The wall confronting large language models
22 by PaulHoule | 2 comments on Hacker News.
Wednesday, 3 September 2025
New top story on Hacker News: Vector search on our codebase transformed our SDLC automation
Vector search on our codebase transformed our SDLC automation
9 by antonybrahin | 0 comments on Hacker News.
Hey HN, In software development, the process of turning a user story into detailed documentation and actionable tasks is critical. However, this manual process can often be a source of inconsistency and a significant time investment. I was driven to see if I could streamline and elevate it. I know this is a hot space, with big players like GitHub and Atlassian building integrated AI, and startups offering specialized platforms. My goal wasn't to compete with them, but to see what was possible by building a custom, "glass box" solution using the best tools for each part of the job, without being locked into a single ecosystem. What makes this approach different is the flexibility and full control. Instead of a pre-packaged product, this is a resilient workflow built on Power Automate, which acts as the orchestrator for a sequence of API calls: Five calls to the Gemini API for the core generation steps (requirements, tech spec, test strategy, etc.). One call to an Azure OpenAI model to create vector embeddings of our codebase. One call to Azure AI Search to perform the Retrieval-Augmented Generation (RAG). This was the key to getting context-aware, non-generic outputs. It reads our actual code to inform the technical spec and tasks. A bunch of direct calls to the Azure DevOps REST API (using a PAT) to create the wiki pages and work items, since the standard connectors were a bit limited. The biggest challenge was moving beyond simple prompts and engineering a resilient system. Forcing the final output into a rigid JSON schema instead of parsing text was a game-changer for reliability. The result is a system that saves us hours on every story and produces remarkably consistent, high-quality documentation and tasks. The full write-up with all the challenges, final prompts, and screenshots is in the linked blog post. I’m here to answer any questions. Would love to hear your feedback and ideas!
9 by antonybrahin | 0 comments on Hacker News.
Hey HN, In software development, the process of turning a user story into detailed documentation and actionable tasks is critical. However, this manual process can often be a source of inconsistency and a significant time investment. I was driven to see if I could streamline and elevate it. I know this is a hot space, with big players like GitHub and Atlassian building integrated AI, and startups offering specialized platforms. My goal wasn't to compete with them, but to see what was possible by building a custom, "glass box" solution using the best tools for each part of the job, without being locked into a single ecosystem. What makes this approach different is the flexibility and full control. Instead of a pre-packaged product, this is a resilient workflow built on Power Automate, which acts as the orchestrator for a sequence of API calls: Five calls to the Gemini API for the core generation steps (requirements, tech spec, test strategy, etc.). One call to an Azure OpenAI model to create vector embeddings of our codebase. One call to Azure AI Search to perform the Retrieval-Augmented Generation (RAG). This was the key to getting context-aware, non-generic outputs. It reads our actual code to inform the technical spec and tasks. A bunch of direct calls to the Azure DevOps REST API (using a PAT) to create the wiki pages and work items, since the standard connectors were a bit limited. The biggest challenge was moving beyond simple prompts and engineering a resilient system. Forcing the final output into a rigid JSON schema instead of parsing text was a game-changer for reliability. The result is a system that saves us hours on every story and produces remarkably consistent, high-quality documentation and tasks. The full write-up with all the challenges, final prompts, and screenshots is in the linked blog post. I’m here to answer any questions. Would love to hear your feedback and ideas!
Tuesday, 2 September 2025
Monday, 1 September 2025
Sunday, 31 August 2025
New top story on Hacker News: How do you fight YouTube addiction and procrastination? I'm struggling with it
How do you fight YouTube addiction and procrastination? I'm struggling with it
21 by angelochecked | 23 comments on Hacker News.
My current daily routine looks like this: - 8:00~9:00 – Getting ready for work - 9:00–13:00 – Work - 13:00–14:00 – Lunch + YouTube - 14:00–18:00 – Work - 18:00–20:00 – Break from work + Dinner + YouTube - 20:00~1:00 – YouTube, gaming, occasional events, personal projects, or sports. Lately, I’ve noticed my screen time during this period has increased a lot, and I’ve been feeling lazy to do anything productive—mostly just doomscrolling or watching videos What’s your routine like? How do you manage your time, maintain social connections, avoid digital distractions, and stay on track with your goals and learning?
21 by angelochecked | 23 comments on Hacker News.
My current daily routine looks like this: - 8:00~9:00 – Getting ready for work - 9:00–13:00 – Work - 13:00–14:00 – Lunch + YouTube - 14:00–18:00 – Work - 18:00–20:00 – Break from work + Dinner + YouTube - 20:00~1:00 – YouTube, gaming, occasional events, personal projects, or sports. Lately, I’ve noticed my screen time during this period has increased a lot, and I’ve been feeling lazy to do anything productive—mostly just doomscrolling or watching videos What’s your routine like? How do you manage your time, maintain social connections, avoid digital distractions, and stay on track with your goals and learning?
Saturday, 30 August 2025
Subscribe to:
Posts (Atom)