Genre filters give people the same blockbusters everyone already saw. This recommender reads what a viewer actually describes and finds titles that fit the mood.
Genre filters give people the same blockbusters everyone already saw. This recommender reads what a viewer actually describes and finds titles that fit the mood.
Movie documents stay in MongoDB Atlas, with embeddings indexed next to them through Atlas Search. A request runs a hybrid search that blends vector similarity with rating and genre filters, then returns ranked picks, each with a one-line reason pulled from the synopsis.
How it runs
Used at step 01 to kick off the pipeline.
Write
Used at step 01 to kick off the pipeline.
WebFetch
Used at step 01 to kick off the pipeline.
WebSearch
Used at step 01 to kick off the pipeline.
Build an Atlas Search index that combines vector similarity with genre and rating filters.
pending
On a request, embed the user's described taste and run a hybrid search over the catalog.
pending
Return the top matches with a short reason for each pick drawn from its synopsis.
pending
Sample output
json
// Sample output
// (generated when the pipeline finishes)
Given a user's described taste, return ranked movie recommendations from MongoDB Atlas with a one-line reason per title.
Unlock the rest
The full agent definition, install snippet, and starter task are gated for community members.
Members get the full `.md` agent file, the npm / pnpm install one-liners, a starter prompt that we've tuned against real runs, and the open-source repo when this automation ships there. One email, magic link, done.