dasobral

Build and replay controlled agent attack scenarios with measurable evidence.

Rewrite instructions with Agent STE, create agent definitions, and orchestrate multi-agent pipelines.

Assess repository control-plane trust and review MCP capability drift.

Rust AOS services with LiteLLM-compatible APIs and local LLM inference.

Professional career documents with audience-aware framing.

End-to-end code quality: analyze conventions, write conformant code, review quality, and audit cognitive debt.

Production C++ for QKD ground-segment systems: implement, build, and multi-lens review.

Inventory cryptography, review changes, and plan interoperable PQC migration.

Qualify entropy sources and determine when changes require requalification.

Capture reproducible runs and audit scientific and SciML claims against evidence.

Scientific computing platform design with right-sized infrastructure.