Course-aligned practice for D31-D36 Context Template Seed. This page uses the previous and next artifacts to keep the practice connected.
Part 2 | D31-D36 Context Template Seed | normal
Define task goal fields that state the work outcome, decision use, done signal, and bad-goal repair.
A manager says: “The template is useful, but how do workers know what goal to put in?”
It sounds like a simple goal field. The trap is that vague goals create vague AI output; the goal must name decision, reader, and success signal.
“Goal: improve the task output.”
The weak version contains improve, task output, no reader, no success signal.
What will this output help decide?
Who uses the result?
How will we know it worked?
Use this rule before filling the build table. The goal is a reusable context asset, not another one-off prompt.
What will this output help decide?
Who uses the result?
How will we know it worked?
A project coordinator asks AI for a project update, but the actual goal is to help the manager decide whether to unblock procurement today.
Define task goal fields that state the work outcome, decision use, done signal, and bad-goal repair.
Using vague goals like "write an update" instead of naming the decision the artifact supports.
The vague goal “make this better” cannot be reviewed. A useful goal names the outcome, decision use, done signal, and one non-goal.
What is missing from the vague goal?
Received: D32 task_template_structure.md
Hands off: D34 background_fields.md
Redline: Do not treat a task goal as complete unless the business outcome and done signal are visible.
Before building the artifact, decide what the template should make easier to review.
This is not a generic sample. It is filled for Day 33: Task Goal Fields.
| No. | Task goal | User/business outcome | Done signal | Bad goal wording | Repair note | Evidence used | Readiness |
|---|---|---|---|---|---|---|---|
1 | Update procurement blocker status | Manager decides whether to escalate vendor delay today | Escalation choice and owner are clear | Make this update better | Rewrite goal as decision-support update for escalation | Vendor email + project risk note | Ready for D34 |
The goal becomes testable instead of taste-based.
Make this better
Produce a 5-bullet risk summary for manager approval; done when evidence risks and owner decision are visible.
Core path: complete three rows. Deep path: complete three rows. Blank required fields create export warnings.
| No. | Task goal | User/business outcome | Done signal | Bad goal wording | Repair note | Evidence used | Readiness |
|---|---|---|---|---|---|---|---|
| 1 | |||||||
| 2 | |||||||
| 3 |
Optional but recommended: Use this pass to find the context/template field that would fail reuse, confuse a teammate, or hide a review need before export.
Weak row: Goal: improve the update.
Repair move: Add decision, reader, and success signal.
Better row: Goal: help support manager decide whether the reply draft is safe to send; success = no unsupported policy claims.
Choose the field you would be comfortable carrying into the next day.
Choose the field most likely to fail reuse or need review.
Sentence starter: The weak row is weak because ___. I will repair it by adding ___ before using AI.
This file is today’s work receipt. It should show which context/template field can be reused tomorrow, not just that you filled a table.
What this artifact proves: This file proves you can make task goals specific enough to guide reusable AI work.
Weak export: Goal: improve the update.
Good export: Goal: help support manager decide whether the reply draft is safe to send; success = no unsupported policy claims.
Click Generate Markdown to create task_goal_fields.md.
Continue with a day-specific practice example.