# Check a forecast's work-class eligibility

Illustrative planning brief; no automatic product import.

Synthetic planning case: A documented toy forecast rule is for a single ready proof review with known inputs. The proposed evaluation includes A:ready proof, B:proof with missing input and C:fixture migration.

## Decision

Only A meets the declared forecast context. Keep B and C as ineligible cases for this rule rather than reporting their errors as if the rule targeted them.

## Owned work

- Read the forecast context
  - Owner role: Model reviewer
  - Acceptance evidence: The rule’s target class and required input state are documented before evaluation.
- Classify proposed evaluation cases
  - Owner role: Recorder
  - Acceptance evidence: B and C have explicit eligibility exclusions, not silently missing scores.
- Choose a proper evaluation cohort
  - Owner role: Planning lead
  - Acceptance evidence: Future comparisons retain the same target definition or explicitly revise the rule.

## Workflow

1. Read the forecast context. Check: The rule’s target class and required input state are documented before evaluation.
2. Classify proposed evaluation cases. Check: B and C have explicit eligibility exclusions, not silently missing scores.
3. Choose a proper evaluation cohort. Check: Future comparisons retain the same target definition or explicitly revise the rule.

## Judgment

No native TeamBoostAI forecast, entitlement or real model deployment is asserted. The rule is an external manual example.


## Filled manual planning note

Only A meets the declared forecast context. Keep B and C as ineligible cases for this rule rather than reporting their errors as if the rule targeted them. Eligibility is the conjunction of the stated work class and ready-known inputs. A meets both; B fails input readiness and C the class condition. One eligible case is not an accuracy study. No native TeamBoostAI forecast, entitlement or real model deployment is asserted. The rule is an external manual example.


## Workflow questions

### Can an ineligible case still reveal a useful limitation?

Yes. It exposes unsupported scope, but that differs from error on the declared target.

### Does one eligible case validate the rule?

No. The worksheet checks applicability, not model performance.

## Product connection

Use the owned checks and downloaded brief to discuss this planning decision alongside your TeamBoostAI tasks. Confirm available fields, roles and account features separately. The example is manual; it does not calculate live analytics, create work or run an experiment in the product.

Confirm account availability before adopting this manual outline.

## Original worked case

Synthetic records, manual planning only. No account import or live analytics.

### Inspect the invented case records

Case | Work class | Input condition | Rule eligibility
--- | --- | --- | ---
A | Single proof review | Known and ready | Eligible
B | Single proof review | Required input missing | Outside context
C | Fixture migration | Known input | Wrong work class

### Reasoning

Eligibility is the conjunction of the stated work class and ready-known inputs. A meets both; B fails input readiness and C the class condition. One eligible case is not an accuracy study.

### Bounded result

Only A meets the declared forecast context. Keep B and C as ineligible cases for this rule rather than reporting their errors as if the rule targeted them.

### Distinct decision

The decision checks model applicability before computing performance on unrelated or unready work.

### Limits

No native TeamBoostAI forecast, entitlement or real model deployment is asserted. The rule is an external manual example.

### Definitions and method context

- Forecasting: Principles and Practice — accuracy — https://otexts.com/fpp3/accuracy.html — Genuine held-out forecast and point-error evaluation context. Binary scoring examples use their own explicit toy definitions; no real task model is validated.