> ## 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. # Core concepts > Understand Domains, events, results, feedback, and the state that connects them. A Domain gives one task a stable contract and a scope for its evidence and learned state. Calls within that scope can use applicable experience from earlier work. ## The objects in your integration | Object | Role | Example | | ------------------ | ------------------------------------------------------------------- | ----------------------------------------------- | | **Domain** | Task contract and state scope, addressed by `domain_id` | Predict output from process measurements | | **Event** | An observation, transition, execution record, or outcome | A completed measurement and its observed output | | **Query** | A request for the current contract-defined result | Predict output with the target withheld | | **Feedback** | A measured outcome or correction attributed to a decision or record | Reward for the policy that actually executed | | **Retained state** | Evidence-shaped state available to later calls | An input projection or learned action values | Creating a new environment episode does not reset a Domain. Reusing a Domain carries its applicable state forward until an explicit lifecycle operation changes it. ## Decide what teaches the result | What you observe | Starting relationship | Guide | | ------------------------------------------------ | -------------------------- | -------------------------------------------------------------------------------------- | | Inputs and a completed target value | Transition prediction | [First learned result](/docs/neuroadapt/first-learned-result) | | One decision and its attributable outcome | Contextual policy feedback | [Learn from an outcome](/docs/neuroadapt/make-behavior-improve-from-feedback) | | Actions that affect later states and rewards | Sequential learning | [Sequential Discovery](/docs/neuroadapt/discovery-sequential) | | Evidence or a correction useful to later queries | Continuing state | [Continuity across calls](/docs/neuroadapt/build-an-assistant-with-persistent-context) | Completed observations can teach a predictor without a reward. Preserve decision-time context and the executed policy when the learner should instead revise action values. [Learning relationships](/docs/neuroadapt/learning-patterns-for-domains) covers the full set of configurations. ## Structure and learning schedule [Discovery](/docs/neuroadapt/discovery) forms eligible learner-facing structure from evidence. [Authored structure](/docs/neuroadapt/build-a-domain-aware-assistant) makes selected task relationships explicit before use. Either can start empty, use previously acquired state, or keep learning during operation. Choose the schedule separately: define the starting state and whether writes are allowed during the run. During frozen use, observations and returned actions can still change while the applicable learner state stays fixed. See [Learning schedules](/docs/neuroadapt/choose-a-learning-setup). ## Inspect what happened Check three things: the request succeeded, the intended learner admitted the event or feedback, and the later result used the applicable state. A stored record and a learning update are separate signals. Use the route's result status, evidence, and learning diagnostics. Confidence fields have route-specific meanings; use the documented support and abstention behavior when deciding whether to act. See [Explain a result](/docs/neuroadapt/explain-and-audit-responses). ## Contract and application boundaries The public task meanings, event schema, result contract, available actions, outcome semantics, and boundaries stay stable within the declared workflow. Supporting observations, discovered input and representation structure, learned relationships, active alternatives, policy or transition state, uncertainty, and support can change through eligible writes. State can form during a zero-start run or a separate acquisition phase. Decide whether later use permits further learning or only reads retained state. See [Choose a learning setup](/docs/neuroadapt/choose-a-learning-setup). No. A Domain defines the public task boundary. [Discovery](/docs/neuroadapt/discovery) can form eligible input projections, fields, combinations, temporal relationships, state-dependent action values, and other learner-facing structure from evidence. Use [authored structure](/docs/neuroadapt/build-a-domain-aware-assistant) when it must be fixed or reviewed in advance. Naming legal actions does not name the correct action; defining a coordinate system does not supply a hidden target; defining a successful outcome does not supply the procedure that achieves it. The external environment, perception or format translation, candidate generation where required, final commitment, execution, safety checks, and consequence measurement belong to the application. An adapter should expose only information available at that point, not inject the preferred answer or hidden mapping the learner is expected to form. Keep the returned result, the application's committed value, and the operation actually executed separately when validation or overrides can change them. Reuse a Domain when public meanings, result units and schema, consequence semantics, and state lifecycle remain compatible. Use separate Domains when those boundaries differ, even if observations come from the same product or dataset. Each Domain operation addresses a `domain_id` under the authenticated owner. Current observations and external state are not retained Domain state. State-gateway continuity is another scope for evidence and constraints when a Domain contract is unnecessary. Predicting an observable consequence, judging a committed decision's utility, scoring movement toward a bounded objective, assigning delayed credit, and comparing typed hypotheses are different relationships. A Domain can combine compatible relationships, but they do not become interchangeable because they all return JSON. [Choose how a Domain learns](/docs/neuroadapt/learning-patterns-for-domains) describes the distinctions. [Explain a result](/docs/neuroadapt/explain-and-audit-responses) describes support, uncertainty, and learner diagnostics.