Human Side
AI should help people think, recover, and move forward without forcing them to become system operators.
Frontier AI Systems · Sanshar Swarm · Multimodal Agents
Harihar Thapa
I am building Sanshar as a personal frontier-AI prototype: a way to connect models, interfaces, infrastructure, human workflows, and proof loops. The work explores how AI systems can become more useful, more grounded, and more honest as they move into real life.
H-1B
AWS Support Engineer
Plano, TX
Why Sanshar
I want AI to become useful in real life, not only impressive in a window
My motivation is simple: frontier AI is changing how people learn, work, create, and make decisions. I am building Sanshar to understand what has to exist around the model for that change to be trustworthy: event surfaces, memory boundaries, permission gates, proof loops, human correction, multimodal context, and small actions that actually close.
Systems Side
Useful autonomy needs infrastructure: events, routing, evals, logs, permissions, and verification.
Safety Side
The system must know when to act, when to ask, what not to store, and what it cannot honestly claim.
Builder Side
I learn by making the loop real: deploy it, watch where it fails, and turn failures into better design.
What I Bring
I combine cloud operations, network debugging, teaching, frontend prototypes, and hands-on AI systems work. My work is strongest where systems need to be useful in the real world: observable, rate-limited, reversible, and grounded in source evidence.
- Capability
- AI workflows designed around real human work, learning, and decision support.
- AI Systems
- Agent orchestration, event gateways, source packets, evaluation, verifier loops.
- Product Sense
- Rapid prototypes shaped around a real user, not a demo script.
Selected Work
Private artifact
Request access to the sanitized Sanshar repo
Sanshar prototype
How the project explores human-AI product loops
Proof discipline
Source packets, read-back, postproof, retickets
Secure deploy
TLS, rate limits, DNS, AWS relay operations
Sanshar Swarm
A prototype multi-agent systems testbed where specialized peers coordinate through event streams, local machines, Discord surfaces, and proof artifacts. The work focuses on making agents useful under real operating constraints: rate limits, memory pressure, stale context, private surfaces, and human correction.
- Manager-Agent-Verifier packets with expected metrics, observed metrics, source refs, and postproof.
- Event-driven Discord Gateway capture with cursor state, read-back, and reaction proof semantics.
- Request-gated sanitized repo showing schemas, dynamic decision records, and safety boundaries.
Dynamic Attention and Zoom Policy
A runtime policy layer for deciding when an AI system should observe, probe, summarize, ask, act, escalate, or hold. The policy replaces static behavior with measured runtime choices across language, surface, modality, risk, privacy, model, verifier, and autonomy.
- Expected-vs-observed metrics before and after action.
- Reason codes for pass, partial, blocked, timeout, false positive, and false negative.
- Replay-oriented handling for missed expectations, stale context, and noisy surface signals.
Medha Labs Chess and Vision AI
Product prototypes for model-assisted chess reasoning, board-state validation, visual context, and tutoring workflows. This work shaped the Sanshar pattern of combining model suggestions with deterministic validators, replay, and confidence scoring.
- LLM coach and judge loops wrapped around valid game state.
- Vision and attachment handling treated as first-class source packets.
- Customer-facing learning flows, not only backend experiments.
Experience
AWS Support Engineer, Networking and Security
VPC, Route 53, WAF, Shield, and Network Firewall support across customer troubleshooting, packet-level reasoning, and production constraints.
Self-Directed AI Systems Development
Personal frontier-AI prototypes including Sanshar Swarm, dynamic attention and zoom policy, multimodal surfaces, chess and vision AI, and proof-first agent workflows.
Network Administrator, Montrose Hospital
Hands-on hospital network operations in Colorado, balancing reliability, security, and user-facing urgency.
Teaching Assistant, Network Labs, and Builder
University of New Haven teaching support in networking and systems labs, applied networking practice, and early systems-building projects.
Contact
Open to frontier AI systems, applied AI, human-AI capability, infrastructure, and agentic tooling roles.
Local counter is loading.