Preswald – AI Data Engineer in VSCode for Local Testing, Metrics
Hey HN, We're rolling out Preswald: an AI data engineer that lives inside VSCode. The goal is to make setting up and managing your startup metrics stupid simple—all from your editor, without adding SaaS tools, dashboards, or extra steps. Why? Most early-stage teams cobble together metrics using SQL, Python scripts, manual exports, and spreadsheets. We built Preswald to simplify that whole mess and keep it close to where engineers are comfortable: in their codebase. What Preswald Does: Local Testing: Write your SQL or transformation scripts directly in VSCode and test them locally before…
What it does
In the maker’s words, at launch
Hey HN, We're rolling out Preswald: an AI data engineer that lives inside VSCode. The goal is to make setting up and managing your startup metrics stupid simple—all from your editor, without adding SaaS tools, dashboards, or extra steps. Why? Most early-stage teams cobble together metrics using SQL, Python scripts, manual exports, and spreadsheets. We built Preswald to simplify that whole mess and keep it close to where engineers are comfortable: in their codebase. What Preswald Does: Local Testing: Write your SQL or transformation scripts directly in VSCode and test them locally before deploying. Preswald provides real-time validation and sample output previews to cut down the cycle of query-run-fix-repeat. Code Completion and Suggestions: Preswald autocompletes data transformations in SQL, helps with joins, checks your references, and prompts for missing details. It understands common patterns like churn and activation rates—no need to reinvent the wheel or dig through notebooks. Lightweight Analytics in VSCode: Get metrics like retention or churn set up in minutes, without exporting to another environment. Preswald can show sample metrics outputs as you work—helping you spot mistakes before they compound into bad analysis. Automation, Versioned in Code: Define your pipeline in pipeline.yml and deploy directly with preswald deploy pipeline.yml. No complex cron jobs, no broken scripts—Preswald automates ingestion, transformation, and delivery in a clean workflow. If something breaks, Preswald tells you what happened and suggests fixes. How it Works: Built on SQL Parsing and AST Analysis: Preswald analyzes your queries using abstract syntax trees to identify patterns and inefficiencies. It helps prevent redundant calculations or inconsistent joins and gives you suggestions to fix them. Real-Time Feedback: As you type in VSCode, Preswald generates inline comments, suggesting better SQL snippets, missing joins, or potential optimizations. We want to reduce the manual back-and-forth between writing queries and discovering runtime errors. Who It’s For: - If you’re a founder or part of a small team, Preswald can be your missing data engineer—saving you time that would otherwise be spent manually maintaining metrics. - If you’re a data engineer, this keeps your analytics in one place, gives you better version control, and helps automate testing and verification locally, all while reducing the tool overhead. Why VSCode? Everyone’s already in VSCode, so we figured, why create yet another dashboard? Preswald tries to bring the data engineering workflow into the same place you write the rest of your code, treating metrics setup like part of the codebase rather than a separate, duct-taped mess. We’re launching in private beta right now. If this sounds like something you could use, you can sign up for early access here: preswald.com We’d love your thoughts or feedback.
Does the same job
all alternatives →
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, November 2024
the whole month →
- IB
I wasn't quite sure if this qualified as "Show HN" given you can't really download it and try it out. However, dang said[0]: > If it's hardware or something that's not so easy to try out over the internet, find a different way to show how it actually works—a video, for example, or a detailed post with photos. Hopefully I did that? Additionally, I've put code and a detailed guide for the netboot computer management setup on GitHub: https://github.com/kentonv/lanparty Anyway, if this shouldn't have been Show HN, I apologize! [0]…
Dev tools · 2024 · lanparty.house
