What it does
Classifies batches of text before an agent reads them, exposing the filter through a portable plugin and MCP tool.
Agent tooling
Only you can see your notes.
Screenshot unavailable. Open the experiment ↗
Classifies batches of text before an agent reads them, exposing the filter through a portable plugin and MCP tool.
Start by collecting sample web pages, files, or tool descriptions you want screened. Have your developer set up the sift tool using an access key from the TypeSafe dashboard. The tool sends those items to Jev to score their relevance against your query so your main assistant only reads the best matches.
Keep in mind that this tool sends your text or web links out to an external service to judge them. Also, when screening tools, it only evaluates their written descriptions. It does not run the tools or guarantee what their results will actually be.