Shipped production LLM and agentic features across Convert and Instantly: an MCP (Model Context Protocol) server exposing Convert's experimentation platform to LLM clients as tools, an AI email editor at Instantly that detects spam-trigger language in real time, and a natural-language lead search that replaces rigid filter UIs with semantic retrieval.

Brought agentic workflows to an enterprise experimentation platform via Anthropic's open MCP standard. At Instantly, directly improved outbound inbox deliverability and let users find leads by describing an ideal customer profile in plain English.

Delivering core internal applications used across marketing and operations, including a schematics platform enabling teams to create and manage complex diagrams for trucks, oil refineries, plastic manufacturing plants, inside-out protection systems, tugboats and more.

Own architecture and feature delivery end-to-end, from system design to deployment, ensuring scalability, clean abstractions and long-term maintainability. Used across global marketing operations.

Delivered Multi-Arm Bandit (MAB) features and contributed significantly to the Visual Editor, improving experimentation performance, usability and customer experience at Convert.com.

Enhanced experimentation platform capabilities, maintained backend systems ensuring schema integrity, and raised engineering quality through clean-code practices and proactive technical debt management.

Built a global error boundary system that captured app-wide failures and delivered bulk tagging across campaigns, accounts and emails at Instantly.

Sharply reduced user frustration and support ticket volume. Major productivity improvement for high-volume users. Enhanced codebase structure, stability and API reliability.

Led a full front-end redesign, implementing a modern design system and upgrading the CI/CD pipeline to Heroku at Pocketnote.

Improved overall UX consistency and performance. Reduced deployment friction and lowered operational cost. Delivered features across React and Node.js, improving stability, speed and maintainability.

Migrated the front-end from Vue.js to React.js at Cobija Industries, improving maintainability and performance.

Improved UI responsiveness and optimized backend interactions. Led a remote team of developers, providing technical direction and code reviews. Delivered stable, well-tested features.

Most MCP servers ship demo-grade: no per-tool auth policies, no write confirmation gates, no audit trail, and no PII redaction on tool results. Those are exactly the gaps that show up the moment you expose a production SaaS to LLM clients.

Published Express-style middleware for MCP servers: glob policies (allow / deny / requireConfirmation), token-bucket rate limits, JSONL audit logs with hashed args, and result redaction. Wrap an existing server in a handful of lines.

RAG pipelines usually ship on vibes: swap an embedder, glance at a chat demo, and miss retrieval regressions until users ask for a product code the vector index never hits.

Shipped a CLI + library that evaluates any pipeline against YAML golden questions: hit-rate@k, MRR, answer-contains, LLM-as-judge faithfulness, latency percentiles, and CI gates that fail on regressions.

React Error Boundaries catch render crashes; streaming LLM UIs fail differently: stalls, mid-stream drops, and tool-call errors that would otherwise wipe partial tokens the user already saw.

Published a headless React library with useGuardedStream and StreamBoundary: typed stream failure classes, partial-preserving fallbacks, exponential retry, and optional resume-from-checkpoint.

In production React apps, a single render error can take down the whole surface. Teams often rely on one generic boundary or none at all, and native boundaries never catch async failures, so users see a white screen and you lose usable error signal.

Published a layered pattern (global, route, and feature boundaries) with async-to-boundary bridging, error classification, recovery hooks, and pluggable reporters (including Sentry) so crashes stay contained, recoverable, and visible in observability tools.

LLM products accept arbitrary user text; without a gate, prompt injection, jailbreaks, and data-exfiltration phrases can reach the model and override instructions or leak context. Naive blocklists create false positives and miss obfuscated payloads.

Shipped a zero-dependency, TypeScript-first guard with weighted scoring across dozens of rules, verify/strip/analyze APIs, Express and Next.js middleware, a React hook for chat UIs, and an optional Claude adapter for a second verification pass before tokens hit your provider.

Tool-first design, auth for LLM clients, idempotent writes, and the schema/prompt failures that show up once MCP hits production.

The safety ladder from read-only to scoped autonomous writes, RBAC, audit trails, confirmation tokens, and a near-miss that forced the design.

Chunking for datasheets vs prose, hybrid search for product codes, golden-question eval before you touch a vector store, and extension latency budgets.

Cost, latency, and quality from a real ingestion pipeline, plus a confidence-gated routing pattern between edge models and frontier APIs.

A deep dive into architecting production-grade error boundaries that capture 99.8% of failures, refreshed for streaming LLM UIs.

How proper architectural decisions early on can 3x developer velocity and prevent technical debt.