Question 1

What does Scale Prognostics actually predict?

Accepted Answer

Capacity retention vs. cycle number for silicon-graphite lithium-ion cells, plus per-cycle decomposition into degradation mechanisms (LLI, LAM-Si, LAM-Gr, transport-driven failure). The engine simulates 1,000 cycles in ~30 ms.

Question 2

How accurate is the model?

Accepted Answer

Calibrated against 8 published silicon-anode datasets — 6 at A+ (RMSE 0.13–0.32 percentage points) and 2 at A on knee-prone cells (RMSE 1.01–1.23 pp). Mean RMSE 0.44 pp. Held-out forward-prediction RMSE on knee-prone cells is materially higher (mean 11.86 pp at 70% retention cutoff) and is the focus of ongoing architecture-sprint work; see /methodology for the full breakdown. Validation spans 2.5–20% silicon, 0.5C to 2C charge rates, and 25°C to 45°C temperatures.

Question 3

How does this compare to PyBaMM or running my own model?

Accepted Answer

PyBaMM solves full PDE (Doyle-Fuller-Newman) systems — rigorous but ~1000x slower and requires extensive parameterization. Our engine runs 1,000 cycles in ~30ms with 7 coupled aging mechanisms, built-in uncertainty quantification, and auto-calibration. Use PyBaMM for voltage-level predictions; use us for lifetime predictions at scale.

Question 4

What chemistries are supported?

Accepted Answer

Silicon-graphite anodes with NMC cathodes, with silicon content from 2.5% up to 20%. Pure-graphite cells work but the competitive advantage is highest for silicon-containing cells. LFP cathode support is on the roadmap.

Question 5

What does it cost?

Accepted Answer

Free trial: 50 simulations/month, no credit card. Starter: $499/month for 2,500 simulations. Professional: $1,499/month for 10,000. Enterprise pricing on request.

Standard	Status	Notes
GDPR (EU)	DPA published	Data Processing Agreement at /dpa includes 72-hour breach notification, customer data isolation, no secondary use.
DFARS 252.204-7012	Partial	DPA breach-notification clause meets the 72-hour requirement. Other DFARS controls (CDI handling, NIST 800-171 mapping) on the roadmap.
NIST SP 800-171	Roadmap	Not yet mapped. Planning a formal gap assessment in 2026 if customer demand confirms.
SOC 2 Type 1	Roadmap (Q4 2026)	Auditor selection pending. Not yet held.
SOC 2 Type 2	Roadmap (post-Type-1)	Requires 6-12 months of audited operations after Type 1.
ISO 27001	Not yet	Not on near-term roadmap; will reassess if customer demand justifies.
HIPAA	Out of scope	Battery cycling data is not PHI. We do not process protected health information.
ITAR / EAR	Out of scope	The engine is published software. We do not handle ITAR-controlled data; customer is responsible for not submitting ITAR-controlled cell data via the API.
CMMC	Not yet	Defense buyers should engage Enterprise tier for CMMC alignment discussion.
FedRAMP	Not yet	Hosting on Railway (not a FedRAMP-authorized substrate). On-prem deployment available at Enterprise tier for buyers requiring FedRAMP-equivalent isolation.
TLS 1.2+ in transit	Yes	All API traffic encrypted. Verified by curl/openssl on the production endpoint.
Customer data isolation	Yes	No pooling, no cross-customer training, no secondary use. Documented in /dpa §3.
In-memory processing	Yes	Simulation inputs not persisted after response. /dpa §4.
Customer data deletion	Yes	Within 90 days of contract termination. Immediate on request. /dpa §10.

Compliance Posture

For defense buyers

For OEM buyers

What honesty costs us, and why we still publish this