Hierarchical & structured reasoning
How can multi-level computation and intermediate representations help models solve problems that are difficult to handle in one pass?
COMPUTER SCIENCE STUDENT · BUILDER
Curious about
how machines
think.
I explore AI reasoning and build software that makes complex systems easier to understand, inspect, and evaluate.
FIELD NOTES / HS—01OPEN SYSTEMS
H
01 / STRUCTURE02 / COMPUTE03 / VERIFYQUESTIONS → EXPERIMENTS → SYSTEMS2026
↳
Long-term focus: building a clearer understanding of reasoning, computation, and intelligent systems.
AI REASONING✳MACHINE LEARNING✳AGENTIC SYSTEMS✳QUANTITATIVE SYSTEMS✳HPC & COMPUTATION✳AI REASONING✳MACHINE LEARNING✳AGENTIC SYSTEMS✳QUANTITATIVE SYSTEMS✳HPC & COMPUTATION
01 ABOUT
I learn by building.
I build to understand.
I'm a computer science student focused on understanding how intelligent systems reason, plan, and solve difficult problems. My primary long-term direction is AI reasoning research — especially hierarchical approaches, deliberate multi-step inference, and the role of computation at inference time.
Alongside that direction, I build software, visual learning environments, and tools for AI-assisted engineering. I treat projects as a way to strengthen fundamentals, test ideas, and make technical concepts easier to inspect. I care about reproducibility, clear scope, and precision about what an experiment actually demonstrates.
[ CURRENT APPROACH ]Understand the problem. Build the smallest useful system. Verify the result. Document the limits.
02 RESEARCH INTERESTS
Questions worth
working on.
These are areas I am learning about and exploring. They are research interests, not claims of completed results.
↗
System 2-inspired inference
When should a model pause, plan, search, or verify — and how should it decide how much additional computation to spend?
Reasoning evaluation
How do we measure correctness, robustness, consistency, and efficiency rather than reward answer length or convincing presentation?
Compute & efficiency
What trade-offs emerge among model size, inference cost, latency, memory, and reasoning quality?
HPC & scientific computing
How can parallel computation and shared compute infrastructure make experimentation more capable, efficient, and reproducible?
INDEPENDENT INITIATIVE↗
A RESEARCH & ENGINEERING DIRECTION
ReasoningAI
Research and tools for more reliable AI reasoning. An evolving body of work around structured computation, evaluation, reproducible research, and practical tooling.
Visit reasoningai.tech ↗03 SELECTED WORK
Built, tested,
and documented.
A selection across research tooling, machine learning, agent workflows, algorithms, markets, and systems. Open each repository for implementation details, current scope, tests, and limitations.
01 / RESEARCH TOOLINGRAI
ReasoningAI Studio
Evidence-first research toolkit for AI agents and human researchers: portable workflows, reusable prompts, and local Python utilities for transparent, reproducible research.
Repository ↗02 / MACHINE LEARNINGNN
Neural Networks Playground
Interactive lab for training small neural networks, inspecting activations and gradients, comparing optimisers, and connecting visual behaviour to the underlying mathematics.
Repository ↗Live demo ↗03 / AGENT WORKFLOWSAF
AgentFieldkit
Open-source field kit of 25 evidence-first workflows for software engineering, security, AI/ML research, and multi-agent collaboration.
Repository ↗04 / ALGORITHMSALG
Algorithm DSA Forge
Browser-based learning environment with 129 demonstrations across data structures, pathfinding, AI/ML, and reasoning, with step-by-step traces and editable inputs.
Repository ↗Live demo ↗05 / DEVELOPER SYSTEMSLC
LaunchCrew
Spec-first toolkit for Codex CLI with portable workflows, specialist agent profiles, and practical guardrails for planning, implementation, and verification.
Repository ↗06 / QUANTITATIVE RESEARCHMP
MarketPilot AI
Cross-model trading research toolkit with market scans, risk checks, scenario replay, walk-forward testing, and a local paper-only ledger. Human-led; no live order routing.
Repository ↗07 / SIMULATION WORKFLOWSKQ
KINETIQ
17 portable agent skills for interactive 3D machine explainers, mechanical simulation, physics validation, and offline delivery.
Repository ↗08 / PERSONAL PRODUCTIVITYSØ
StudyOS
Local-first study workspace for planning, syllabus tracking, focus sessions, active recall, revision, and progress reporting. No account or cloud sync.
Repository ↗Live demo ↗09 / AI CODING TOOLSCG
Claude Garage
Claude Code plugin with specialist agents, slash commands, and resumable workflows for planning, implementation, testing, and review.
Repository ↗Project site ↗10 / STUDENT SOFTWARECF
CampusFlow
Student-built attendance workflow prototype with time-limited QR check-ins, fictional demo records, SQLite persistence, and CSV reports. Not for official attendance.
Repository ↗Descriptions summarise the linked repositories; they are not independent audits. Consult each repository for current status, license, tests, and limitations.
MORE REPOSITORIES, EXPERIMENTS & SMALLER TOOLSBrowse all GitHub repositories ↗
04 TECHNICAL TOOLKIT
Tools are means.
Understanding is the goal.
A working toolkit across software development, machine learning, data, and experimentation. Proficiency varies by language and project; the repositories show the practical context.
Python · Java · C++ · JavaScript · SQL
PyTorch · TensorFlow · NumPy · Pandas · Matplotlib
Git · GitHub · Terminal · Slurm
Reasoning models · Agents · Quant systems · HPC
WORKING PRINCIPLESThink before coding.Keep the system simple.Verify the result.Be honest about evidence.
05 / CONTACT & COLLABORATION
Let's work on
good questions.
I'm interested in thoughtful discussions around AI reasoning, machine learning, model evaluation, agentic engineering, and open-source projects.