The catalog

300+ projects to build

Every project comes with a complete PRD, HLD & LLD. Filter by domain, difficulty or tech stack to find your next build.

7 projects

Sort

Easy

Regulation Lookup Assistant with Plain-Language Explanations

Banking regulation governs everything from how accounts are opened to how suspicious transactions are reported, yet the primary texts are impenetrable to the students and junior staff who most need them. An assistant that retrieves the relevant rule and explains it simply makes compliance knowledge accessible instead of intimidating. The intern builds this assistant as a streamlit application in python. A corpus of banking regulations and guidance documents is embedded into a vector database, and when a user asks a question, such as what identification is required to open an account, a retrieval-augmented generation pipeline locates the most relevant regulatory passages. Generative AI then explains the rule in simple terms, stating what it requires, who it applies to, and why it exists, while the interface shows the retrieved source text alongside the explanation so users can check the answer against the actual rule. Grounding through RAG is essential here, since invented regulatory detail would be worse than no answer. The project teaches retrieval over authoritative texts, faithful plain-language explanation, and the transparency patterns that responsible AI tools use in legal and compliance settings.

bankinglegalgenerative-aipython+4

View project

Easy

Regulatory Change Alert Builder with Retrieval-Based Context

Compliance staff cannot read every regulatory update the moment it lands, so banks rely on alerting: short, targeted messages that tell the right people what changed and what to do. Producing those alerts quickly and accurately is a focused, high-value task for retrieval-grounded AI. The intern builds an alert builder as a streamlit application in python. Regulatory updates and reference materials are embedded and stored in a vector database, and when a user wants an alert on a topic, such as changes to customer verification requirements, a retrieval-augmented generation pipeline pulls the relevant updates and context. Generative AI then drafts the alert message: what changed, who is affected, and the recommended response, in a concise format suited to internal distribution. The interface lets users adjust scope and regenerate drafts, and because generation is grounded through RAG in retrieved regulatory content, alerts reflect the actual updates rather than model guesswork. The project teaches regulatory monitoring concepts, grounded drafting for high-stakes communication, and practical RAG pipeline construction, leaving the intern with a compact but convincing compliance-technology demonstration.

bankinglegalgenerative-aipython+4

View project

Hard

Collaborative Multi-Agent Workflow System for Legal Case Analysis

Legal work is naturally multi-role: one person researches precedent, another reviews documents, another drafts, and a senior lawyer synthesizes it all into advice. Single-prompt AI tools flatten this into one shot and lose the rigor. The frontier of legal AI lies in systems where specialized agents mirror that division of labor, checking and building on each other's work, and engineering such a system is among the most demanding tasks in applied AI today. The intern implements this system using LangGraph to define the collaboration as a stateful graph: nodes for a research agent, a document-analysis agent, a drafting agent, and a reviewer agent, with edges controlling how work and intermediate conclusions flow between them. LangChain supplies each agent's tools and prompt infrastructure, OpenAI models provide the reasoning, and shared memory lets agents reference earlier findings so the workflow stays context-aware across steps. The whole system is exposed through a Python FastAPI service where a user submits a legal question or document set and receives the orchestrated result with each agent's contribution traceable. This hard-difficulty project demonstrates elite-tier skills: graph-based orchestration, inter-agent state management, role-specialized prompt engineering, and delivery of a complex agentic system as a dependable API.

legalfastapigenerative-ai+4

View project

Medium

Formal English Rewriting Service for Legal Client Communications

Law firms receive client communications in every register: text-message fragments, colloquial emails, and slang-heavy accounts of events. Before those accounts can enter case files, demand letters, or court documents, someone must translate them into precise formal English without altering their meaning, and in legal work a shifted nuance can change a case. That rewriting is skilled, repetitive, and currently absorbs paralegal hours that firms would rather spend elsewhere. The intern builds a web service that automates this conversion with the fidelity the legal domain demands. The service is a Python FastAPI application in which LangChain structures the rewriting pipeline and OpenAI models perform the transformation, converting informal or slang-laden input into formal English while preserving factual content. The intern engineers prompts that explicitly guard against meaning drift, implements a side-by-side response format highlighting what changed so a professional can verify the rewrite, and adds batch endpoints so a firm can process message threads at once. Configurable formality levels let output match different document types. The project demonstrates controlled text transformation, a subtler skill than generation: constraint-focused prompt engineering, meaning-preservation checks, and delivering language AI through a clean, professional-grade FastAPI service.

