Home

WORKSPACE

Substrate signoff from geometry to evidence report

The primary buyer workflow chains TGV impedance, isolation, and yield screening into one design-to-yield call — with OOD state, solver-disagreement status, claim links, and pending external validation shown before report export.

DON'T TAKE OUR WORD FOR IT
A buyer verifies the compiled PDK with zero dependencies, and can make the verifier generate 26 forgeries of the object and reject every one …
this result and the rest, each with its receipt Receipt for this result: pdk-portable-verifier.json (sha256 07ebcdf814bc…)

Every result has a receipt behind it

Each result this platform claims is quoted from its receipt in the public results record, with the command that reproduces it and a check that catches a planted defect. Open the Evidence Room and check one.

Open the Evidence Room

Checked against solvers we do not own

The sign-off geometries are re-solved by independent electromagnetic engines, FastCap and Palace among them. Where they disagree with ours, the disagreement is stated, not averaged away.

How cross-solver works

Simulation, said plainly

Everything here is computed. No fabricated wafer measurement stands behind any of it, and the pages that could imply otherwise say so.

How a release is validated

Workflows

start anywhere

Glass Package Signoff

Impedance + isolation + yield

Geometry + material + target → impedance, OOD, inverse alternatives, isolation, yield, solver disagreement, evidence report, next validation step.

POST /v1/chiplet-suite/design-to-yield

PDK Playground

TGV + evidence trace

Explore substrate TGV impedance and inverse candidates, then escalate the design into the evidence-linked signoff workflow.

POST /v1/glass-package/signoff

ChipletOS Photonic Signoff (alpha)

Photonic IC primitives

Sister sub-brand to the chiplet glass-TGV PDK. Waveguide + ring alpha run locally through a closed-form analytical model; a trained surrogate for it is on the roadmap.

POST /v1/photonics/predict-waveguide-mode

Evidence Registry

Claim -> witness

Trace claim state, model cards, dataset provenance, witness JSON, and external validation blockers before using a result in a report.

GET /v1/evidence/claim/{claim_id}

Provenance Inspector

Audit-grade lineage

Paste any output and inspect the solver, dataset, validation, and pending-external chain behind each buyer-visible number.

GET /v1/provenance/lineage

EM Isolation

Isolation screening

Isolation and keepout screening with explicit caveats until external validation artifacts are attached to scoped claims.

POST /v1/isocompiler/reference-flow

Bondability

Yield screening

Bondability and yield-risk screening linked into the design-to-yield decision and evidence report.

GET /v1/bondability/calibration-slice

Lot Intelligence

Process context

Lot-level process signals remain available as companion context, not the first buyer-signoff surface.

POST /v1/lots/intelligence-report

Wafer Explorer

Companion analytics

Wafer-pattern analytics stay disclosed as separate workflow support, not glass-package external validation.

POST /v1/wafer/classify-pattern

Digital Twin Runner

Companion workflow

Multi-stage analysis stays behind the primary signoff workflow unless its outputs are linked to the current local evidence report.

POST /v1/twin/submit

Start here

Check us before you talk to us

The Evidence Room quotes every result this platform claims from its receipt in the public results record, with the command that reproduces it. It needs no account, and every receipt is a file you can download and hash yourself.

Open the Evidence Room
AGENT PLANE

Keep agents downstream of the registry

The genesis-glass-pdk FastMCP package can drive local APIs, but buyer-facing answers must cite claim registry, witness, model-card, and data-catalog IDs.

Install MCP

Operational envelope and disclosures

  • Evaluation workspace, not a released product.
  • Every result here is computed. We claim no fabricated through-glass-via measurement anywhere on this platform.
  • Comparisons against the literature are against values other people published, not against measurements we took.
  • The checks that guard a release are our own. No third-party audit of them has been commissioned.
  • Cadence, Ansys, Keysight, Synopsys, NVIDIA and every other company or tool named here are named only as formats and interfaces we read and write: ChipletOS has no commercial, partnership, supply, evaluation or endorsement relationship with their makers.
What state each figure on this page is in

This workspace binds no figure; figures and their receipts are on chipletos.com.

  1. LOADING none here; a figure read in the browser is listed here until its receipt is read.
  2. UNSEARCHED none here; a claim class nobody has searched for is listed here by name.
  3. SEARCHED_NONE_FOUND none here; a search that ran and found nothing is listed here with its scope and date.
  4. NO_DATA_AVAILABLE none here; a receipt that holds no value for its row is listed here.
  5. SEARCH_FAILED none here; a receipt that is not served, or does not hash to the registry, is listed here.
  6. UNRESOLVED_IDENTITY none here; two receipts about different objects offered as one figure are listed here.
  7. UNDERPOWERED none here; a figure whose sample is below the site minimum is listed here with its sample size.
  8. CONTRADICTORY none here; two receipts giving different values for one quantity are listed here, both shown.
  9. LICENSE_RESTRICTED none here; a receipt that cannot be published is listed here with its commitment.
  10. STALE none here; a receipt older than the freshness bound is listed here with its age.
  11. NOT_APPLICABLE none here; a claim class that does not apply to this page is listed here.
  12. ANALYSIS_FAILED none here; a generator that exited non-zero is listed here with its exit code.