Recent work, deeper cuts

Problem

Health insurance support teams drown in repetitive queries — agents waste time on FAQs while complex issues get delayed and customers never hear back reliably.

Approach

Built an AI agent (Claude Haiku 4.5) with a single `smart_search` tool that first hits a pgvector knowledge-base (with an LLM judge to verify ≥60% relevance), falls back to Tavily web search scoped to admin-approved domains, and escalates to a ticket flow that sends confirmation + resolution emails via Resend. Resolved tickets feed back into the KB.

Value

Customers get instant, accurate answers for known topics; complex issues are escalated with a full audit trail; every resolved ticket makes the system smarter over time.

Problem

Manual peer review is slow, inconsistent, and doesn't scale — reviewers apply different rubrics, miss key dimensions, and create bottlenecks.

Approach

Built a multi-agent pipeline with two sequential waves: Wave 1 runs Grammar, Novelty (with live Google Search), and Fact-Check agents concurrently; Wave 2 runs Consistency and Authenticity agents in parallel; a final Evaluator agent applies weighted scoring to produce a PASS/FAIL verdict.

Value

Structured, explainable peer-review reports in seconds — traceable per-dimension scores with rationale, not just a verdict.

Problem

Debugging across large codebases is slow — devs context-switch between docs, search, and code without a unified interface that understands the project.

Approach

Built a full MERN stack tool with an ingestion pipeline (POST /ingest) that indexes codebases into a vector store, a search layer (GET /search) with filters by username, project, and producer, and a RAG endpoint (POST /ai) that runs tool-call to vector search and returns an AI-generated answer.

Value

A project-aware debugging assistant that answers questions grounded in the actual codebase — not generic docs.

Problem

GenAI apps break when providers fail, outputs drift, and retries aren't standardized.

Approach

Designed a unified interface with routing, retries, and fallbacks built-in.

Value

Faster experimentation, less integration glue, and more reliable production behavior.

Problem

Handwritten prescriptions are hard to read and error-prone.

Approach

Used a vision-capable model with a web workflow for clean, readable output.

Value

Improves clarity and reduces errors for patients and pharmacies.

Problem

DNS visibility and updates were fragmented across tools.

Approach

Built a single dashboard with MERN and AWS SDK integrations.

Value

Gives teams a clear, centralized view of DNS state.

Problem

Needed a clean retail UI baseline.

Approach

Built a responsive landing page with Tailwind and React.

Value

Strong baseline for retail product presentation.

Problem

Needed model-driven insights from noisy real-world data.

Approach

Built pipelines and models for sentiment and stock prediction.

Value

Demonstrated end-to-end ML modeling and evaluation skills.

Problem

Explored event-driven UI and gameplay mechanics.

Approach

Built a lightweight game with vanilla JS and DOM updates.

Value

Showcases interaction design and performance on the web.

Problem

Language apps rely on tapping buttons and filling blanks — learners never actually speak, so they can't build real conversation skills.

Approach

Built a voice-first agent with Deepgram STT → GPT-4o tool dispatch → Cartesia TTS, running over LiveKit WebRTC. The agent switches between 5 modes (casual chat, structured lessons, quizzes, roleplay conversation, doubt resolution), semantically grades answers via LLM, persists sessions to Neon Postgres, and logs per-turn latency metrics.

Value

Learners practice real spoken conversation, not screen-tapping. Every turn feels like talking to a real tutor — and the system gets smarter about each learner's progress.

Problem

Agent workflows can feel like a black box when their usage, cost, and execution footprint are invisible.

Approach

Built a focused TypeScript project around the idea of receipts: legible artifacts that expose what an agent consumed while doing work.

Value

Gives teams a clearer mental model for agent usage and a foundation for more accountable AI systems.

Problem

Traditional slide decks are static even when the conversation around them is not.

Approach

Explored a TypeScript-first foundation for presentation content that can be more responsive and alive than a static deck.

Value

Turns presentation content into a more flexible product surface.

Problem

Useful agents need a dependable bridge into real tools and workflows, not a demo-only chat surface.

Approach

Built an exploration around that integration boundary: where agent decisions meet useful software actions.

Value

Strengthens the connective tissue between autonomous reasoning and product capabilities.

Problem

People often need candid, actionable feedback rather than more generic information.

Approach

Built an agent that interprets a learner's context, surfaces flaws, and turns critique into an immediate next step.

Value

Makes feedback more specific, confronting, and useful for deliberate improvement.

Problem

Underwriting workflows involve a lot of fragmented context and repeated judgment calls.

Approach

Explored an agent-led approach to organizing underwriting inputs and supporting more structured decisions.

Value

Demonstrates how agents can assist with operational, high-context business workflows.