git:20261031.2390887 to git:20261101.8be107b

21 added, 47 removed. Audit A to A.

---

name: orbyn-ai-application

description: "Design, implement or evaluate model-powered application behavior: grounded answers, retrieval, structured generation, tool workflows and quality/cost operation. Not model training, generic AI-assisted coding or host/provider setup."

---

# Engineer a model-powered application

- Start from the user's task and the consuming project's current source, authority,

- provider capabilities and data policy. AI is an implementation choice, not the

- outcome. Compare the existing/manual or deterministic baseline before adding a

- model, retrieval pipeline or autonomous loop. Use the smallest design that can

- meet the task's quality, latency, cost and failure requirements.

- For problem evidence and whether to build, use [product discovery](../orbyn-plan/references/product-discovery.md).

- For an ordinary API, UI, bug fix or agent-host setup with no model-powered product

- contract, use its existing owner. This skill does not train models, install an

- SDK/provider, enable capture, purchase access or authorize live calls.

- ## Select the changed boundary

- Read only the relevant method:

+ Use for a model-powered product contract. For an ordinary API, UI, bug fix or

+ agent-host setup without one, use its existing owner. For problem evidence and

+ whether to build, use [product discovery](../orbyn-plan/references/product-discovery.md).

- - [Application contract](references/application-contract.md): use-case baseline,

- model versus workflow/agent, prompt/context versions and structured outputs.

- - [Grounded retrieval](references/retrieval.md): ingestion/query lineage,

- permission filtering, source quality and answer support.

- - [Tool effects](references/tool-effects.md): proposals versus authorized effects,

- semantic validation, approval, unknown outcomes and bounded loops.

- - [Streaming interactions](references/streaming-interactions.md): typed progress,

- state convergence, terminal witnesses, passive history and supported pending resume.

- - [Assistant-chat UI](../orbyn-ui-design/references/assistant-chat.md): consuming-product

- components/tokens, composer/runtime ownership, safe parts and reading intent.

- - [Task evaluations](references/evaluations.md): representative slices, independent

- outcomes, repeated comparisons, calibrated grading and privacy.

- - [Operation and change](references/operations.md): version bundles, budgets,

- fallback, qualification, rollout and retention.

+ This skill does not train models, install an SDK/provider, enable capture, purchase

+ access or authorize live calls. A security scan still needs its own explicit request.

- ## Connect the owners and evidence

+ ## Method

- Use [backend design](../orbyn-backend-design/SKILL.md) for actual authorization,

- state, concurrency and effect mechanics; [UI design](../orbyn-ui-design/SKILL.md)

- for usable suggestions, progress, correction, manual alternatives and recovery.

- Use [TDD](../tdd/SKILL.md) for deterministic contract regressions and the

- [CI owner's designated gates](../orbyn-ci-design/references/change-scope.md#designate-gates-for-the-feature-worktree)

- for affected checks. Ordinary unit tests and task-quality evaluations answer

- different questions. Security controls belong at actual data/effect boundaries;

- a prompt instruction or schema is neither authorization nor an injection barrier.

- A security scan still needs its own explicit request.

+ 1. **Start from the user's task** and the consuming project's current source, authority, provider capabilities and data policy. AI is an implementation choice, not the outcome.

+ 2. **Compare the baseline.** Weigh the existing/manual or deterministic baseline before adding a model, retrieval pipeline or autonomous loop. Use the smallest design that can meet the task's quality, latency, cost and failure requirements.

+ 3. **Select the changed boundary** and read only its method:

+ - [Application contract](references/application-contract.md): use-case baseline, model versus workflow/agent, prompt/context versions and structured outputs.

+ - [Grounded retrieval](references/retrieval.md): ingestion/query lineage, permission filtering, source quality and answer support.

+ - [Tool effects](references/tool-effects.md): proposals versus authorized effects, semantic validation, approval, unknown outcomes and bounded loops.

+ - [Streaming interactions](references/streaming-interactions.md): typed progress, state convergence, terminal witnesses, passive history and supported pending resume.

+ - [Assistant-chat UI](../orbyn-ui-design/references/assistant-chat.md): consuming-product components/tokens, composer/runtime ownership, safe parts and reading intent.

+ - [Task evaluations](references/evaluations.md): representative slices, independent outcomes, repeated comparisons, calibrated grading and privacy.

+ - [Operation and change](references/operations.md): version bundles, budgets, fallback, qualification, rollout and retention.

+ 4. **Connect the owners.** Use [backend design](../orbyn-backend-design/SKILL.md) for actual authorization, state, concurrency and effect mechanics, and [UI design](../orbyn-ui-design/SKILL.md) for usable suggestions, progress, correction, manual alternatives and recovery. Use [TDD](../tdd/SKILL.md) for deterministic contract regressions and the [CI owner's designated gates](../orbyn-ci-design/references/change-scope.md#designate-gates-for-the-feature-worktree) for affected checks. Ordinary unit tests and task-quality evaluations answer different questions.

+ 5. **Put security controls at actual data/effect boundaries.** A prompt instruction or schema is neither authorization nor an injection barrier.

+ 6. **Deliver** the selected baseline/design, inputs and trust boundaries, permission and output/effect contracts, versioned evaluation plan/results, resource bounds and unverified surfaces. Distinguish a proposed experiment, offline fixture, live provider observation and released behavior.

- Deliver the selected baseline/design, inputs and trust boundaries, permission and

- output/effect contracts, versioned evaluation plan/results, resource bounds and

- unverified surfaces. Distinguish a proposed experiment, offline fixture, live

- provider observation and released behavior. Missing credentials/data/authority

- are limits, not reasons to install, fabricate results or run paid calls.

+ Missing credentials/data/authority are limits, not reasons to install, fabricate results or run paid calls.

- The [document-assistant example](examples/document-assistant.md) connects retrieval,

- revocation, a tool timeout and evaluation without requiring a provider. Methods

- are original local guidance; linked primary sources are research/update pointers,

- not mandatory downloads or imported workflows.

+ The [document-assistant example](examples/document-assistant.md) connects retrieval, revocation, a tool timeout and evaluation without requiring a provider. Methods are original local guidance; linked primary sources are research/update pointers, not mandatory downloads or imported workflows.