Aplikacja Storia AI do YC

Summer 2024Active

Storia AI przeszedł przez Y Combinator w batchu Summer 2024 jako firma z branży B2B. Poniżej: czym zajmuje się firma, kto ją założył i jej aplikacja do YC, zrekonstruowana pytanie po pytaniu w prawdziwym formularzu YC.

Batch YC: Summer 2024
Branża: B2BEngineering, Product and Design
Wielkość zespołu: 2
Status: Active
Wystartowano: 2024

Foundersi

Julia TurcFounder

Czym zajmuje się Storia AI

With AI increasingly automating away code generation, software engineers will spend more time reading, judging, and architecting code rather than writing it. Storia is building an open-source copilot that knows a company's codebase and its context. We are starting with Sage, a Perplexity-like agent for helping developers understand, judge, and generate software. Given an existing codebase, developers can ask Sage questions such as: 1) Given my project’s SLA and latency constraints, what is the appropriate underlying vector database to use? How would I incorporate it into my existing codebase? 2) Why should I pick Redis over Milvus as my underlying vector store? 3) Does this codebase in our organization still work and what steps are required for a complex integration with another library? Sage’s answers are directly supported by documentation and external references like GitHub, Stack Overflow, technical design documents, and project management software, preventing hallucinations. Today, Sage has up-to-date knowledge about open-source repositories (indexed daily). Tomorrow it will have a deep understanding of every line of code on the Internet. For teams, Sage will know about your private codebase too. No group has yet solved how to build an AI system that comprehends a codebase and its context and can empower every developer to architect better code, faster. This requires new research advances because vanilla RAG and out-of-the-box LLMs aren’t going to cut it. We have 20+ years of software engineering and AI research experience. Julia worked on precursors of Gemini using contextual neural techniques before they were called “RAG” (and applied it to products like Google Keyboard and Pixel phones). Mihail built the earliest LLMs at Amazon Alexa and launched the first contextual deep learning conversational AI system in production at Alexa.

Aplikacja Storia AI do YC, zrekonstruowana

Aplikacja Y Combinator

Storia AI, batch Summer 2024. Prawdziwe pytania z formularza, odpowiedzi na podstawie danych publicznych.

Founders2
Company7
Progress7
Idea4
Equity3
Curious2
Batch Preference1

Company

Company name

Storia AI

Describe what your company does in 50 characters or less.

Open source AI copilot that knows your company's code

What is your company going to make? Please describe your product and what it does or will do.

We are building Sage, an open-source AI copilot designed to help developers understand, judge, and generate software by deeply knowing their company's existing codebase and its context. Sage answers complex engineering questions by referencing documentation, GitHub, Stack Overflow, design documents, and project management tools to avoid hallucination, starting with public open-source repos and expanding to private codebases. It's made for software engineers who spend more time reading and architecting code than writing it as AI automates generation.

Where do you live now, and where would the company be based after YC?

We live in San Francisco, CA, and the company will be based here after YC.

Explain your decision regarding location.

San Francisco is where we both live and it's the center of software engineering and AI innovation, making it the natural place to build a developer-focused AI product with engineering talent and early adopter customers nearby.

21 dodatkowych odpowiedzi w pełnej aplikacji

Są w pełnej wersji. Utwórz darmowe konto, aby otworzyć je w YC Insights, obok każdego innego batcha YC.

Zobacz pełną aplikację

Często zadawane pytania

Czy to jest prawdziwa aplikacja Storia AI do YC?

Nie. Y Combinator utrzymuje prywatność złożonych aplikacji. Jest to rekonstrukcja: prawdziwe pytania z formularza YC, na które odpowiedziano na podstawie publicznych danych Storia AI (notatki o premierze, tło founderów, opis produktu). Pokazuje, jak firma taka jak Storia AI przedstawiłaby się YC, a nie tekst, który złożyli.