Model solve-and-check
Use solve-any or MCP solve_any for admitted source formats and checked compatible-engine selection.
UNISOLVE / DIRECT SPINFORGE SERVICES
Your model.
Our working brief.
Buy software access, commission a defined analysis, or request an operated deployment. SpinForge is the direct provider; the execution environment and acceptance contract come first.
Current source G: UNISOLVE 0.16.1, 82 profiles, 65 entry functions, 133 Python exports, 38 CLI operations and nine stdio MCP tools. All profiles were exercised through the installed-package campaign; optional declines and incomplete outcomes remain explicit. Current evidence ↗
NEW SCOPE TO QUALIFYOne product.
One product.
More useful workflows.
Latest supplied inventory capabilities extend the existing service scopes; they do not add mandatory fees or automatically grant hosted execution.
Planning and mathematical analysis
Qualify optional/variable scheduling, exact algebraic values, supported nonlinear/quantified reasoning or the guarded larger-tour path.
Incremental what-if work
Use LinearSession revisions and conditional bound transfer while retaining current-original certificates and explicit acceptance requirements.
FOUR SCOPED ENGAGEMENTS
Specify the work.
Know the delivery.
Proposed service scopes around documented UNISOLVE capabilities. Hosted availability, operating responsibilities and compute pricing require agreement.
Model solve-and-check
Execute a supported source model within an agreed budget and return the candidate, objective and applicable checks.
Inputs & acceptance
Inputs: Source format and admitted constructs; expected size; objective convention; deployment environment.
Acceptance: A truthful result state, original-model checks and agreed artifacts. No automatic promise of optimality.
Proof-required analysis
Attempt an admitted proof obligation with search, construction and independent-check budgets kept explicit.
Inputs & acceptance
Inputs: Original source; required theorem or result property; time and work budgets; requested proof format.
Acceptance: A supported independent proof that passes, or an explicitly incomplete outcome. A request is not a guarantee of completion.
Incremental what-if analysis
Evaluate supported model revisions and assumptions while retaining the effective query and its result identity.
Inputs & acceptance
Inputs: Base model; permitted mutations; assumptions; expected run cadence; retention requirements.
Acceptance: Revision-bound certificates and documented session semantics. No unsupported live-frontier claim.
Model integration and migration
Connect an existing customer workflow to a supported importer, execution path and original-source checking boundary.
Inputs & acceptance
Inputs: Current interface; source examples; deployment constraints; operating responsibilities; reference workflow.
Acceptance: A defined integration, correctness comparison, handover and explicit production rights.
PREPARE A SERVICE REQUEST
A better brief.
A clearer scope.
Choose the proposed delivery and desired evidence. This prepares a local inquiry; no file upload, model execution, payment or subscription activation occurs.
PREFER DIRECT SOFTWARE ACCESS?
Keep your
own environment.
UNISOLVE is one selectable engine in the monthly plans, subject to admitted models, the selected release and agreed capacity. Compatible UNISOLVE methods are included in an activated platform workflow. The retained 24-product annual Core Suite does not include UNISOLVE.
Developer $1,000/monthProduction $4,000/monthTeam $8,000/monthScale $12,000/month
Choose an eligible software scope CONNECTED WORKFLOWS
Solving is one entry point.
Source-bound checking, supported revision workflows and agent evaluations create additional ways to use UNISOLVE.
01
Independent result verification
Check a supported candidate or proof against the original model—even when another system produced the answer. Understand what passed, what failed and what remains unresolved.
02AI decision checks
Check an AI-generated configuration, allocation or plan against approved, explicitly modeled requirements before an authorized system acts.
03AI training & evaluation environments
Commission a task environment or evaluation suite in which supported mathematical and decision outcomes are checked by code, not judged only by the fluency of an explanation.
WHOLE-SYSTEM OPTIMIZATIONThe connection
The connection
can change the result.
Joint configuration, decision-sensitive computation, checked memory, useful future options, exact reformulation and evidence-led improvement. Explore the role of every product and agree a matched system evaluation.
Customer-specific integration opportunities—not added software entitlements or universal performance claims.