For technical evaluators

The engine that discovers, and proves it decided well.

A complete discovery pipeline: generative design from a named target, structure prediction on every candidate, a fail-closed governance gate, a selection engine, and a decision record that survives an audit. Generation substrate is a commodity we deliberately license in rather than build.

The stack

We build the engine that discovers, and license everything upstream of it.

Generation has become a commodity and we treat it as one. What we build, protect and improve is generative design tuned to your target, structure-informed ranking, and the record that proves each decision was made safely.

L1

Generation substrate

Open protein language, structure and design models that produce candidate sequences.

Licensed in
L2

Generative design

Fine-tuned models that take your named target and produce a candidate library — trained on curated data for the target class in question. The layer that turns a target into candidates.

Developed internally
L3

Selection engine

Ranking and build-list construction across the governance-cleared pool, informed by Boltz-2 structure prediction and interface-confidence scoring on every candidate. Decides what is worth building.

Developed internally
L4

Governance

Biosafety gate, freedom-to-operate attribution and a tamper-evident decision record.

Patent pending
L5

Reporting

Interpretation and delivery of results in a form your scientists can act on.

Developed + licensed

The internal methods of the selection engine are held as trade secret and are not described here or in diligence materials. What we publish is what it does, not how it does it.

Generator-agnostic, by design

Designed molecules, and the decision of which ones to make.

A candidate is an amino acid sequence — a protein or a peptide. You order it as DNA, express it, and assay it. Every step after design costs real money, so the question we answer is which sequences are worth that spend.

What comes in

Candidate sequences, from any source

Designs from open models, from a generator you already use, or from ours. We are generator-agnostic by design, so nothing about working with us requires you to change how you make candidates.

What runs today

Proteins and peptides

  • Bacterial and vaccine antigens
  • Bacteriophage proteins
  • Enzymes and engineered proteins
  • Binders, antibodies and nanobodies

Nucleic acid enters on the screening side, because DNA is what actually gets synthesised.

Where it extends

Further along the ladder

  • Nucleic acid modalities
  • Viral vectors and capsids
  • Neoantigen and oncology applications

Named as roadmap, not as capability. We are precise about the difference.

Why the roadmap is credible

Our selection and governance layers do not know what a molecule is. They operate on candidate features, constraint signals and decisions — not on molecule class. That machinery carries to new modalities without redesign. What changes each time is the generation and feature layer beneath it, and we say plainly which ones are wired.

Watch it work

Design, fold, and engage a target — in about fifteen seconds.

Structure prediction isn't a side demo — it runs on every candidate in the pipeline, between generative design and selection. These schematic demonstrations walk through the sequence of events a real campaign passes through, compressed from a timescale no instrument can watch directly. Pick a demonstration and press run.

Sequence folds to structure

A designed amino acid sequence collapses into a three dimensional shape. Contacts form between residues far apart in the chain but close in space.

    Schematic — accelerated timescale

    These are schematic visualizations of the events a campaign passes through, rendered for clarity at a speed the underlying physics does not occur at. They are not real-time instrument output, and not structure predictions of specific candidates — for real Boltz-2 structure predictions, see Structures.

    The differentiator

    Every batch ships with proof, not assurances.

    Most discovery platforms treat sequence screening as internal compliance. We built it as the product — it runs before any candidate is eligible for selection, and every batch ships with a sealed, auditable record.

    Screening gate — illustrative run Running
    Evaluated 0 Cleared 0 Denied 0 Chain intact

    Illustrative reconstruction using synthetic identifiers. No customer sequence or result is shown.

    How the gate works

    United States policy is moving steadily toward requiring that AI-designed biological sequences be screened before synthesis, and that the screening be documented and auditable.

    • The gate fails closed

      A candidate is eligible only when every required signal returns an affirmative clearance. A missing signal, a timeout, an error or an incomplete record all produce a denial. There is no path through the gate that reaches approval by accident, and that property has been verified across each failure mode independently.

    • Screening runs on the open international standard

      We use the Common Mechanism, the open-source synthesis screening standard, running on infrastructure we operate with the full reference database set. We deliberately did not build a private screening method. Our contribution is the enforcement and the evidence around it, which is the part that has been missing.

    • Freedom-to-operate is attached before selection, not after

      Each candidate carries an attribution of what it derives from, and that attribution gates whether the candidate can advance at all. You find out that a candidate is encumbered before you build it, rather than during a licensing negotiation two years later.

    • The record can be checked by someone who does not trust us

      Decisions are sealed into a tamper-evident chain. A third party, a regulator, a partner or your compliance group can verify independently that the record has not been altered since it was written. Verification does not require access to our systems.

    The pipeline

    A defined campaign, measured against your baseline.

    We work in discrete campaigns against a named target. Every engagement is structured so that the result is established by measurement rather than assertion, and so that your team can audit how each decision was reached.

    01

    Target intake and baseline

    We scope the target, functional bar and control arm with your scientists — agreed before any work starts.

    02

    Generation

    Candidates come from open models, models tuned for your target class, or a generator you already use. We never lock you to ours.

    03

    Governed screening

    Every candidate passes the fail-closed biosafety gate and carries freedom-to-operate attribution before it is eligible for selection.

    04

    Selection and build list

    The selection engine ranks the cleared pool into one ordered, auditable build list sized to your lab capacity.

    05

    Measurement and iteration

    Results come back against your control arm, reported whether they favor us or not, and inform the next build list.

    More detail on each step
    • 01 — Target intake and baseline

      We scope the target, the functional bar and the control arm with your scientists. The comparison is agreed before any work starts, so the outcome is unambiguous to both sides.

    • 02 — Generation

      Candidates are generated from open foundation models, from models tuned for the target class, or from a generator you prefer to use. We are indifferent to the source and never lock you to ours.

    • 03 — Governed screening

      Every candidate passes the fail-closed biosafety gate and carries freedom-to-operate attribution before it is eligible for selection. Nothing reaches your build list without a sealed decision record.

    • 04 — Selection and build list

      The selection engine ranks the governance-cleared pool and produces one ordered, auditable build list sized to your lab capacity — regardless of which generator a candidate came from.

    • 05 — Measurement and iteration

      Results come back against the control arm you set at intake. That outcome informs the next build list, and the comparison is reported to you whether it favors us or not.

    What you receive with every batch

    A ranked build list sized to your lab capacity. A sealed, third-party-verifiable screening record for every candidate. Freedom-to-operate attribution on every sequence. And a measured comparison against your baseline — reported whether it favors us or not.

    Want the benchmark and diligence detail?

    Methodology, the fragmentation problem, and the third-party comparator data live on Evidence.

    Go to Evidence →