SShortSingh.
TopTechnologyAI & MLStartupsProgrammingScienceBusinessFinanceCrypto & Web3World
Back to feed
Programming

GeoSQL: Open-Source AI Skill Lets Claude and Codex Query Geospatial Data

0
·3 views

GeoSQL is a newly released open-source tool developed by Dekart XYZ that functions as an AI skill for geospatial data analysis. It is designed to work with large language models, specifically Anthropic's Claude and OpenAI's Codex. The tool enables these AI models to query and process geospatial datasets using SQL-like interactions. It was shared on Hacker News, where it attracted modest early attention from the developer community.

Read the full story at Hacker News

This is an AI-generated summary. ShortSingh links to the original source for the complete article.

Discussion (0)

Log in to join the discussion and vote.

Log in

Related stories

0
ProgrammingDEV Community ·

Student Builds On-Device AI Security App Aigris to Detect Phishing Without Cloud

A second-year Computer Engineering student has developed Aigris, an experimental Android application designed to protect users from phishing, malicious URLs, and social engineering attacks using AI that runs entirely on-device. Unlike most security tools that rely on remote cloud servers, Aigris processes data locally on the smartphone to preserve user privacy and reduce latency. The app is built using Kotlin, ONNX Runtime, and on-device machine learning models optimized to work within mobile performance and battery constraints. Current features focus on phishing detection, suspicious URL analysis, and real-time threat alerts, with future plans including social engineering detection and browser protection. The developer has open-sourced the project to invite community feedback and collaboration as development continues.

0 comments Read more at DEV Community
0
ProgrammingDEV Community ·

Open-Source Tool rubric-bench Brings Regression Testing to LLM Grading Systems

Developer teams routinely deploy LLM-based judges and graders to production without formal testing, leaving their behavior vulnerable to silent regressions from model updates or prompt changes. To address this, a new open-source TypeScript library and CLI called rubric-bench v0.1 has been released, treating LLM grading engines like any other code subject to automated testing. The tool uses versioned JSON golden sets of labeled cases and compares grader outputs across runs, flagging regressions via exit codes that can halt CI pipelines before a breaking change is merged. An initial 72-case benchmark for introductory statistics showed the tested grader scoring 95.8%, with all three errors falling in the partial-credit gray zone where human graders also tend to disagree. The authors note that the approach generalizes beyond academic grading to tasks like content moderation and ticket triage, provided teams use discrete verdict labels rather than continuous scores.

0 comments Read more at DEV Community
0
ProgrammingDEV Community ·

Developer Builds First Working Version of SiteGen AI Using FastAPI and Gemini API

A developer has shared the process of building the first functional version of SiteGen AI, a tool designed to generate complete websites — including HTML, CSS, and JavaScript — from a simple text prompt. The initial stack used Python, FastAPI, SQLite, and Google's Gemini API, with a straightforward workflow routing user prompts through the backend to the AI and rendering results directly in the browser. Early testing revealed recurring issues such as generic designs, near-identical outputs, and the AI partially ignoring prompts, which the developer attributed not to the AI itself but to poor prompt engineering and system architecture. The experience led to a key insight: quality AI output depends heavily on structured, context-rich prompts and thoughtful system design. The developer plans to detail a more ambitious second version, SiteGen AI v2, aimed at functioning as a full AI software engineer capable of generating complete applications.

0 comments Read more at DEV Community
0
ProgrammingDEV Community ·

Building Cloud-Connected Software as a Medical Device: Key Architecture and Compliance Needs

Cloud-connected Software as a Medical Device (SaMD) is transforming clinical application development by enabling real-time data sync, AI-driven decision support, and remote patient monitoring. Unlike standalone medical software, these systems integrate secure cloud infrastructure to support continuous device communication, over-the-air updates, and centralized analytics. A modern SaMD architecture spans multiple layers, including device endpoints, edge processing, secure API gateways, cloud backends, and specialized data storage. Building such systems demands expertise in security protocols like OAuth 2.0 and OpenID Connect, as well as cloud-native practices such as containerization, CI/CD pipelines, and infrastructure as code. Healthcare technology teams must also address strict regulatory compliance and interoperability requirements throughout the development and deployment process.

0 comments Read more at DEV Community