What I'm working on.

Building

Rasphia — AI-native conversational commerce platform using RAG + multimodal models (OpenAI, Claude, Gemini) for cross-site product search and purchase. Currently expanding the product catalogue coverage and improving cross-site retrieval accuracy. Live at rasphia.com.

Seedhape + Sonar — Seedhape is an agentic-payments control plane with mandates, policy, x402 settlement, self-custodial wallet approval, and auditable records. Sonar is the independent reliability and routing layer for x402 agent commerce, measuring uptime, latency, price honesty, schemas, and evidence. Live at seedhape.com and sonar.seedhape.com.

Consulting

Taking on select consulting engagements with US-based service businesses and brands around AI discoverability, conversational commerce, and agentic payment architecture. The three core offerings are on the homepage.

If you have a specific bottleneck in mind, the fastest path is a short scoping call.

Thinking about

Agentic payment governance. The payment rails (x402, Stripe, Visa/Mastercard agent specs) are mostly solved. The open problem is permission models — spending envelopes, counterparty allowlists, audit trails. I wrote about this in a recent post.

LLM evaluation frameworks at production scale. Most eval setups I see are tested against synthetic data and break on real customer inputs within two weeks of deploy. I'm working on a lightweight harness design that holds up under distribution shift.

Verifiable compute + ML convergence. Running ML inside RISC-V environments (the work I did at Cartesi) is getting more tractable as toolchains mature. Worth watching whether this opens a path to auditable inference for regulated industries.

Reading

Anthropic's interpretability research — particularly the work on sparse autoencoders and feature geometry. The x402 protocol spec and the Visa/Mastercard agentic payment standards. Gwern's writing on forecasting and rationality, which I return to periodically.