🤓 Latest Submissions
Quantum Dot Live Twin
Semiconductor quantum dot labs read out device state via dispersive/RF measurements running far faster than the classification loops meant to track them. When a twin falls behind, drift goes unnoticed until fridge time is burned re-characterizing. This project builds a live digital twin that stays synchronized with a quantum dot device's changing state under exactly that pressure — a passive mirror, not a tuning/control system. Frames come from a real QArray-simulated device trajectory (Rust-backed for speed). Measured on a 2000-frame run on AMD MI300X (PyTorch/ROCm): serial CPU baseline hits 0.222s worst-case lag; GPU-batched inference cuts that to 0.020s, an ~11x reduction in worst-case staleness. A rule-based triage agent then holds that same 0.020s worst-case while cutting compute further — FULL 245 / CHEAP 51 / SKIP 0 tier decisions from real queue depth, staleness, and drift signals, a decision genuinely consumed by the control loop, not narrated after the fact. An LLM supervisor (Fireworks AI) is wired in to tune those triage thresholds in the background, reasoning over backlog trends without blocking the real-time hot path. It did not produce measurable threshold updates during our testing window, so the deployed system runs on the validated static thresholds above — flagged here rather than overclaimed. The same stream is also exposed as a real QCoDeS Instrument, so a lab's existing control stack could subscribe to it with no new integration work. Results ship in an interactive control console. Known limitations — synchronous micro-batching, untrained classifier weights — are documented, not hidden.
13 Jul 2026
SimQuantum: Agentic AI for Quantum Chips
Right now, somewhere in a quantum devices lab, a PhD student is spending hours cooling down a quantum chip, then carefully adjusting voltage knobs until exactly one electron sits in each tiny semiconductor pocket called a quantum dot. Miss the mark even slightly, and the whole setup fails. This painstaking process, known as device tuning, is one of the biggest hurdles to scaling quantum computers. SimQuantum fixes that. It explores a 2D voltage space using a 6-stage decision loop modeled as a POMDP, the same framework used in robotics when systems have to act without perfect information. At each step, it measures voltage, checks if the reading makes physical sense (Data Quality Control), classifies what it sees with a 5-model CNN ensemble trained on 51,000 simulated charge stability diagrams, updates a particle filter belief over possible charge states, and picks the next voltage move using Bayesian optimisation. A safety critic enforces strict voltage limits, and every choice is logged for audit purposes. On top of that, an LLM called Dr. Q (Qwen3-8B) serves as a live copilot in the interface. It sees the full agent state at all times: current stage, voltage position, CNN confidence, belief probability of the target state, and anomaly flags. Users can ask it anything in plain language, and it explains the agent’s actions, flags issues, and produces a summary at the end. The full stack was built on AMD MI300X via ROCm, with Qwen2.5-1.5B served via vLLM as the original inference target. The Streamlit demo runs on HuggingFace Spaces with Dr. Q connected via Fireworks AI (Qwen3-8B) as a portable fallback, pointing the sidebar URL back at an MI300X endpoint switches the backend instantly seamlessly. The agent is able to scan a large 2‑D voltage space (16 V²), automatically detect where a charge transition happens, and correctly label the charge state, all on it's own. Next goal, Navigation: getting the agent to move precisely to the target point on purpose.
10 May 2026
Infrastructure Investment Intelligence Agent
Our solution tackles a key challenge for telecom operators and infrastructure investors across the SADC region, where decisions about where to deploy connectivity infrastructure are hindered by sparse, outdated, or fragmented data. Traditional approaches rely on costly field surveys and incomplete reports, often leading to inefficient capital allocation and missed opportunities to reach underserved communities. We built an intelligent agent system powered by IBM watsonx Orchestrate that synthesises tower coverage data, settlement locations, and socioeconomic indicators to generate actionable investment insights. It brings together five tools: a readiness index ranking countries by investment potential, a coverage gap analyser detecting settlements beyond tower reach, a deployment cost estimator reflecting local logistics, a multi-country comparison tool, and a settlement prioritisation engine that uses geographic heuristics when demographic data is missing. A key strength of our approach is transparent data handling. Instead of hiding data gaps, the system uses proxy metrics such as settlement clustering, proximity to infrastructure, and strategic location to infer density and feasibility while clearly signalling confidence levels. Accessible via web and WhatsApp, the agent enables field teams to query coverage gaps, compare markets, and estimate deployment costs from anywhere, reducing reliance on specialised GIS staff. The solution supports mobile operators expanding rural coverage, development organisations targeting digital inclusion, and investors assessing SADC opportunities. By lowering the time and cost of analysis while improving decision quality, it accelerates connectivity deployment across Southern Africa and demonstrates the power of agentic AI in complex, data-limited environments.
23 Nov 2025
