Documentation & getting started

Make the workbench
your own.

Start with the scientific workflow. Add your AI provider, build a private enhancement stack and choose where to retain your research evidence.

Watch the narrated walkthrough

See the workflow

Step inside
the research workbench.

Follow the r34 SaaS workflow and examine how private layers can override equation implementations, with a recorded Bell study and retained equation-level test evidence. Use the chapters to find a step, or read the complete transcript.

Inside the research workbench5:35

Recorded r34 SaaS walkthrough · Narrated · English captions

Actual r34 interface and retained equation-override test evidence, with scripted AI responses and real numerical execution. Storage setup is shown.

Jump to a chapter

Choose a deployment path

Start where your research works.

See the workflow first: watch the narrated r34 SaaS demo .

Standalone

Run the PF application in your own environment. Install the dependencies for your selected scientific workflows, configure your AI credentials and open the local research workbench.

  • Control local execution and retained data
  • Use the supplied application launchers
  • Begin with a documented simulation preset
Read the core scientific manual

Hosted research workbench

Use an institution- or operator-managed PF deployment. Enable the AI assistant, configure approved provider access and choose managed storage or an optional personal destination.

  • User-scoped private enhancement stacks
  • Optional per-user BYOK and BYOS
  • Separate simulation workers and web access
Read the hosted storage guide

You need access to a PF Simulation application package or an existing hosted workbench. This public site provides documentation and examples; it does not run the research application in your browser.

Guides from the r34 package

From the first question
to the next private layer.

Select a guide to read it here. Each guide includes a table of contents, a formatted download and a print-friendly view.

AI Research Assistant

Evidence inspection, proposals, private source layers and numerical validation.

r34 workflow guide · Read guide

Bring Your Own Key

Personal API credentials, supported providers and credential handling.

r34 guide · Read guide

Bring Your Own Storage

S3-compatible storage, NAS connector, migrations and recovery.

r34 guide · Read guide

Continuation & attachments

Continue intact investigations, remove attachments and retry cleanup.

Corrected r34 guide · Read guide

Portable numerical relativity

Vacuum BSSN, gauge waves, convergence and the solver’s bounded scope.

Scientific method guide · Read guide

Quantum benchmarks

Protocol, component and channel models with declared assumptions.

Scientific workflow guide · Read guide

Numerical spacetime workflows

Connect numerical fields to mission and photon-link studies.

Scientific workflow guide · Read guide

Scientific integrations

Companion studies, dependencies and lineage contracts.

Integration guide · Read guide

Satellite tracking model

Current-UTC predictions, coordinate conventions, data validity and replay.

Tracking contract · Read guide

Orbit & quantum comparisons

Matched-state orbit branches and physical scenario comparisons.

Workflow guide · Read guide

Open quantum systems & tomography

QuTiP dynamics, Qiskit Experiments and explicit state/count contracts.

Research guide · Read guide

Recorded detector events

Integer-picosecond CSV replay and optional Swabian recording decoder.

Recorded-data guide · Read guide

Engineering integrations

Pinned FMU and bounded licensed MATLAB / Simulink models.

Runtime guide · Read guide

r34 integration audit

Implementation-backed capabilities, requirements and research value.

Website enhancement audit · Read guide

Connected research examples

Choose a question.
Inspect a complete study.

Start with the integration catalogue to understand applicability and required runtimes. Use the new satellite and Aer Gallery bundles to inspect saved inputs, numerical outputs and exact reproduction steps.

The website enhancement review is separate from the release validation below. Read the new validation scope

Core scientific reference

The wider workbench.

The 223-page core scientific manual covers established workflows, configuration, interpretation and reports. Its edition predates the r34 AI, BYOK and BYOS additions; use the current guides above for those features.

Core manual edition 1.17.0 · r26 · 20 September 2026

Corrected r34 release

Validation, with its scope visible.

1,806regression tests
454successful subtests
252interface checks
25numerical lifecycles

All planned checks in the retained corrected-r34 continuation, BYOK and BYOS validation passed with no failures, errors or skips. The final package passed fresh-extraction verification, and 117 audited scientific and supporting files matched the original r34 baseline.

Provider responses were scripted and storage endpoints controlled. Numerical calculations ran in real local subprocesses. This validates the covered application workflows; it does not establish live model accuracy, production load capacity, customer cloud behavior or experimental physics claims.

Read the complete validation report