Developer builds macOS file-renaming app using Apple Intelligence during a 9-hour flight

·1 views

A developer built a macOS app called Waypost during a 9.5-hour flight to solve the common problem of cryptically named files cluttering Downloads folders. The app reads file contents — including text, scans, PDFs, and images — and uses Apple Intelligence to generate meaningful names, sort files into folders, and apply tags. All processing runs locally on the user's Mac with no cloud uploads, meaning sensitive documents never leave the device. Waypost includes user controls such as per-file-type toggles, custom naming conventions, and an approval mode that suggests names before making any changes. The app is available as a one-time purchase for $7, built with Swift for macOS, Next.js for authentication, and Stripe for payments.

Read the full story at DEV Community

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

Discussion (0)

Developer Builds AI-Powered Legal Document Analyzer Using TypeScript and NodeJS

A developer has published a tutorial on DEV Community demonstrating how to build an AI-powered legal document analyzer using TypeScript, NodeJS, and the HazelJS framework. The tool automates four core tasks that traditionally consume significant lawyer time: document parsing, legal term extraction, risk assessment, and obligation summarization. It employs a multi-agent architecture where five specialized agents each handle a distinct analytical function, coordinated by a supervisor agent called LegalManagerAgent. Retrieval-Augmented Generation (RAG) with semantic search allows the system to query a knowledge base of legal documents categorized by type, risk level, and key clauses. The project aims to reduce the manual effort involved in reviewing contracts, NDAs, employment agreements, and other complex legal documents.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

RAG Techniques: How Query Transformation and Expansion Improve AI Retrieval

In Retrieval-Augmented Generation (RAG) systems, query transformation rewrites vague or incomplete user queries into more specific ones using context already available to the LLM, improving document retrieval accuracy. Query expansion complements this by generating multiple variations of the original query, each used to fetch relevant documents from a vector database. For example, a query like 'How do I deploy a FastAPI application?' can be expanded into variations covering Docker, AWS, Gunicorn, and Uvicorn deployments. During the augmentation phase, all retrieved contexts are combined with the original query and passed to the LLM to generate more accurate responses. As an alternative to LLM-based expansion, a rule-based approach can store pre-clustered related queries in the vector database for faster, cost-effective retrieval.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

Why Laravel Sanctum Sessions Break in Nuxt SSR and How to Fix It

When using Laravel Sanctum's SPA cookie authentication with a Nuxt frontend, authenticated requests succeed in the browser but return 401 errors during server-side rendering. This happens because Nuxt's SSR runs inside a Node/Nitro server process that has no cookie jar, no Origin header, and no browser context to attach session cookies automatically. The fix requires manually forwarding the incoming request's cookie and origin headers to outbound server-side API calls using Nuxt's useRequestHeaders utility. Additionally, the API base URL must differ by environment, since internal server processes often cannot reach public-facing addresses like localhost or external domains. State-changing requests also require proper CSRF handling by reading the XSRF-TOKEN cookie and echoing it in the X-XSRF-TOKEN request header.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

How to Build a WhatsApp AI Agent Using Google Gemini and Flask

Developers can create a WhatsApp bot powered by Google Gemini by connecting Meta's WhatsApp Cloud API with Google's Gemini API through a Python Flask server. The setup uses Gemini in a dual role: as the AI brain generating replies at runtime and as a coding copilot during development via the Gemini CLI or Gemini Code Assist in an IDE. The project requires a free Meta for Developers account, a Google AI Studio API key, Python 3.10 or higher, and a tool like ngrok to expose the local server to Meta's webhook. Inbound WhatsApp messages are received via a webhook POST request, processed by the Flask app, and responded to using the Gemini API through Meta's Graph API. The guide walks developers through environment setup, credential configuration, and writing the core app.py file to handle webhook verification and message responses.

0 comments Read more at DEV Community