How MovieJam Builds a Perfect Rec Flow in Under 90 Seconds
The WhatsApp experience is deceptively simple—text MovieJam, wait a minute, get three eerily accurate picks. Under the hood we run a tight loop of context capture, scoring, and human spot-checks. Here’s the exact flow we iterate on every week.
Step 1 · Warm context intake
Conversation primer
We ask for four data points upfront: mood, companions, available services, and hard no-go genres. If the user skips one, the bot adds a light follow-up (“any services off limits tonight?”) before it starts ranking.
We also track “emotional energy” keywords (tired, wired, need cozy) because they map better to success than genre labels alone.
Step 2 · Scoring + ranking
Recipe
- Weight 1: Mood compatibility score pulled from our embeddings library.
- Weight 2: Momentum signals (Letterboxd buzz, WhatsApp mentions, box office if theatrical).
- Weight 3: Diversity guardrail—we ensure at least one pick is a “curveball” to avoid bland lists.
The system drafts 5–7 options, then whittles down to three based on freshness (no repeats in the last 21 days for the same user).
Step 3 · Human-in-the-loop
Editor review
20% of chats route to a human editor (rotating schedule) who can tweak synopses, swap a title, or add snack/playlist notes. Editors tag each change with a reason code so the model learns when we override it.
Step 4 · Delivery + instrumentation
What we watch
- Did the user react with 👍, ask for swaps, or drop off?
- Did they request the same mood again within 7 days?
- Were any titles geo-blocked? If so, the fallback library updates automatically.
“The magic trick is balancing personalisation with novelty. We’d rather risk one wild-card pick than send three safe tiles you could’ve scrolled past yourself.” — MovieJam Ops
What’s next
- Auto-summarising “why this rec” blurbs so people can skim faster.
- Surfacing soundtrack snippets inside WhatsApp for music-driven films.
- Letting Premium users say “send me the rainy-night variant” and auto-apply saved preferences.
Want the full playbook?
If you’re building a compset concierge or want help tuning your rec system, we can share our prompt templates and QA dashboards.
Request the walkthrough →