Algo Vision

Landing Page After Google Signup Select The Problem
A personalized video visualization is generated that performs a full dry run of the algorithm for the provided test cases.
Each and Every Question Available Which is Present in LeetCode

Inspiration

Algorithms are fundamental to computer science, yet many learners struggle to understand how they actually execute. Platforms like LeetCode provide excellent problems, but most explanations rely only on static code and textual walkthroughs.

We realized that the biggest challenge for beginners is visualizing how data structures evolve step-by-step during execution, especially for complex algorithms such as Dynamic Programming or Graph algorithms.

This inspired us to build Algo Vision, an AI-powered platform that converts algorithmic code into dynamic visual explanations.

To power reasoning and explanations, Algo Vision integrates Amazon Nova, a multimodal foundation model capable of understanding code, generating structured reasoning, and guiding learners through complex algorithmic logic.

What it does

Algo Vision transforms algorithm problems into interactive visual learning experiences.

Key features include:

Amazon Nova-powered AI reasoning to analyze algorithm logic
Step-by-step visualization of algorithm execution
Dynamic visualization of arrays, stacks, trees, graphs, and DP tables
A Live AI Tutor powered by Amazon Nova that explains algorithm behavior
Animated visual explanations generated from code execution

For example, consider the classic Dynamic Programming Fibonacci problem.

Inline recurrence relation:

$F(n) = F(n-1) + F(n-2)$

Display math representation:

$$ DP[i] = DP[i-1] + DP[i-2] $$

Instead of manually tracing recursive calls, Algo Vision visually shows how the DP table evolves step-by-step, helping learners understand overlapping subproblems and optimal substructure.

Amazon Nova analyzes the algorithm and generates explanations describing how each DP state is computed.

How we built it

Algo Vision uses a modern AI-powered full stack architecture combining visualization systems and intelligent reasoning.

Frontend

Next.js
TypeScript
Interactive UI for visualization playback

Backend

Python FastAPI
Code execution tracing
Visualization state generation

Visualization Engine

Manim for generating algorithm animations
FFmpeg for rendering animation videos

AI System

Amazon Nova for code reasoning, algorithm explanations, and tutoring
Agent-based architecture for task orchestration
Retrieval pipelines for algorithm documentation and context

When a user submits code, Amazon Nova analyzes the algorithm, extracts logical steps, and helps generate structured execution traces that are later converted into animations.

Many algorithms visualized in Algo Vision follow computational models such as:

$$ DP[i] = \max(DP[i-1], DP[i-2] + value_i) $$

which appears in optimization problems like House Robber or other dynamic programming tasks.

Challenges we ran into

Building Algo Vision involved several technical challenges:

Extracting deterministic execution traces from arbitrary user code
Designing a flexible system capable of visualizing multiple data structures
Ensuring explanations generated by Amazon Nova accurately match program execution
Optimizing rendering performance for algorithm animations
Maintaining scalability when generating animations for complex problems

Accomplishments that we're proud of

Built a complete AI-powered algorithm visualization platform
Integrated Amazon Nova to power reasoning, explanations, and tutoring
Generated animated explanations directly from user code
Created a Live AI Tutor capable of explaining algorithm steps
Designed a scalable architecture combining AI reasoning and visualization engines

What we learned

During development we learned:

How foundation models like Amazon Nova can assist algorithm education
Techniques for converting execution traces into visual representations
How AI can analyze complex algorithms such as Dynamic Programming
The challenges of building multimodal systems combining code, text, and visualization

For example, dynamic programming problems often involve computing optimal states:

$$ DP[i][j] = \max(DP[i-1][j], DP[i-1][j-w_i] + v_i) $$

Visualizing these transitions makes it much easier for learners to understand how optimal solutions are built.