legalfastapigenerative-ai+3

View project

Easy

Upload-and-Ask PDF Reader for Study and Legal Documents

Whether it is a landlord agreement, a course syllabus, or a fifty-page reading assignment, most people interrogate PDFs the same way: scroll, squint, and hope the relevant paragraph jumps out. Students and people facing legal documents feel this hardest, because the answer they need is usually present but buried in language designed for experts. Letting a user upload the document and simply ask their question closes that gap. The intern builds this tool as a Streamlit application in Python. A user uploads a PDF and types questions in plain language; behind the interface, LangChain's PDF loader extracts the document text, which is split into chunks and embedded for retrieval. Each question triggers a retrieval-augmented generation flow: the most relevant chunks are found by similarity search and passed to the language model, which composes an answer grounded in the document, with the supporting excerpts shown so users can confirm the answer against the original text. The intern implements the upload handling, the loader and splitter configuration, and the question-answer interface with source display. The project teaches the complete RAG pattern at an approachable scale, covering document loading, chunking, embeddings, retrieval, and grounded generation, and leaves the intern with both a genuinely useful study tool and the architecture underlying most commercial document AI.

educationlegalgenerative-ailangchain+2

View project

Medium

Histogram Comparison Toolkit for Art Authentication

Art authentication disputes often hinge on subtle material evidence, and pigment usage leaves measurable fingerprints in the color statistics of a photographed work. Galleries, appraisers, and legal teams involved in provenance cases need accessible quantitative tools that complement expert opinion, since laboratory analysis is expensive and not always available in early screening. In this project the intern creates a Streamlit application for forensic image comparison built on OpenCV and NumPy. Users load photographs of two artworks, and the tool computes and plots channel histograms across multiple color spaces, applies histogram equalization to normalize for differing photographic conditions, and produces similarity scores between the works using histogram comparison metrics. Results are organized with pandas into a comparison report, and the interface visualizes where two pieces align or diverge so a non-technical examiner can interpret the evidence. The intern learns how low-level image statistics become decision-support evidence, gains hands-on practice with color space theory, histogram operations, and similarity measures, and demonstrates the judgment needed to present quantitative findings honestly, as supporting signals rather than verdicts, in a domain where conclusions carry legal weight.

legalmediacomputer-visionnumpy+4

View project

Medium

Extractive Summarization Tool for Legal and News Documents

Lawyers reviewing case files, journalists monitoring wire feeds, and students confronting dense readings all face the same problem: documents arrive faster than anyone can read them. Extractive summarization, selecting the most important sentences verbatim rather than generating new text, offers trustworthy compression because every sentence in the summary provably exists in the source. The intern builds a Python command-line tool implementing two complementary approaches. A frequency-based summarizer scores sentences by the importance of their words after NLTK-driven tokenization and stopword filtering, while a TextRank summarizer builds a sentence similarity graph with NetworkX and ranks sentences using the PageRank-style algorithm that treats each sentence as a node voting for its neighbors. Users feed in large text files and receive concise summaries at a chosen compression level, and a visualization option displays each sentence's importance score so users can see exactly why the algorithm kept what it kept. The project gives the intern a solid grounding in graph-based NLP and classical text scoring, practical experience designing a CLI that handles real documents gracefully, and a demonstrable tool relevant to legal, media, and education workflows where transparent, non-hallucinating summarization is a hard requirement.

educationlegalnetworkxnlp+2

View project