... declared. values does not change and never will. It is the half that carries the coordinates and the character level match, so " 13,220" stays " 13,220" and 13220 shows up beside it in the other tree. The parsers are deterministic, with no model call, no added latency, and the same answer on every run. They handle full width digits, thousands separators, currency marks, unit suffixes like 3 , accounting negatives written as or in parentheses, era years like 8 ...

... Happy to finally say hello here! I ve spent most of my time working o n document parsing , and one of the open-source projects I released earlier was OCRFlux . I m now working on DocDot, a local PDF parser stack for macOS. The problem we kept coming back to was pretty simple: people want to keep documents local for privacy reasons, but local tools often force a tradeoff between speed and parsing quality. We built DocDot around that tension ... ... people can run multiple parsers

... getting close to launch. I m posting because I still want a round of honest product feedback before we put it in front of more people. DocDot is a local PDF parsing workflow for macOS. You can install multiple parsers with one simple command: curl -fsSL https://docdot.ai/install.sh | bash, compare outputs side-by-side with our web UI, switch parsers

... Product Hunt! I wanted to share 4 production-ready AI products I ve built recently, exploring different AI architecture patterns from in-browser WASM databases to ATS parsers: SetFlow AI Smart AI workout generator with quick-commerce price comparisons. Live App: https://setflow-ai-app.vercel.app Nexis Insights Product feedback analyzer featuring a 128-dimensional WASM SQLite RAG engine for semantic vector search & grounded citations. Live App: https://nexis-insights-app.verce... Tailorfit AI ATS resume optimizer & keyword match engine (also published ...

... goal streamline the application process for students, job seekers, researchers, and of course Founders. What we shipped for launch: Question Archive hundreds of programs catalogued across accelerators, grants, grad schools, and jobs. Every question scored by significance. Answer Bank VS-Code-style tree organized by theme. Write once, mark it draft , solid , or locked , reuse it everywhere with confidence tracking. Workstation paste any application you've already filled out and the system pulls the Q&A pairs straight into ... ... tell you who, not the client. The tired business owner. I was over chasing info from teams, drawn out projects, disconnected feedbacks, no way of seeing whom was working on each projects and how much is was costing vs

... wrong. ATS filters reject you before a human ever reads it. What KraftCV does: Save a job from LinkedIn/Indeed each one gets its own resume version ATS Scanner checks your keyword match, formatting, and structure against real ATS parsers before you hit apply AI tailors your bullets and skills to match the job description Every version saved and organized no more resume_final_v4_REAL.pdf Think of it like GitHub for resumes. Every job is a branch. Every resume version is a commit ...

... turf and not get further disintermediated by Google. Comment from Jonathan Song(@jonathan_song2): this is genuinely impressive. the dom-native approach makes so much sense - i've seen too many "AI agents" that are basically just screenshot parsers with vision models, which breaks constantly. few questions: - how do you handle dynamic SPAs where the DOM changes constantly? (thinking React/Vue apps with heavy client-side routing) - what's the latency like? 40 seconds for a full salesforce integration sounds fast ...

... results as Excel, CSV, JSON , send them to Google Sheets , or pull them via REST API into your own tools and pipelines. - Scheduled runs (paid plans) On paid tiers you can schedule recurring runs to monitor prices, inventory or competitors automatically. - Enterprise tier Custom robots for almost any website, large volumes, complex workflows and the ability to combine multiple parsers