# Match a forecast to its decision horizon

Illustrative planning brief; no automatic product import.

Synthetic planning case: A proposal predicts two days for the next individual proof. A stakeholder asks whether a three-proof batch plus its receiving review will be ready in two days; no joint schedule or other durations are supplied.

## Decision

The next-proof forecast does not answer the batch-and-review question. Define the requested endpoint and collect the missing joint schedule before transferring the number or its confidence label.

## Owned work

- Name the requested receiving endpoint
  - Owner role: Stakeholder lead
  - Acceptance evidence: The question concerns three proofs plus review, not only the next proof.
- Inspect the forecast target
  - Owner role: Evaluation owner
  - Acceptance evidence: The recorded two-day number applies to one specific individual target.
- Build an eligible endpoint model
  - Owner role: Planner
  - Acceptance evidence: Missing durations, dependencies, resources and review gate are provided before a batch claim.

## Workflow

1. Name the requested receiving endpoint. Check: The question concerns three proofs plus review, not only the next proof.
2. Inspect the forecast target. Check: The recorded two-day number applies to one specific individual target.
3. Build an eligible endpoint model. Check: Missing durations, dependencies, resources and review gate are provided before a batch claim.

## Judgment

A point prediction and its probability label cannot be transported to another horizon or unit without justification.


## Filled manual planning note

The next-proof forecast does not answer the batch-and-review question. Define the requested endpoint and collect the missing joint schedule before transferring the number or its confidence label. Even 3×2=6 days would introduce extra identical-duration and serial-execution assumptions. Neither two nor six is established for the requested endpoint by the supplied next-item forecast. A point prediction and its probability label cannot be transported to another horizon or unit without justification.


## Workflow questions

### Can I multiply the next-item number by three?

Only under additional explicit duration and sequencing assumptions; any confidence claim still needs its own model.

### Can parallel work make the batch faster?

Possibly, if inputs and eligible resources support it. The current prediction does not provide those facts.

## 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

Question | Available prediction | Missing conditions
--- | --- | ---
Next individual proof | 2 days | Supplied target only
Three-proof batch | No joint prediction | Other durations, overlap and resources
Batch plus receiving review | No endpoint prediction | Review duration and acceptance gate

### Reasoning

Even 3×2=6 days would introduce extra identical-duration and serial-execution assumptions. Neither two nor six is established for the requested endpoint by the supplied next-item forecast.

### Bounded result

The next-proof forecast does not answer the batch-and-review question. Define the requested endpoint and collect the missing joint schedule before transferring the number or its confidence label.

### Distinct decision

This audits the forecast’s decision unit and horizon before reusing it for a larger endpoint.

### Limits

A point prediction and its probability label cannot be transported to another horizon or unit without justification.

### 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.