json435 B

Video Workflow 10 — Evaluation Contract

JSON evaluation contract for non-profit story kit 10; it publishes readability, timing, comparison, and edge-report assertions. Stable P8 artifact p8-video-kit-10-evaluation-contract.

Prompt testing Agent workflows Schema validation

Preview — first 25 linesjson

{
  "assertions": [
    {
      "id": "source-readable",
      "required": true
    },
    {
      "id": "duration-preserved",
      "toleranceSeconds": 0.05
    },
    {
      "id": "expected-output-comparable",
      "required": true
    },
    {
      "id": "edge-case-reported",
      "required": true
    }
  ],
  "medium": "video",
  "provider": "vendor-neutral",
  "topic": "non-profit story",
  "workflow": "p8-video-kit-10"
}

Specifications

Workflow Role: evaluation-contract
Workflow Order: 3
Provider: vendor-neutral
Medium: video
Kit Number: 10
Assertions: 4
Provenance: Synthetic deterministic P8 fixture generated by generation/p8_content.py; seed namespace 2026082300

Testing contract

Reference control

Scenario: Validate the JSON and collect the assertion ids plus the duration tolerance.
Expected result: Four unique assertions are attached to p8-video-kit-10, and duration-preserved has toleranceSeconds 0.05.

What is a .json file?

JSON (JavaScript Object Notation) is a lightweight, text-based data-interchange format representing objects, arrays, strings, numbers, booleans, and null. It is language-independent, human-readable, and the dominant format for web APIs and configuration. It requires a single well-formed root value.

How to use this file

Use an example JSON file to test parsers and serializers, schema validation, Unicode and number-precision handling, and API request or response processing.

How to use this file for testing

“Video Workflow 10 — Evaluation Contract” is a deterministic Novus Examples fixture for Prompt testing, Agent workflows, Schema validation. Vendor-neutral plans and provider-compatible message fixtures paired with explicit inputs, assertions, failure cases, and expected results for repeatable prompt regression testing.

Documented properties for this file: JSON · 435 bytes. Compare results against paired or grouped companions on this page when present (clean↔damaged, searchable↔scanned, or format twins) so scores stay reproducible across runs.

Download the file once, keep the path stable in CI or local scripts, and treat the spec table as the contract: dimensions, seeds, field lists, and roles are intentional. Corrupt or invalid samples are labelled as such — expect parsers to fail loudly rather than silently accept them.

Prompt fixtures are static, provider-labelled inputs and contracts — they do not call an API. For a six-step kit, follow workflowOrder from the brief through the expected output, then compare the documented assertions before trying the controlled edge case.

Run the static plan through your own harness, record the provider adapter and model settings separately, and score the result against the included evaluation contract. The fixture itself performs no network request and contains no credentials.

Code examples

import json

with open("evaluation-contract.json") as f:
    data = json.load(f)
print(type(data), len(data))

Generated by generation/p8_content.py. Free for any use, no attribution required — license.