Neural Intelligence Labs
Menu

Independent AI research · San Francisco + Chicago

Reinforcement learning environments for AI agents.

We build and study reinforcement learning environments for software, terminal, and web agents. Our research focuses on resettable tasks, observable state, trustworthy verification, and recovery from failure.

01 / Maker's portfolio

Apps and tools for everyday life.

Explore NeuralInt apps for Persian writing, focused work, family routines, and fashion discovery, alongside open-source tools.

Persian Ink app icon

Persian Ink

An offline Persian handwriting keyboard for iPad. Write Farsi with Apple Pencil, review recognition candidates, and insert text into Notes or another supported app.

Persian Swipe app icon

Persian Swipe

An offline Persian and Farsi swipe keyboard for iPhone and iPad, with tap typing, نیم‌فاصله, word suggestions, and learning from your corrections. No Full Access required.

Trailhead app icon

Trailhead: Deep Focus

A focus timer for iPhone that turns completed work sessions into a simulated national-park hike, with optional Screen Time distraction blocking, soundscapes, and Lock Screen Live Activities.

Lady app icon

Lady: Family Routines

A family routine and reminder app for parents. Write your own announcements, schedule iPhone reminders, and tap to play speech on a compatible Google, Nest, or Cast-enabled speaker.

LinkedFull app icon

LinkedFull

An AI fashion discovery app for iPhone. Search for clothing with a description or reference photo, explore products across stores, and preview styles with virtual try-on.

Koto wooden K logo

Koto

Alpha

An alpha workspace for coordinating coding agents with isolated Git worktrees, reviewed integration, and saved sessions.

Open Radio waveform logo

Open Radio

RadioDesk is an open-source workspace for amateur-radio station control, signal analysis, RF tools, and local logging.

02 / Research program

The environment is part of the intelligence.

Better agents require more than better policies. They need worlds with legible state, meaningful consequences, trustworthy feedback, and enough variation to learn skills that transfer.

01

Executable environments

Resettable, observable worlds for training and evaluating agents across repositories, terminals, and browser-based workflows.

02

Reward & verification

Testable outcome contracts, partial-credit signals, and adversarial checks that distinguish task completion from reward hacking.

03

Curriculum & transfer

Task generation and curricula that transfer skills from shell operations to software engineering and stateful web work.

Mehrdad Zaker

Founder & researcher

Mehrdad Zaker, Ph.D.

Reinforcement learning · Planning · Agent systems

Mehrdad is a computer scientist and founder of Neural Intelligence Labs. His work connects reinforcement learning, planning, and human-centered agent systems with the systems problems that make long-running AI work reliable in practice.

Build a better world for agents to learn in.

Open to research collaborations, benchmark partnerships, visiting talks, and working sessions in San Francisco + Chicago around agent environments and reliable AI systems.

Start a conversation