{"id":83405,"title":"Storia: A contextual AI pair programmer for developer teams","tagline":"We help engineering teams understand, analyze, and generate software with their codebases.","body":"![uploaded image](/media/?type=post\u0026id=83405\u0026key=user_uploads/812126/ce70880c-852a-4e80-a573-88f6742298ed)\n\nHi everyone. We’re Julia and Mihail, the team behind [Storia](https://storia.ai/?utm_source=yc\u0026utm_medium=social\u0026utm_campaign=launch-yc). We have 20+ years of software engineering and AI research experience. [Julia](https://www.linkedin.com/in/iulia-raluca-turc/) 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](https://www.linkedin.com/in/mihaileric/) built the earliest LLMs at Amazon Alexa and launched the first contextual deep-learning conversational AI system in production at Alexa.\n\n**👎 The Problem: \u003c5% of software teams use AI code understanding and generation systems**\n\nDespite all the hype around AI coding following the release of GitHub Copilot, a disappointingly small percentage of engineering teams have actually adopted AI assistants into their developer workflows. Why?\n\nWhat developers don’t like about systems today:\n\n1. **Code search is not accurate enough**, slowing dev velocity.\n2. **Code assistants are not grounded in their team’s codebase**, so they lack the necessary context to produce useful and high-quality answers.\n3. **Code outputs can be incorrect** due to hallucination which strains dev patience and trust.\n\n**🚀 The Solution: A contextual AI pair programmer built for any team’s codebase**\n\n![uploaded image](/media/?type=post\u0026id=83405\u0026key=user_uploads/812126/0e093af4-4352-4550-a123-be44cf3dc747)\n\nWe’re building [Sage](https://sage.storia.ai/?utm_source=yc\u0026utm_medium=social\u0026utm_campaign=launch-yc), a Perplexity-like agent for helping developers understand, analyze, and generate software. Given an existing codebase, developers can ask Sage questions such as:\n\n* _For 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?_\n* _Why should I pick Redis over Milvus as my underlying vector store?_\n* _Does this codebase in our organization still work, and what steps are required for an integration with another library?_\n\nA few of the features Sage supports:\n\n* **We index repos daily**, providing users with the most up-to-date info about how to use a library (no stale, deprecated API definitions),\n* We have a Perplexity-like focus on **citing the source of every generated line of code**, enhancing developer trust.\n* We've developed algorithms grounded in research for **syntactic and semantic understanding of a codebase** so that we can provide more relevant context and use it effectively given a user query.\n\n We are now actively working with seed to series C partner companies to help them integrate Sage into their developer workflows. \n\n**🌅 The Opportunity: Making every engineer on a software team a 10x developer**\n\nThere are \\~28M developers worldwide. Github Copilot is the frontrunner in AI assistant tooling and reached $100M ARR in 2 years, which is only a small percentage of the $913B spent on software development in 2023.\n\n**🙏 Our Ask**\\\nWe’re still onboarding a closed group of beta partners to integrate with Sage. We would appreciate connecting with engineering leaders (VP of engineering, Head of Engineering, CTO)  at Seed-Series C companies. \n\nAdditionally, if you want your open-source repository indexed reach out to us at [mihail@storia.ai.](mailto:founders@storia.ai)\n\n![uploaded image](/media/?type=post\u0026id=83405\u0026key=user_uploads/812126/dd520900-8415-4ee5-8707-554b7197037b)\n\n","slug":"LhF-storia-a-contextual-ai-pair-programmer-for-developer-teams","created_at":"2024-08-26T16:32:20.077Z","updated_at":"2026-05-24T21:07:14.895Z","total_vote_count":38,"url":"https://www.ycombinator.com/launches/LhF-storia-a-contextual-ai-pair-programmer-for-developer-teams","share_image_url":"https://www.ycombinator.com/media/?type=post\u0026id=83405\u0026key=user_uploads/812126/dd520900-8415-4ee5-8707-554b7197037b","company":{"id":29673,"name":"Storia AI","slug":"storia-ai","url":"https://storia.ai","logo":"https://bookface-images.s3.amazonaws.com/small_logos/b303aec8b08b8ee5b7c074ef02f910506fd73654.png","batch":"Summer 2024","industry":"B2B","tags":["Artificial Intelligence","Developer Tools","Machine Learning","SaaS"],"search_path":"https://bookface.ycombinator.com/company/29673"}}