Own project
resume-tailor
Built a tool that tailors a LaTeX resume to a job description by reordering skills only. It can never add a skill that isn't true, and it reports gaps honestly.
- 73% coverage on a backend SDE JD
- 89% on an AI Engineer JD
What I do, 5 of 5
AI agents and internal tools
Tools your team uses every day, grounded in your own data, with sources, and honest about what they don't know.
The problem
- Knowledge stuck in a few people's heads.
- AI tools that make things up confidently.
- Repetitive work nobody has time to automate.
Try it
resume-tailor, one of my own tools. Switch the job post.
resume-tailor
89%coverage of what this job asks for
Moved to the top
LLMsRAGLangChainPythonVector search
Gap, not added
This job wants AWS. You don't list it, so it stays off your resume.
Download tailored PDF
Where I've done it
Own project
AI Code Reviewer (MCP)
Built an installable MCP server that reviews code diffs against a repository's own conventions, using RAG (AST chunking, on-device FastEmbed embeddings, Chroma) and a LangGraph review agent.
- 100% citation accuracy (5/5)
- 0 false positives across a 6-case eval suite
Jeevansathi, team project
Internal AI engineering assistant (team project)
Contributed to the team's internal AI engineering assistant. I built its live-production Debug/RCA tool (reads prod logs and cross-service traces, leads with evidence, never a verdict), one-command setup, conversational follow-ups and a plan-approval gate in its agent engine.
How I'd do it for you
Ground it
Retrieve from your own docs and code, and cite every answer.
Check itself
A critic step verifies sources exist before the answer reaches you.
Keep it safe
Read-only by default, with nothing leaving your systems that shouldn't.
Need this?
Tell me what you're working with. I'll tell you honestly whether it's worth doing and roughly what it takes.
Email me about this