Star ratings can't tell you what to watch tonight when you're in a specific mood. This recommender asks a couple of questions and answers from how films actually feel.
Star ratings can't tell you what to watch tonight when you're in a specific mood. This recommender asks a couple of questions and answers from how films actually feel.
Plot and tone embeddings live in Qdrant; a short chat captures mood, runtime, and what you've already seen, then the search excludes repeats. You get a ranked shortlist where each pick comes with a sentence explaining why it matches.
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.
Hold a short conversation to capture mood, runtime limits, and titles already seen.
pending
Search Qdrant for nearby films, excluding anything the viewer has already watched.
pending
Present a ranked shortlist, each with a sentence on why it fits the stated mood.
pending
Sample output
json
// Sample output
// (generated when the pipeline finishes)
Run a short conversation about taste, then return ranked films from Qdrant with a per-title reason and no repeats.
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.