03 / 05EnginePrototypev1.1 · Active prototype

Decision Intelligence / Active Prototype

FORECAIRN

Governed decision intelligence for the NexCode system

The engine of the NexCode system: governed decision intelligence that keeps evidence, memory, live data, briefs, and approvals in one place, and checks its claims against what actually happened.

Web · FastAPI · Open contract

Useful intelligence needs more than a model response. Forecairn writes down what it believes as claims, each with a confidence and the condition that would prove it wrong, and scores them against what actually happened. Models reason inside it; the record is what counts.

Many modules,
one engine.

Forecairn now brings together 7 modules that used to be separate products: Revive for focus and work sessions, Summit for money decisions, always signed off by a person, NexOverlay for one schema for showing claims and scores, Orbit for the next useful move, as a proposal, Relay for handoffs between people, opt-in only, ShipLog for build decisions and milestones, and Keepsake for private memory that stays local by default. Their roles are set; module-specific features are still to come.

  • Revive
  • Summit
  • NexOverlay
  • Orbit
  • Relay
  • ShipLog
  • Keepsake

From live evidence to reviewed decisions.

Explore FIELD weather and radar, then sign in to organize projects, connect sources, and use the Intelligence Pilot.

Open Forecairn →

Observe reality.
Remember why.

Forecairn is the engine of the NexCode system. The v1 foundation is working as three connected prototypes over one Decision & Memory Library. Models are used for reasoning; NexCode owns the evidence, rules, workflows, approvals, and the record of what actually happened.

01 / LIVE PROTOTYPE

Decision Laboratory

Frames decisions, connects evidence, records approvals, and compares recommendations with outcomes.

Connected through shared evidence
02 / LIVE PROTOTYPE

FIELD Pilot

Registers governed sources and devices, checks collection health, and turns observations into reusable evidence.

Connected through shared evidence
03 / LIVE PROTOTYPE

Intelligence Pilot

Produces structured briefs, risks, and options while keeping assumptions and uncertainty visible.

Connected through shared evidence

Eight coordinated layers guide the platform beyond the current prototype.

01 / Forecairn

Reality Graph

Connect entities, events, evidence, decisions, and outcomes in a persistent world model.

Platform direction
02 / Forecairn

Causal Twin

Model bounded systems and the causal relationships that may shape their behavior.

Platform direction
03 / Forecairn

Branch Engine

Explore plausible paths while preserving assumptions, uncertainty, and constraints.

Platform direction
04 / Forecairn

Decision Genome

Record how a decision formed so its reasoning can be reviewed and improved.

Platform direction
05 / Forecairn

Proof of Reality

Preserve provenance and verification trails for observations and transformations.

Platform direction
06 / Forecairn

Confidence Exchange

Represent confidence transparently without converting uncertainty into false certainty.

Platform direction
07 / Forecairn

Intent Compiler

Translate human goals into structured, governable objectives and actions.

Platform direction
08 / Forecairn

Federated World Twins

Coordinate authorized models across systems without erasing ownership or boundaries.

Platform direction

Explore the Forecairn foundation on GitHub.

Review the architecture, prototype workspace, API, database migrations, tests, and project roadmap.

View repository ↗
Evidence before confidenceUncertainty stays visiblePeople remain accountableDefault local, opt-in sharing

Proof over
prediction.

If there’s no claim on record, nexAI says it doesn’t know yet instead of guessing. Models do the reasoning inside; the record is what counts.

01

nexAI proposes

nexAI drafts the answer or suggests a decision. It can propose; it can’t approve.

02

Forecairn records a claim

A view about what’s ahead is written down as a claim, with a confidence and the condition that would prove it wrong.

03

A person decides

Health, money, and public decisions need a human sign-off. Forecairn can also refuse.

04

Reality keeps score

When the outcome is known, Forecairn scores the claim against what actually happened, and that score informs the next one.

This is how the system is designed, and it’s being wired in now: the shared contract lives in the Forecairn API, and nexAI’s Forecairn-backed answers come in a later release. Until then, wherever this site calls a model directly, a question about what’s ahead gets an honest “I won’t guess” instead of an answer.

01

Target user

Operators, researchers, developers, and decision-makers working with changing real-world information where provenance, uncertainty, and consequences matter.

02

Core problem

Live signals, documents, model outputs, and human observations arrive through disconnected systems, making it difficult to preserve their context or turn them into accountable decisions.

03

Differentiator

One NexCode-owned record connects sources to evidence, memory, claims, approvals, and measured outcomes, while model providers stay replaceable. nexAI proposes; Forecairn records, scores, and can say no.

Small enough to learn.
Strong enough to keep.

  1. 01Forecairn Memory with projects, sources, conversations, memories, archives, and deletion controls
  2. 02Software Decision Laboratory for evidence-backed decisions and outcome review
  3. 03FIELD Pilot for governed connectors, observations, ingestion health, and live data
  4. 04Intelligence Pilot for structured briefs, risks, and recommended actions with assumptions visible
  5. 05Shared contract for events, evidence, claims, decisions, outcomes, and confidence, with a human sign-off for health, money, and public decisions

The loop behind
the interface.

RETENTION

nexAI proposes → Forecairn records a claim with a confidence and what would prove it wrong → a person decides where it matters → the outcome is recorded → the claim is scored and the next one starts from that record.

BUSINESS MODEL

Research-stage platform. Any future business model must preserve source transparency, data control, and a strict separation between trust signals and paid influence.

PUBLIC POSITION

An active NexCode prototype for transparent decision intelligence—not an autonomous authority, universal truth engine, or guarantee about future events.

Built as a system.

A practical architecture sized for the current stage and ready to evolve after real usage.

Evidence before expansion.

Timelines assume a focused solo or very small team.

01

Current

Connected foundation

Stabilize the shared memory, source registry, and three prototype workflows, and land the shared contract: claims, outcomes, and per-domain scoring in the Forecairn API.

02

Next

Hosted pilot

Deploy an authenticated API, managed database, scheduled collectors, and observability for a private cohort.

03

After hosting

Edge validation

Test authenticated device gateways, offline buffering, calibration, and safe field operations.

04

Evidence-led

Responsible expansion

Advance the Reality Graph and simulation stack only when measured pilot outcomes justify it.

Evidence and provenance completenessSource freshness and collection successRecommendation usefulnessHuman override and outcome captureClaims scored against outcomes, per domain

Next project

True Heading