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.

79 projects for “generative-ai”

Sort

Medium

Continuous Delivery Pipeline for Generative AI Apps in Hospitality

Hospitality companies are adopting generative AI for guest messaging, review responses, and concierge features, but their engineering reality is unforgiving: a broken deployment during a holiday weekend directly costs bookings. AI applications add new failure modes that traditional release processes do not catch, because a code change can pass unit tests while silently degrading model output. Teams need delivery pipelines built with those risks in mind. The intern builds a complete CI/CD pipeline for a generative AI application serving the hospitality sector. The application itself is a Python FastAPI service using LangChain to power guest-facing question answering, and the pipeline around it automates the path to production on AWS: source changes trigger automated builds, a test suite that covers both conventional code behavior and AI output checks, and staged deployment to AWS infrastructure with rollback if checks fail. The intern implements the pipeline configuration, environment management for API keys and model settings, and the deployment scripts that make releases repeatable rather than artisanal. The project teaches DevOps fundamentals in their modern AI-flavored form: pipeline design, automated testing strategies for LLM applications, AWS deployment practices, and the operational mindset that separates hobby projects from services businesses rely on.

hospitalityawsfastapi+3

View project

Hard

Image-to-Blog Generation Studio Using Vision-Language Models

Online sellers and content teams sit on large libraries of product and lifestyle photography but struggle to produce the written content that should accompany it: publishing schedules demand articles, product stories, and campaign posts faster than writers can study each image set and draft around it. A platform that looks at the images and drafts the article itself, weaving visual details into the text, removes the slowest step in that pipeline. The intern builds this multimodal generation studio using Streamlit for the interface and Python throughout. Users upload one or more images, and the system sends them to OpenAI's GPT-4o vision capability to extract what is actually in the frame: objects, materials, settings, mood. LangChain orchestrates the generation pipeline that turns those observations plus the user's brief into a structured blog post whose descriptions genuinely reference the uploaded visuals rather than generic filler. The intern implements the image-handling flow, the multimodal prompt design, tone and format controls, and a revision loop where users can regenerate individual sections while keeping the rest intact. The project demonstrates command of multimodal AI, a rare and current skill: combining vision-language models with orchestrated text generation, managing image inputs safely in a web app, and shipping a creative tool with real e-commerce utility.

e-commercegenerative-ailangchain+3

View project

Easy

Lightweight Text Generation API Built With LangServe

The gap between a working LangChain script and a service other software can call is deployment, and LangServe exists to close it: it turns chains into REST APIs with typed endpoints, streaming, and an interactive playground almost for free. Knowing this path from notebook to network service is essential for any developer who wants their AI work used by anyone other than themselves, and this project walks it end to end at a friendly scale. The intern builds a FastAPI project in Python that exposes a text generation chain through LangServe. The intern first constructs the chain itself with LangChain, a prompt template feeding a language model with configurable parameters such as topic and style, then mounts it as a LangServe route, gaining automatically generated endpoints for invocation, batching, and streaming. Around this core the intern adds a health check, request logging, and clear API documentation, then exercises the service from the built-in playground and from an external client script to prove the full round trip works. The project teaches deployment fundamentals for LLM applications: how chains become HTTP services, how FastAPI and LangServe divide responsibilities, what streaming responses look like on the wire, and how to structure a small AI service so that adding the next endpoint is easy, foundations the intern will reuse in every production AI role.

educationfastapigenerative-ai+2

View project

Easy

Plain-Language Explanation Generator for Bank Transactions

Bank statements are full of cryptic merchant codes, abbreviations, and reference numbers that leave many customers unsure what they actually paid for. Support teams field a steady stream of questions that could be answered automatically if raw transaction lines were translated into clear, human-friendly sentences. In this project the intern builds exactly that translator. Users supply anonymized banking transactions, and a python program parses each entry, cleans the fields, and passes them through a generation pipeline that uses openai models to produce a short, plain-language explanation of what the transaction likely represents. The workflow is structured with langgraph, which defines the steps from ingestion to explanation, while an agentic-ai coordination layer decides how each record moves through parsing, generation, and output formatting. The finished tool reads a list of transactions and returns an annotated version anyone can understand. Along the way the intern practices careful data handling, prompt design for financial text, and workflow automation, and finishes with a working example of generative AI applied to a genuinely common retail banking pain point.

bankingagentic-aigenerative-ai+3

View project

Easy

Business Insight Generator for Banking Scenarios and Data

Turning raw observations into a recommendation is the daily work of banking analysts: a branch sees deposit outflows, a product team sees rising card usage in one segment, and someone has to say what it means and what to do. This project builds a tool that assists that leap from data to insight. The intern creates a streamlit application in python where users describe a banking scenario or paste in summary data. The system embeds a library of prior cases and analytical patterns in a vector database, and a retrieval-augmented generation pipeline finds the situations most similar to the user's input. Generative AI then drafts actionable insights and recommendations that are grounded through RAG in those retrieved precedents, so suggestions echo what has actually been observed rather than generic advice. The interface presents the insight, the supporting cases, and the reasoning in a format a business reader can scan quickly. By building it, the intern learns how retrieval and generation combine into a decision-support tool, how to structure a case library for useful similarity search, and how to present AI-generated business advice with appropriate transparency.

