Skip to content
NewMS Lattice found both sealed targets blind, in 32 minutes, for under 20 cents.See the proof →
Advancing Bits to Master Atoms

Four modes.
One engine, four kinds of question.

Open Discovery, Prototype-Guided Optimization, Guided Rediscovery and the Blind Rediscovery Benchmark run on the same engine, in every domain. Choose by what you already have.

A central faceted hub of satin silver and cobalt-blue spheres with four clean titanium tracks leading to an open dot grid, a refined crystal, a unit-cell frame and a sealed matte charcoal cube.A central faceted hub of satin silver and cobalt-blue spheres with four clean titanium tracks leading to an open dot grid, a refined crystal, a unit-cell frame and a sealed matte charcoal cube.

Which mode fits.

Start from what you already have.

An ordered crystal of matte graphite, satin silver and cobalt-blue spheres assembling cleanly along geometric axes as outer spheres step into place.An ordered crystal of matte graphite, satin silver and cobalt-blue spheres assembling cleanly along geometric axes as outer spheres step into place.

Open Discovery

You have a target, not a starting structure.

What the engine sees
Your target, nothing more
You give it
A domain, a goal preset or your own targets, and a budget.
It does
It searches the whole composition space.
You get
A ranked, diverse set of candidates, each with its record.
Best for
New materials, from the target alone.
For example
A machining coating from three numbers: 28 GPa, 800 °C and $30 a kilo. (Ti,Al)N and (Cr,Al)N, the coatings the industry runs on today, landed in the top five.
One prototype crystal of matte graphite and satin silver spheres branching cleanly to three variant crystals with cobalt-blue site substitutions.One prototype crystal of matte graphite and satin silver spheres branching cleanly to three variant crystals with cobalt-blue site substitutions.

Prototype-Guided Optimization

You have a good material. Make it better.

What the engine sees
Your target and your structure
You give it
A starting structure and what to improve.
It does
It searches around your structure and tracks every variant against the original.
You get
Variants ranked against your prototype.
Best for
Taking the material you use today further.
For example
Today’s automotive magnet, searched for variants that hold their strength at motor temperature.
A brushed-titanium unit-cell frame at the center being populated along orthogonal axes by orderly rows of matte graphite, satin silver and cobalt-blue spheres.A brushed-titanium unit-cell frame at the center being populated along orthogonal axes by orderly rows of matte graphite, satin silver and cobalt-blue spheres.

Guided Rediscovery

Point it at a known material. Watch it arrive.

What the engine sees
The known targets, as guides
You give it
Known target structures.
It does
It lets the targets guide the search and scores how closely every candidate reaches them.
You get
A match level for every target.
Best for
14 of 14 candidates on target in about three minutes, the closest within 0.0008 Å.
For example
Zirconium diboride: 14 of 14 candidates on target in about three minutes, the closest within 0.0008 Å.
A sealed matte charcoal cube on the left beside an uncovered crystal lattice of identical dimensions built from matte graphite, satin silver and cobalt-blue spheres on the right.A sealed matte charcoal cube on the left beside an uncovered crystal lattice of identical dimensions built from matte graphite, satin silver and cobalt-blue spheres on the right.

Blind Rediscovery Benchmark

Seal the answer. See if it comes back.

What the engine sees
None of the targets, until the freeze
You give it
Sealed targets, hidden from the engine while it searches and ranks.
It does
It searches without the answers, freezes the candidates, then reveals the targets and scores the match.
You get
A graded verdict for every target.
Best for
Both sealed ceramics found, down to the arrangement of their atoms.
For example
Two sealed ultra-high-temperature ceramics: both found among 64 candidates, in 32 minutes, for under 20 cents.

Stop guessing which crystal to make. Ask for it.

Tell us the domain and what the material must do. License MS Lattice for your team, or let Norck take the discovery all the way to finished parts.