Developer-facing blueprint
Super Cut Club is a matching engine, not a job board.
In film, word of mouth is a wall that new talent cannot easily climb. This product turns professional intuition into a system: taste, resources, and availability get queried together so a director can find the right editor, not just the most connected one.
1. Core logic
The triple mapping system
The search layer needs to map three data types at once. If any one of them is missing, the shortlist feels incomplete or misleading.
Taste
Subjective creative fit
Aesthetic, mood, tempo, and visual rhythm extracted from reels instead of manually typed bios.
Resources
Objective production reality
Location, storage, workstation power, turnaround constraints, and pricing bands stored as structured filters.
Availability
Real-time bookability
A strong match is only useful if the editor is actually free when the project lands.
Search composition
How the engine assembles a match score
Taste should lead the shortlist, but it must stay grounded by production reality and actual availability.
2. Extraction logic
Let the system read the work instead of asking for essays.
Editors should not have to over-explain themselves in a text bio if the platform can analyze their reels directly and recover visual and rhythmic signatures from the actual work.
Visual extraction
The mood sensor
Frame snapshots from a reel become vectors. That lets the system compare a director’s visual reference against what an editor actually cuts, not just what they call themselves.
Rhythmic extraction
The pulse sensor
Music BPM, energy level, and pacing become machine-readable signals. High-BPM commercial editors separate naturally from slower documentary and narrative editors.
Visual matching
CLIP turns mood into vectors
Similar-looking work begins to cluster, which makes “moody neon” or “clean documentary realism” searchable without keyword stuffing.
Rhythmic matching
Audio analysis becomes pace metadata
BPM and energy help the system separate slow-burn editors from high-tempo commercial and music-video specialists.
3. Why this exists
Discovery platform beats word of mouth.
Word of mouth is slow, biased, and geographically narrow. A matching engine gives clients a better fit while giving overlooked talent a chance to surface through the quality of the work itself.
The platform becomes useful to both sides at once: clients get a more precise shortlist, and editors outside the usual production circles get a fairer route into the room.
4. Functional blueprint
Build a capabilities engine, then wrap it in a visual-first interface.
The database should not stop at “users.” It should model practical constraints, while the front end should let reference media reshape the shortlist in real time.
Database strategy
Capabilities, not just profiles
Store city, travel radius, machine strength, storage, and software stack as structured filters.
Use pricing tiers so basic reels and high-end commercial edits do not collapse into one vague rate field.
Offer simple toggles first, then calendar sync later if the product proves the need.
Speed-dating interface
Reference media should rearrange the grid instantly
The UI should feel visual-first: upload a reference track or mood board, then let the ranking shift around taste, not just text filters.
Capabilities engine
Treat hardware, city, price tier, and turnaround strength as a search substrate, not profile decoration.
Reference-first interface
Let the director upload a mood board or reference track so the grid reorders around the brief’s taste profile.
Proof over proximity
The system should help a strong editor in a smaller city surface beside big-network names if the work and setup match.
Next design layer
The next useful page is the onboarding flow.
We can turn this PRD into a concrete editor onboarding sequence next: what to ask, in what order, and how to capture signal without exhausting the user.