> ## Documentation Index
> Fetch the complete documentation index at: https://docs.reilabs.org/llms.txt
> Use this file to discover all available pages before exploring further.

# Building with Core

> Ways to connect Core to products, tools, and applications.

Core can be used across products, tools, and applications. The surrounding application or integration decides how information enters, how results are used, and what actions follow.

The examples below illustrate common ways to connect Core. They are not limits on what Core or Adapt-1 can support.

## The application boundary

<div className="my-8" role="group" aria-label="Application boundary diagram" aria-describedby="application-boundary-caption">
  <div className="grid gap-2 md:grid-cols-5 md:items-stretch">
    <div className="rounded-lg border border-zinc-200 bg-zinc-50 p-4 dark:border-zinc-800 dark:bg-zinc-900">
      <div className="text-xs font-semibold uppercase tracking-wider text-zinc-500 dark:text-zinc-400">Input boundary</div>
      <div className="mt-2 text-base font-semibold text-zinc-950 dark:text-zinc-50">External systems</div>
      <div className="mt-1 text-sm leading-6 text-zinc-600 dark:text-zinc-400">Records, sensors, parsed content, events, or interactions supplied through the chosen interface</div>
    </div>

    <div className="flex rotate-90 items-center justify-center py-1 text-lg text-zinc-400 dark:text-zinc-600 md:rotate-0" aria-hidden="true">→</div>

    <div className="rounded-lg border border-teal-300 bg-teal-50 p-4 dark:border-teal-700 dark:bg-teal-950">
      <div className="text-xs font-semibold uppercase tracking-wider text-teal-700 dark:text-teal-300">Reasoning substrate</div>
      <div className="mt-2 text-base font-semibold text-zinc-950 dark:text-zinc-50">Core</div>
      <div className="mt-1 text-sm leading-6 text-zinc-700 dark:text-zinc-300">The continuing instance forms and revises task-relevant structure</div>
    </div>

    <div className="flex rotate-90 items-center justify-center py-1 text-lg text-zinc-400 dark:text-zinc-600 md:rotate-0" aria-hidden="true">→</div>

    <div className="rounded-lg border border-zinc-200 bg-zinc-50 p-4 dark:border-zinc-800 dark:bg-zinc-900">
      <div className="text-xs font-semibold uppercase tracking-wider text-zinc-500 dark:text-zinc-400">Result boundary</div>
      <div className="mt-2 text-base font-semibold text-zinc-950 dark:text-zinc-50">Application</div>
      <div className="mt-1 text-sm leading-6 text-zinc-600 dark:text-zinc-400">Inspect, validate, display, route, or execute the current result and its supporting evidence</div>
    </div>
  </div>

  <div id="application-boundary-caption" className="mt-3 text-sm leading-6 text-zinc-500 dark:text-zinc-400">
    This is the application contract around Core, not an ordering of Core's internal processes. Supported workflows can return structured outcome feedback through the same declared boundary, while application-side validation and outcome measurement remain outside Core.
  </div>
</div>

Applications can supply input directly through the selected interface. When a source format differs from a route's request contract, an optional adapter can translate the boundary format; it should not contain the task solution. Core has no native visual component. A detector or visual encoder is an upstream observation source, not part of Core.

A fair adapter may expose literal or deterministic facts: coordinates, colors, tracked components, available operations, exact deltas, or public action meanings. It should not label the current goal, choose the action, or encode the episode's hidden mapping. Record the adapter as part of the system being evaluated.

## Recurring application patterns

| Pattern                      | What must persist                                                      | Typical Core-facing result                      |
| ---------------------------- | ---------------------------------------------------------------------- | ----------------------------------------------- |
| Hidden-state monitoring      | Object identity, recurrence, activation, and uncertainty               | Structured current-state prediction             |
| Domain reasoning             | Entities, relations, hypotheses, rules, and missing evidence           | Ranked hypotheses and evidence packet           |
| Outcome adaptation           | Which relation or policy worked under which conditions                 | Updated scoped preference or policy score       |
| Long-running personalization | Constraints, corrections, durable preferences, and fading weak signals | Context and structured reasoning for later work |

These are application patterns, not product boundaries. A single deployment can combine them.

## Domain contract

In Adapt-1, a domain declares the stable grammar of a task: object and relation types, signals, event and native outcome semantics, action or plan interfaces, candidate hypotheses, rules, and the expected result shape.

It does not contain the current episode's hidden mapping, target coordinates, correct procedure, or solution path. Structure still has to form from the observations and outcomes presented during operation. This lets a fresh domain begin without accumulated task history while keeping public interface semantics separate from the answer.

For action-producing tasks, preserve `state -> committed decision -> exact action -> transition -> native outcome` as an observed trace. Scoped feedback can assign credit to the intended relation/policy; a reusable causal mechanism remains a stronger claim that requires later predictive evidence.

## State revision

| Early state                              | Revision                                | Later work begins with                 |
| ---------------------------------------- | --------------------------------------- | -------------------------------------- |
| Candidate structure has partial support  | Repeated evidence strengthens it        | The supported structure remains active |
| Several interpretations remain plausible | Their associations stay active together | Multiple alternatives remain available |
| A weak signal is present                 | Weak support loses influence            | The signal has reduced weight          |

Several interpretations can compete until the current result settles provisionally; later observations then meet an already changed state.

<Warning>
  Persistent state can also preserve incorrect structure. Use isolation, reset controls, ordered event handling, evidence review, and explicit feedback when operating stateful workflows.
</Warning>

## Structured outputs

Depending on the domain and gateway, an application can consume:

* state estimates and structured predictions;
* ranked hypotheses, policies, assignments, or other domain-shaped results;
* evidence, conflicts, missing information, and confidence;
* inspectable state changes for later review.

Natural language can be added after that result exists. Rei Chat demonstrates the articulation boundary; Adapt-1 exposes the structured contract directly.

## Interfaces

<CardGroup cols={2}>
  <Card title="Adapt-1" href="/docs/neuroadapt/overview">
    Direct access to Core for stateful reasoning, adaptive behavior, evidence, and machine-actionable outputs.
  </Card>

  <Card title="Rei Chat" href="/docs/rei-chat/overview">
    A conversational demo where a language model articulates Core's structured result.
  </Card>
</CardGroup>