At Alsym, our mission is to provide safe, affordable energy for all — a billion-people purpose, and not merely a billion-dollar goal. Batteries are the path forward; however, today’s dominant chemistry – lithium-ion – poses inherent safety risks that make it unsuitable to serve as the solution at the scale the world needs. Therefore, we have set out to develop an innovative alternative.
Traditional battery development takes decades to advance from concept to commercial product. This delay is not due to the lack of effort, but rather the combinatorial space of possible chemistries is effectively infinite, and each experiment requires days to weeks to yield meaningful data. Sequential, manual experimentation cannot make meaningful progress in that space at the speed the market demands. It is no coincidence that the last major battery chemistry innovation, lithium-ion, took nearly two decades to transition from lab discovery to commercial viability, and that was 35 years ago.
In 2020, we began developing an alternative approach — one that leverages the speed and power of AI and computation, integrating them with real–world battery performance and data. The result is a physics-informed AI platform that compresses the development cycle down from more than a decade to just 12 to 18 months. This platform operates as a closed learning loop comprising four connected stages, all underpinned by deep, battery-specific domain expertise.
To unlock the awesome pattern-recognition capabilities of AI and ML, the system requires guidance. Physics is the key to making this process tractable. Quantum mechanical simulations, density functional theory, and molecular dynamics applied across multiple length scales eliminate candidates that are thermodynamically unstable, electrochemically incompatible, or mechanistically implausible. Furthermore, performance specifications, material availability, synthesis feasibility, and manufacturing costs serve as additional constraints, narrowing down the most viable options.
Through this rigorous filtering process, trillions of possibilities are distilled into thousands. This entire foundation of computation and simulation rests upon both publicly available electrochemical data and years of our proprietary data detailing molecular and electrochemical battery behavior.
Optimizing for a single best result tends to trap the search within a local maximum; conversely, optimizing for information gathering expands our understanding of the entire space and accelerates convergence towards the true overall optimum including successive iterations.
Autonomous Experimentation. Since batteries are physical products, no amount of simulation replaces real-world data. Our robotic systems run experiments around the clock under rigorously controlled, consistent conditions. Consistency matters just as much as speed: by eliminating human-to-human variability in cell assembly, electrolyte preparation, and testing, the signal in the resulting data is cleaner and more comparable across all candidates. As a result, fewer experiments are required to draw confident, actionable conclusions.
The key is to integrate both in-situ and ex-situ diagnostics to generate a complete picture, and then seamlessly feed that information back into the platform. These four processes form a tight, closed-loop learning system. Each experiment refines the next selection; each diagnostic output updates both the physics-guided filter and the AI’s understanding of the chemistry. Consequently, the platform becomes more intelligent with every iteration.
Alsym’s output is a product: a better battery. Product specifications are essential because they inform the questions we ask, the priorities we set, and the evaluations we make. We set out explicitly to develop a safe, affordable battery chemistry. Achieving a deployable, non-flammable, long-lasting, and low-cost solution was not a happy accident of our chemistry choices; it was achieved by deliberate design.
Our platform does not simply transfer results across scales; it transfers understanding. The electrochemical model built at the lab scale — identifying which processes are rate-limiting, which interfaces are most sensitive, and how the system responds to changes in conditions — serves as the foundational starting point for pilot-scale work and beyond, replacing the mere hope that initial lab data holds true. When results inevitably shift during the scaling process, the platform does not merely indicate that something went wrong at a new scale. Instead, it reveals which internal process changed, why it changed, and what to adjust. Deviations from expected behavior are diagnosable immediately rather than being treated as new unknowns, ensuring that solutions are found faster and are more actionable.
Ultimately, the platform’s advantage is not just speed and scale: it is interpretation. Every experiment yields sufficient signal so that fewer trials are required. Physics narrows the search before any cell is built; in-situ diagnostics close the learning loop during cycling; and domain expertise modulates every decision. Each cycle refines the next, and each failure informs the next candidate. Furthermore, each piece of organizational knowledge raises the baseline for future developments. This advantage compounds with every experiment run, establishing our approach as a uniquely durable innovation.
We are driven to provide affordable, safe energy to all. Time is the enemy, and our Physics-Informed AI platform for battery development is our strongest weapon to defeat it.