Physics-Aware AI for Mission-Critical Manufacturing

Validated across four chemistries · Six public benchmarks

Battery pilot, week 1.From cycler data to ranked risk in five working days.

Historian credentials to first prediction in five working days — AVEVA PI, Aspen InfoPlus.21, Siemens Opcenter, and Ignition connect out of the box. Validated on six public benchmarks across LFP, LCO, NMC, and Na-ion.

Built by Oxford and Tesla-trained AI & battery engineers. Advised by senior leaders from Google DeepMind, AWS Chronos, and the World Energy Council.

Factory Decision Console
Live · read-only

$1.26M

Daily value protected

17d earlier

Decision lead time

92%

Action acceptance

Active decision queueRevenue protected

NMC-0429

Early cycling anomaly

87%
$420K

NMC-5102

Impedance rise

79%
$310K

LFP-3812

Formation drift

63%
$180K

NMC-5102-D

Final-QA outlier

58%
$96K

LCO-2088

Telemetry mismatch

41%
$52K
12 approved3 in review1 escalated

Built for

Manufacturing EngineeringProcess EngineeringQuality EngineeringCell EngineeringProduction Leadership

The problem

Three problems we hear every time we talk to a plant team

Defect risk becomes expensive when plant teams can't turn scattered process, lot, equipment, and quality history into timely action.

By the time you see it, you've already lost the material

Formation and aging mean your quality signal arrives weeks after the upstream cause. Every event carries hidden committed cost.

Your data exists. It just doesn't talk to itself.

MES, historian, SPC, QMS, shift notes — the data is there. Getting it to line up around a specific defect event is the actual engineering problem.

Half the investigation is just finding the starting point.

Before your team can investigate, they have to reconstruct what happened across five systems. That's hours per event, every time.

Pilot motion

First signal in 5 days

Lychee scopes a tight first pilot — one line, one defect family, one KPI — so plant teams can evaluate fast.

0 days

From historian credentials to first prediction

Historian, MES, and lot context connected, validated, and surfacing risk on real lots.

0 weeks earlier

Than your current process catches them

Defects flagged from coating-and-drying signals before formation confirms — the gap where scrap and cycle time compound.

The record

We beat Amazon’s Chronos and the Nature Energy gold-standard benchmark

Independently validated on six public benchmarks across four chemistries — one hybrid model, no per-chemistry retuning.

8.9%

Median error · LFP

Beats the Nature Energy gold standard (9.1%)

30–150×

More accurate

vs Amazon’s Chronos foundation model

4.3%

Sodium-ion · first ever

First published Na-ion cycle-life result

The workflow panel

What plant teams see

A live operations view of the line: ranked-risk queue across lots and chemistries, drift-flag chart with confidence and lead-time, likely upstream drivers, and a recommended next step.

Lychee Labs logoLychee Labs
Live
Line A·LFP / Graphite·Operator: J. Walsh
Cycle 42 / 100

Capacity drift · LOT-0427

Flagged 3 weeks before formation confirms

Confidence

0.84

Detected

Cycle 30

Recommended

Quarantine LOT-0427 batch

Estimated value

€41k saved

Risk queue · 3 active

Updated 14:42

LOT-0427LFP

Formation outlier risk

High

0.91

LOT-0419LFP

Coating drift

Elevated

0.74

LOT-0398NMC

Drying variance

Monitor

0.53

Likely upstream drivers

Pump fluctuation

Slot-die line A2

0.81

Slurry viscosity shift

Mixer 03

0.74

Coating head imbalance

Line A · 14:32

0.63

Team and advisors from

Next step

Working on battery yield, scrap, or diagnosis speed?

Scope a manufacturing pilot

Start with one line, one defect family, and one KPI.

Scope A Pilot

Download 1-pager

Share the short overview with technical, manufacturing, or investment stakeholders.

Download 1-pager

Severson 2019 (Nature Energy) primary split: Lychee’s 8.9% median APE beats the published 9.1%. Chronos comparison and per-chemistry methodology reported transparently on /benchmarks.