Reasoning, test-time learning, verified autonomy. I build agents that can prove what they did.
Research: ASSAY · ARG · Sensi.
Production: EVON & GRID as CTO @ evolutionID.
15+ years shipping production AI - agent runtimes, grammar-constrained decoding, neuro-symbolic agents, distributed systems. Trained through Iran's exceptional-talents system.
The research work is ASSAY, a general agent harness: the agent is never told what its actions do - it discovers its tools by prediction, declares its own instruments, plans its own subgoals, and every run lands on a hash-chained record anyone can re-verify. First performance benchmark: ARC-AGI-3, 96.54 RHAE under hard action caps. Third architecture in this research line: Sensi, then ARG (a null result, on arXiv), then ASSAY.
The production work is at evolutionID, where I'm CTO, architecting EVON - a multi-harness, multi-provider, sandboxed agent runtime in production. The thesis: the session, not the harness, is the canonical compliance and evaluation unit.
Inventor of GRID (Grammar-Railed Decoding, EP 4687028) - deployed in production coding agents.
Co-founded and led two AI companies as CTO. Three granted patents (EPO, USPTO) and two further applications.
Specializations: Reasoning & Agents • Test-Time Learning • Evaluation Integrity • Agent Infrastructure • Access Control for LLMs.
Directed a research roadmap yielding 6 peer-reviewed publications (LREC, SPIE) that directly translated into enterprise product capabilities. Spearheaded the creation of MirasText, the largest automatically generated Persian corpus, to unlock high-accuracy, at-scale Sentiment Analysis, NER, and Topic Modeling for unstructured social streams. Continuously drove platform innovation by deploying Active Learning to slash annotation costs, engineering graph-based algorithms for trend extraction in noisy data, and developing multimodal audio systems (MirasVoice, Acoustic Fingerprinting).
Applications, tools and platforms I build to help knowledge workers