Smarter Streaming

As streaming libraries grow, viewers increasingly search by remembering moments, scenes, or visual details rather than exact titles. This project explores how AI-driven search experiences can support natural discovery through Smart Search and frame-based exploration in OTT platforms.

Concept Project

Visual/UX Design

Year - 2025

Tools Used - Figma, ChatGPT

Concept overview

Smart Search

Existing Experience: Most OTT platforms rely on keyword-based search limited to titles, genres, and cast, making it difficult to discover content through moments, scenes, or dialogue

Design Vision: Smart Search enables users to search naturally, using scene descriptions, dialogue, themes, and situations - allowing discovery based on how viewers remember content, not just what it’s called

Scan The Frame

Existing Experience: When viewers pause a scene to identify an actor, outfit, location, or object, they must rely on external tools or guesswork, breaking immersion

Design Vision: Scan The Frame allows viewers to explore cast, style, locations, and props directly from a paused moment - turning curiosity into seamless, in-context discovery

Note: These features represent conceptual applications of AI within OTT platforms and are explored from a design and interaction perspective.

Design goals

Reduce search friction without disrupting viewing experience

Support discovery through natural language and visual thinking

Introduce AI without disrupting familiar OTT behaviors

Keep AI optional, explainable, and non-intrusive

Smart Search

Triptych of mobile screens showing the transition from the standard search landing page to the dedicated Smart Search interface and active keyboard input

Lives in a separate mode to keep normal search familiar and avoid confusion

It is opt-in by design, giving users full control over when AI steps in

To make Smart Search feel intuitive and reliable, I mapped user prompts into six clear intent types. Each category helps the system understand what kind of search the viewer means - whether they’re exploring broadly, describing a specific visual, recalling dialogue, searching by theme, using metadata, or mixing multiple cues.

Generic Prompts

Search results for a generic action description with a "Scene Match" detail card for Sherlock

These are broad, low detail searches that express intent but lack specific context

These are broad, low detail searches that express intent but lack specific context

They rely on the system to show a small set of top results first, then help users refine or explore

They rely on the system to show a small set of top results first, then help users refine or explore

Follow up prompt suggestions

AI refinement menu providing contextual follow-up options for a broad search query

These are broad, low detail searches that express intent but lack specific context

They rely on the system to show a small set of top results first, then help users refine or explore

Specific Visual Prompts

These are detailed recall inputs that describe distinct visual elements instead of facts or story themes

These are detailed recall inputs that describe distinct visual elements instead of facts or story themes

They help the system surface the closest scene matches with higher confidence

They help the system surface the closest scene matches with higher confidence

Search refinement interface offering visual and atmospheric scene descriptors

Visual elements based suggestions

Visual similarity search results with a timestamped scene match for the movie Skyfall

These are detailed recall inputs that describe distinct visual elements instead of facts or story themes

They help the system surface the closest scene matches with higher confidence

Dialogue Based Prompts

These are recall inputs where users search using memorable lines or spoken intent instead of titles

Smart Search interface with a natural language query based on a specific movie quote

Dialogue-driven search results showing an exact quote match within a specific scene of the movie Taken

These are recall inputs where users search using memorable lines or spoken intent instead of titles

Theme/Mood Based Prompts

Thematic search results with a "Narrative Similarity" match detail for the series Maid

These are abstract discovery inputs that express a story’s core idea or emotional tone

These are abstract discovery inputs that express a story’s core idea or emotional tone

Results are grouped by how strongly they match the theme, then ranked by tone and relevance

Results are grouped by how strongly they match the theme, then ranked by tone and relevance

Intent driven suggestions

AI-generated thematic refinement options focused on narrative arcs and character journeys

These are abstract discovery inputs that express a story’s core idea or emotional tone

Results are grouped by how strongly they match the theme, then ranked by tone and relevance

Metadata Based Prompts

These are factual searches based on known attributes like actors, awards, year, language, or genre

These are factual searches based on known attributes like actors, awards, year, language, or genre

Results start with factual data and ranking shifts only when intent is clear

Results start with factual data and ranking shifts only when intent is clear

Discovery refinement panel with options to filter content by specific data points like year or awards

Suggestions acting as filters

Search results for award-related queries with specific Oscar metadata highlighted for the movie Argo

These are factual searches based on known attributes like actors, awards, year, language, or genre

Results start with factual data and ranking shifts only when intent is clear

Hybrid Prompts

These combine two or more inputs in one search. Results are then ranked by the strongest clear input first

Smart Search input field showing a hybrid query combining award metadata with a thematic narrative description

Search results for a hybrid metadata and theme query, featuring a "Strong Match" detail card for A Beautiful Mind

These combine two or more inputs in one search. Results are then ranked by the strongest clear input first

Negative Scenarios

Non-sensical Input

System error state for unintelligible text input with suggested valid discovery prompts

Illicit Input

AI safety intervention message for restricted content queries with alternative discovery suggestions

General Input

System response redirecting non-entertainment queries back to movie and TV show discovery

Searching a vivid idea that may not exist in a real movie or show. Results lean on closest conceptual parallels

Smart Search input field demonstrating a complex, creative conceptual query regarding time and character movement

Search interface displaying "closest results" when an exact match for a creative concept cannot be found

Scan The Frame

Triptych of mobile screens showing the "In This Frame" AI feature identifying Scene, Style, and Props across different movie scenes

Video pauses automatically on tap and a side panel slides in to show scene details

Users explore the panel and return to the video instantly when it’s dismissed

In this interface, cognitive load is high because a single movie frame can contain dozens of objects. I categorized results into Scene, Style and Props to transform a cluttered list of items into a structured, intuitive discovery journey

Scene

Provides the "meta-layer"

Answers the immediate "Who is that?" or "Where is this?" without mixing biographical data with commercial products

Style

Addresses the "shop the look" intent

Groups everything wearable, allowing users interested in fashion to find products without sifting through technical gear

Props

Captures the narrative's "how-to"

This is for the tech-curious or fans interested in the gadgets, tools, and iconic items that drive the plot

An active video player with an AI "Details" tool for identifying elements within the current frame

User taps on Scan

The real-world impact & future potential

Integrating AI into the OTT experience moves us away from being passive viewers and toward a world where our screens truly understand our needs, making entertainment both more personal and more productive.

We’ve all spent thirty minutes scrolling through menus only to give up; Smart Search fixes this by letting you find a movie based on a feeling, a half-remembered line of dialogue, or a visual description. By cutting out the "choice paralysis" that ruins movie nights, platforms keep us happy and engaged, ensuring that even the most hidden gems in their library get the spotlight they deserve.

When you see a stunning dress or a cool gadget in a scene, Scan The Frame bridges the gap between "I want that" and "I own that." This turns every frame into an interactive storefront, allowing brands to connect with us through the things we already love, without annoying commercial breaks, and creating a whole new way for platforms to grow beyond just monthly subscription fees.