bankinggenerative-aipython+4

View project

Hard

Script-to-Scene Breakdown Generator for Film Production Teams

Turning a script into a shoot-ready plan is one of the most labor-intensive steps in film and video production: someone must break every scene into camera angles, lighting setups, props, and locations, then keep all of it in sync as the script changes. Small studios and independent creators often skip the rigor entirely because they lack the staff to maintain it. The intern builds a web tool that automates the heavy lifting. Writers paste or upload a script, and a generative AI pipeline transforms it into structured scene breakdowns with suggested shots, lighting notes, prop lists, and continuity flags that the team can then edit collaboratively. The React frontend offers side-by-side script and breakdown views, a Node.js API manages projects and prompt orchestration, and MongoDB stores scripts, generated scenes, and full version history so any earlier draft can be restored. Secure authentication keeps unreleased material private, and finished breakdowns export in production-ready formats. The intern learns to design prompts that yield structured, editable output rather than free-form text, to build collaborative editing with versioning, and to ship a complete full-stack product for a real creative workflow.

entertainmentmediagenerative-aimongodb+2

View project

Hard

Space Mission Design Simulator With Generated Timelines and Risk Reports

Space mission design is normally locked inside agencies and aerospace firms, where teams of specialists iterate on timelines, mass budgets, and risk registers for months. Students and researchers who want to learn the discipline have almost no tools that let them experiment with realistic mission trade-offs on their own. The intern builds an educational platform where generative AI does the specialist heavy lifting. Users define mission parameters such as destination, payload, budget class, and whether the mission is crewed or robotic, and the AI generates candidate mission plans: phased timelines, resource allocations, launch windows, and risk assessments with mitigations. A Python backend orchestrates generation and validates outputs for internal consistency, PostgreSQL stores missions, revisions, and shared plans, and a React interface lets teams customize parameters, compare scenarios side by side, and collaborate on refinements. Secure authentication supports classroom use, and completed plans export as detailed reports. The project teaches structured generative AI design, turning open-ended generation into consistent, schema-conformant plans, plus the modular full-stack architecture that keeps an ambitious domain tool maintainable.

educationresearchgenerative-aipostgresql+2

View project

Hard

Mentor Matching Platform With Generated Mentorship Plans

Students consistently say mentorship changed their careers, yet most mentorship programs fail on logistics: matches are made on gut feel, plans never get written, and pairs drift apart after one enthusiastic first call. Program coordinators in education need tooling that makes good matches and then keeps those matches productive. The intern builds a platform where generative AI powers both the matching and the follow-through. Student and mentor profiles covering career interests, goals, skill gaps, and availability live in MongoDB, and the AI scores compatibility and generates a personalized mentorship plan for each pair: milestones, meeting cadence, and communication templates that keep conversations purposeful. A Node.js API manages accounts, matching runs, and progress tracking, while the React frontend gives mentors and mentees shared dashboards, session notes, and goal check-ins. Docker packages the services for deployment, and secure authentication protects what are often sensitive career conversations. The intern demonstrates AI product thinking beyond chat, using generation to produce structured plans people follow, alongside the full-stack, team-oriented engineering of a real education platform.

educationresearchdockergenerative-ai+3

View project

Medium

Retrieval-Backed Course Material Generator for Banking Education

Trainers and educators in financial services spend enormous effort producing course notes, quizzes, and explanations for every topic they teach, and the material dates quickly as products and regulations change. A generator that assembles fresh, accurate learning content from a maintained resource library changes the economics of banking education. The intern builds this generator in python with a streamlit interface. Educational resources, including articles, definitions, and worked examples, are embedded and stored in a vector database. When a user enters a banking topic or uploads their own learning materials, a retrieval-augmented generation pipeline gathers the most relevant source content and generative AI composes tailored outputs: explanatory lessons, topic summaries, and quiz questions with answers. Because generation is grounded through RAG in the stored resources, the produced material reflects the curated corpus rather than the model's unverified memory, and users can regenerate or refine content interactively. The project teaches content pipeline design, grounded generation for educational quality, and quiz construction logic, giving the intern a strong demonstration of AI applied to learning-content operations in a regulated domain.

bankingeducationgenerative-aipython+4

View project

Hard

Multichannel Marketing Campaign Generator and Analytics Workspace

Marketing teams juggle campaigns across search, social, email, and display, each demanding its own copy, formats, and reporting, and small agencies burn most of their billable hours on production rather than strategy. Generative tooling that drafts, adapts, and analyzes campaigns across channels fundamentally changes that economics. The intern builds a campaign workspace where generative AI produces ad copy variants, headline options, and visual direction suggestions tailored to each channel, then helps analyze performance once campaigns are live. A Node.js backend orchestrates the generation workflows and stores campaigns, briefs, and results in MongoDB, while the React frontend supports collaborative editing so multiple marketers can refine AI drafts together, with roles and approvals enforced by secure user management. Performance analytics close the loop by comparing variants and channels, and finished campaigns and reports export cleanly for clients and stakeholders. The intern learns to build generation workflows with human review at the center, to model collaborative editing safely, and to connect creative output to measurable results, which is the full shape of a modern marketing technology product.

e-commercemediagenerative-aimongodb+2

View project

Hard

Step-by-Step Process Guide Generator for Banking Operations

Banking operations such as loan processing, compliance checks, and customer onboarding involve dozens of steps spread across teams, and new employees typically learn them through fragmented shadowing. A tool that turns a described scenario into a complete, explained workflow gives institutions a scalable way to teach their own processes. The intern builds the generator in python with a streamlit interface. A library of banking workflows is embedded into a vector database, and when a user inputs or uploads a complex scenario, a retrieval-augmented generation pipeline retrieves the most similar existing workflows as scaffolding. Generative AI then produces a step-by-step process guide with a workflow diagram structure and beginner-friendly explanations of each stage: what happens, who is responsible, and what can go wrong. Users can ask follow-up questions about any step, and RAG grounds every answer in the stored workflow content. The design is modular to support team collaboration across ingestion, retrieval, and interface work. The intern learns process modeling, retrieval-grounded content generation, and interactive explanation design, finishing with an ambitious, industry-relevant system that demonstrates deep understanding of banking operations tooling.

bankingtechnologygenerative-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

…