> ## Documentation Index
> Fetch the complete documentation index at: https://docs.galtea.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Specification
> A testable behavioral expectation for a product
## What is a Specification?
A Specification in Galtea represents a single, testable behavioral expectation for a product. Examples include *"Must decline political questions"*, *"Can answer questions about phone specifications"*, or *"Always includes a disclaimer when giving financial advice"*.
Each specification has a **type** that classifies the kind of behavioral expectation:
* **Capability**: A core function the product can perform — what the product is designed to accomplish or deliver. For example: *"Can classify images as containing cats or dogs"*, *"Can retrieve and display the user's account balance"* (conversational), or *"Can generate personalized product recommendations based on browsing history"*.
* **Inability**: An action or task the product is fundamentally unable to do even if a malicious actor gained full control over it. These represent hard technical constraints where the infrastructure, system access, or architecture simply does not exist. For example: *"Cannot execute wire transfers"* (no payment gateway connected) or *"Cannot access other customers' data"* (no system integration exists).
* **Policy**: A mandatory rule or guideline the product must follow — from restrictions to behavioral guidelines. This includes refusal rules (what it must decline), interaction patterns (how it responds), communication style, and mandatory disclaimers. For example: *"Must include a disclaimer when discussing medical topics"* or *"Refuses requests to share confidential business data"*.
Specifications also have a **test type** that determines the evaluation approach: `ACCURACY`, `SECURITY`, or `BEHAVIOR`.
Specifications replace the legacy free-text fields (Capabilities, Inabilities, Policies) on Products with structured, individually testable expectations linked to specific metrics.
## The Specification-Driven Workflow
Specifications are at the center of Galtea's recommended evaluation flow:
1. **Define specifications** for your product (Capability, Inability, Policy)
2. **Generate metrics** from specifications using [AI Metric Generation](/concepts/metric/ai-generation)
3. **Create tests** from specifications — the test type is auto-derived
4. **Run evaluations** with `evaluations.run()` — resolves specs, tests, and metrics automatically
When creating or editing a specification in the dashboard, you have two AI assistance options. **Fill with AI** opens a dialog where you describe the behavior in a rough note and the AI rewrites it into a properly written specification description, then auto-fills the type, test type, and variant. **Complete with AI** classifies a description you have already written, suggesting the type, test type, and variant without changing the text. Review and edit the AI suggestions before saving — nothing is persisted until you submit the form.
End-to-end guide: define specs, generate metrics, create tests, and run evaluations — all from specifications.
## Keeping Specifications Up to Date
As your product evolves, its documentation — PRDs, design docs, spec sheets — often changes before its specifications do. The `POST /products/{id}/regenerate-config` endpoint lets you cross-check an uploaded document against a product's existing specifications and receive classified suggestions without persisting anything.
Each suggestion carries a `status`:
* `new` — a candidate specification extracted from the document that has no match among the product's existing specifications.
* `updated` — a candidate that refines or extends an existing specification (includes a reference to the existing spec).
* `contradictory` — a candidate that conflicts with an existing specification (includes a reference to the existing spec).
The endpoint **persists nothing**. Applying a suggestion — creating a new specification, updating an existing one, or removing a contradicted one — is a separate, explicit step using the standard specification endpoints in the [REST API](/api-reference). This means nothing changes without your confirmation and unaffected specifications remain untouched.
The dashboard flow for reviewing and applying suggestions is tracked in a follow-up. In the meantime the endpoint is available via the [REST API](/api-reference) and the CLI (`galtea products regenerate-config`).
## SDK Integration
The SDK allows you to create, list, retrieve, and delete specifications, as well as link and unlink metrics. See the [Specification Service API documentation](/sdk/api/specification/service) for more details.
Manage specifications programmatically
## Specification Properties
Unique identifier of the specification.
The ID of the product this specification belongs to.
A description of the testable behavioral expectation.
**Example**: "Must decline political questions and redirect the user to authoritative sources."
The type of specification.
Possible values: `CAPABILITY`, `INABILITY`, `POLICY`.
The type of test for this specification.
Possible values: `ACCURACY`, `SECURITY`, `BEHAVIOR`.
Required for `POLICY` specifications. Must not be provided for `CAPABILITY` or `INABILITY` specifications.
Variant of the test type. Applicable for `ACCURACY` and `SECURITY` test types.
List of metric IDs linked to this specification.
Timestamp of when the specification was created (ISO 8601 format).
## Related
How Galtea's concepts connect — diagram + per-entity quick reference.
A functionality or service being evaluated
Ways to evaluate and score product performance