist for tracking updates in a specific jurisdiction.
A prioritized reading path with short annotations and clear relevance.
A dated comparison of publicly documented features and positioning.
A brief centered on the decision you need to make, with evidence and limitations.
A traceable citation trail for a number you want to use.
An evidence table that shows exactly where sources agree and disagree.