Day 31 · Locked · Course Buyer: Part 2 or BundlePrompt vs Context — normal skill page

Course-aligned lesson expansion from original Day 31. Cluster: D31-D36 Context Template Seed.

AI Ages Day 31

Part 2 | D31-D36 Context Template Seed | normal | evidence: reviewed course material (mapped to reviewed course material enum)

Day 31: Prompt vs Context

Build context_template_seed.md so the next day can reuse a concrete field, rule, example, or testable contract.

15mcore path
30mdeep path
9fields
1artifact
Current path: complete three rows plus summary and handoff candidate.
V1Scenario

Concrete workplace scenario

After D30, your manager hands you the Month 1 diagnostic packet: usable evidence, a review rule, an owner/approval path, and known limitations. They ask: “Can this become reusable context instead of another one-off prompt?”

The trap is treating the D30 packet as background text. D31 must turn only supported evidence, review rule, owner, and limitation into reusable context fields.

V2Worked answer before the table

Worked answer

Bad example first: the plausible shortcut fails

Weak example

“Write a better prompt for this work request.”

What goes wrong

The weak version contains better prompt, no reusable context field, no review point, no template seed.

Work-ready version: use the day rule

D30 evidence packet

Usable Month 1 proof that can become context.

Review rule

The human check that must travel with the field.

Limitation / do-not-carry

What should not be reused without repair.

V3Decision fork

Quick decision check

Context becomes reusable when it becomes a field rule

Use this rule before filling the build table. The goal is a reusable context asset, not another one-off prompt.

D30 evidence packet

Usable Month 1 proof that can become context.

Review rule

The human check that must travel with the field.

Limitation / do-not-carry

What should not be reused without repair.

TRACEToday’s workflow trace

Context-template workflow trace

RESULTToday’s visible result

Before / after: what changed in your work?

Before learning

After learning

What AI-in-workflow means today

Q1Request

Workplace situation

A worker must turn prompt vs context into a reusable context-template artifact instead of another one-off prompt.

Main learning job

Build context_template_seed.md so the next day can reuse a concrete field, rule, example, or testable contract.

Failure mode

Treating prompt vs context as advice instead of a reusable field or evidence-backed artifact.

TRYPrototype micro-practice

D30 packet carry-forward failure story

A worker asks: “Write a client update.” AI produces a generic polished message, but it misses the project stage, audience concern, review status, and decision needed.

Diagnosis

The prompt did not fail because the model was bad. It failed because the context template was empty.

Q2Chain

Artifact handoff

Received: D30 foundation_production_pack_and_part2_handoff.md

Hands off: D32 task_template_structure.md

Course path: Original title is Prompt vs Context; review status is reviewed course material; lesson type is normal skill page.

TRYMid-lesson micro-practice

Micro-practice: artifact handoff → template field

Do not add fields because they look tidy. Add fields because a prior evidence or future handoff needs them.

SRCCourse-path example

Course-path example checkpoint

Review status mapping: reviewed course material → generation enum reviewed course material

L3 · W5 · Lesson

Prompt vs Context

Turn one-off prompts into reusable context templates.

Time

10–15 minutes

Complete one small work-like unit.

Artifact

context_template_seed.md

Save a concrete portfolio increment.

Track

Part 2 · Days 31–60 · L3

Stay inside the correct 30-day course part.

Lesson outcome

By the end, you should have a clear decision, template, map, or review note that can be reused at work.

1 · Concept — What you need to understand

This lesson focuses on one practical capability: choose the right AI use, define the context, or make a workflow step reviewable.

Good move: describe the task, the input, the expected output, and the human review point.

Common mistake: asking AI to decide everything without context, constraints, or review responsibility.

2 · Guided check — Check your understanding

Before writing the artifact, confirm what the work unit must prove and how a human would review it.

  • What input is needed?
  • What output should be produced?
  • Where does human review happen?
  • What would count as a failure?

3 · Practice — Build today’s artifact

Create or update context_template_seed.md. Keep it small, specific, and reusable. Do not paste private data or secrets.

4 · Checklist — Minimum acceptance

  • Specific task or workflow step
  • Clear input and output
  • D30 review rule
  • Saved artifact name

Learning path

Next lesson: Continue to the next daily unit when this artifact is saved.

Lesson map

1. Concept → 2. Guided check → 3. Practice → 4. Checklist → 5. Artifact.

Today artifact: context_template_seed.md. After you save it, add it to the course portfolio pack.

Q3Judgment

Manual-first judgment and AI-use window

Worker owns

The worker separates prompt wording from missing context and chooses which context fields are evidence-truth, not AI guesses.

AI may help with

AI may suggest missing context fields, but must not invent audience, evidence, deadline, or output use.

Do not export if evidence/evidence, owner/reviewer, readiness, or limitation fields are blank.

EXExample

Good-enough sample row guide

Use a concrete workplace case: an operations lead preparing a weekly status update for a manager by Friday, using a evidence note, a deadline, an expected format, and a human review owner. Do not leave the artifact as labels only.

  • Name the provided material or evidence pointer.
  • Name the stakeholder or reviewer.
  • Name the business consequence if the field is wrong.
  • Name the limitation or unknown before export.
TRYPrototype micro-practice

Completed row to imitate

D30 packet carry-forward failureMissing D30-derived fieldTemplate seed
Generic client updateReader concern + review status“Audience: customer ops lead; concern: delay date; evidence: verified ticket notes only.”
Q4Build

Build context_template_seed.md

Core path: complete three rows. Deep path: complete three rows plus summary and handoff candidate. Blank required fields create export warnings.

No.Work requestD30 packet carry-forward failureMissing D30-derived fieldD30 review ruleReusable context seedEvidence qualityHuman owner / reviewerReview readinessLimitation / unknown
1
2
3
Q5Summary

Summary / decision

Q6Handoff

D37 context template candidate

Capture a concrete candidate for the next synthesis or handoff page.

V5Repair pass

Repair one weak field

Use this pass to find the context/template field that would fail reuse, confuse a teammate, or hide a review need before export.

Repair example

Weak row: D30 packet is pasted as background, but evidence, review rule, owner path, and limitation are not saved as fields.

Repair move: Name the D30-derived context field, review rule, owner/approval path, and do-not-carry limitation.

Better row: D30-derived seed: approved evidence source, review owner, approval path, and limitation/do-not-carry rule travel into D32 task template.

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.

QXExport artifact

Export artifact

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.

Before you export

  • Does the export name the D30-derived context field, review rule, owner/approval path, and unsupported carry-forward?
  • Does it separate supported evidence from limitation or do-not-carry material?
  • Would D32 know which context seed can become part of the task template structure?

What this artifact proves: This file proves you can receive the D30 diagnostic handoff and convert supported evidence, review rule, owner path, and limitation into a reusable context template seed.

Weak export: D30 packet is pasted as background, but evidence, review rule, owner path, and limitation are not saved as fields.

Good export: D30-derived seed: approved evidence source, review owner, approval path, and limitation/do-not-carry rule travel into D32 task template.

Click Generate Markdown to create context_template_seed.md.
Course path

D31-D36 Context Template Seed

This page is one course-aligned Part 2 artifact link.