ashrivastava
menu
// case study — jobjam← all projects

JobJam.io — AI Job Search & Application Platform

JobJam.io is a commercial AI-native platform for job seekers. It uses LLMs across the full search-to-apply lifecycle: discovering relevant roles, evaluating fit between a candidate and a job description, tailoring application materials per role, and surfacing skill gaps relative to a target position. Built on Next.js with TypeScript, Anthropic's Claude for the AI workflows, Supabase (EU) for data and auth, Stripe for payments, and Vercel for hosting. The pricing is deliberately one-time — aligned with how a job search actually plays out (a bursty effort over weeks or months) rather than a perpetual subscription.

Own product·ai·2026

Products I own and operate end to end — my roadmap, my users, my on-call.

// hero
JobJam.io — AI Job Search & Application Platform
// stack
frontend
Next.jsTypeScript
backend
Anthropic Claude API
database
Supabase (EU)
tools
StripeVercel
// challenges
  • Helping job seekers cut through hundreds of listings to surface the few worth actually applying to
  • Producing application materials tailored to each role without sliding into generic LLM output
  • Building a paid AI product in a market crowded with free subscription tools
// solutions
  • AI fit-evaluation that scores how well a candidate matches each role using their profile and the JD
  • Per-role application tailoring that drafts focused cover letters and resume points
  • Skill-gap analysis that names exactly what is missing relative to a target position
  • One-time pricing model that aligns with how a job search actually plays out
// outcomes — impact3

Live commercial product at jobjam.io

Full AI workflow across discovery, fit, tailoring, and skill-gap analysis

EU data hosting via Supabase for privacy

// related — other projects
Own productpinnedfeatured
ai2026

Fathohm — Comprehension-Debt System of Record

See how much of your codebase no human understands. A treemap of your repo colored by human comprehension score, with a tracked, assignable metric for 'who understands what' in an AI-native codebase.

AIDeveloper AnalyticsGitHub AppLLM Classification+2
Own productpinnedfeatured
ai2026

Grenz — Firewall for AI Agents

A local firewall for AI agents: scoped, revocable, observable permissions instead of your full GitHub token. Deny-by-default, MIT licensed, live at grenz.dev.

AI AgentsSecurityIAMMCP+2
Experimentalfeatured
ai2026

AI Workflow Builder

Chain LLM steps into a workflow with {{stepId.output}} substitution between steps. Pick a preset, edit any prompt, watch the chain execute step by step.

AI WorkflowsMulti-Step LLMPrompt ChainingAI Agents+1