Loading project...
Back to Work
Uppend
An AI-powered job application tracker that turns a pasted job posting into a structured, trackable application, complete with an AI-generated fit assessment against your resume — built to solve a real problem from my own job search: manually retyping postings into a spreadsheet and guessing whether a role was worth applying to.
Features
Local Mode
No signup required — jump straight in and track applications entirely in your browser (IndexedDB), no server round-trip. AI extraction and fit analysis require an account; your local data migrates over if you decide to sign up later.
Automated Data Extraction
Paste JD → AI extraction. The system parses unstructured job descriptions into a structured schema, capturing role requirements, responsibilities, and metadata.
AI resume-fit analysis
Evaluates the extracted job requirements against your stored resume to generate a role/culture fit score, priority rating, and matched strengths vs. gaps.
Pipeline tracking
Pipeline tracking across application statuses with search/filter. A centralized dashboard visualizes application states across stages, keeping the job search organized.
Reminder emails
Timezone-aware scheduled follow-ups. Optional follow-up reminders can be toggled per application, ensuring you never miss a beat when waiting to hear back from recruiters.
System Architecture
Technologies
Next.jsSupabasePostgreSQLGemini APIcron-job.org
Engineering Decisions
01
Prompt-injection defense on AI routes
Input sanitization, delimiter isolation, low-confidence soft-rejection.
02
Defense-in-depth data scoping
RLS at the database layer + explicit server-side re-scoping on every API route.
03
Multi-model AI fallback chain
Multi-model AI fallback chain with persisted temporary blocking, so a single provider outage/rate-limit doesn't break extraction.