<!-- LLM INSTRUCTIONS: Fill in the [ Add details... ] placeholders based on project context.

Context and Definition:
A prompt library log is the record of the prompts a team has found worth
keeping, kept so that the next time the same question comes up the answer is
already written. Its purpose is reuse: a prompt that solved a problem is
worth more the second time it is used than the effort of writing it again,
and worth more still if the team can see what a good response looked like.
It is the working record of an AI-enabled practice, and it changes as the
practice changes, so each entry carries a version.

It can receive information from:
*   Prompt library of the organisation
*   AI governance plan
*   Model card and fact sheet

It provides information to:
*   Lessons learned register
*   Team onboarding checklist
*   Project status report, when AI use is reported

Tailoring Tips:
*   File the prompt, not its history. The library is read under time pressure,
    and a prompt entered with a paragraph of reasoning about it is a prompt
    nobody opens.
*   Write the expected output before the prompt is used. Deciding what a good
    answer looks like after seeing the answer is not a standard, it is a
    description.
*   Retire what does not work. An entry that has been used and did not help is
    the most valuable line in the log, provided it is marked as such.

Alignment:
The prompt library log should be aligned and consistent with:
*   AI governance plan
*   AI readiness assessment
*   Model card and fact sheet, because a prompt that names a model is only
    reusable while that model is in use

Section Instructions:
*   Prompt Library: for each prompt that has been written and used, give its
    identifier, the use case, the text as it is sent, what a good response
    looks like, and the version and status it currently holds.
-->

<h3 dir="ltr" align="right">{{Company_Name}}</h3>
<h2 dir="ltr" align="right">{{Project_Name}} - {{Project_ID}}</h2>
<h1 dir="ltr" align="center">PROMPT LIBRARY LOG</h1>

| **Date Prepared:** {{Current_Date}} | **Project Manager:** {{Project_Manager_Name}} | **Prepared By:** {{Prepared_By}} |
| :--- | :--- | :--- |

---

## Prompt Library

| Prompt ID | Use Case | Prompt Text | Expected Output | Status/Version |
| :---: | :--- | :--- | :--- | :--- |
| [ Add details... ] | [ Add details... ] | [ Add details... ] | [ Add details... ] | [ Add details... ] |
| [ Add details... ] | [ Add details... ] | [ Add details... ] | [ Add details... ] | [ Add details... ] |
| [ Add details... ] | [ Add details... ] | [ Add details... ] | [ Add details... ] | [ Add details... ] |

---

### Sign-off and Approvals

| Role | Name | Signature | Date |
| :--- | :--- | :---: | :---: |
| **AI Engineer / Prompt Designer** | {{AI_Engineer_Name}} | _______________________ | [ .... - .... - .... ] |
| **AI Technical Lead** | {{AI_Lead_Name}} | _______________________ | [ .... - .... - .... ] |
| **Project Manager** | {{Project_Manager_Name}} | _______________________ | [ .... - .... - .... ] |
---

<div dir="ltr" align="right" style="margin-top: 20px; font-size: 12px; color: #7f8c8d;">
  <span>Electronic Audit Trail: Hash SHA256: {{Audit_Trail_SHA256_Hash}}</span> <br>
  <strong>Template:</strong> PROMPT LIBRARY LOG | <strong>Ref:</strong> PMO-05.09 <br>
  <i>Generated on: {{Current_Timestamp}}, by <a href="https://github.com/fakhruldeen/Tasleemat/" style="color: #7f8c8d;">Tasleemat</a></i>
</div>

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://tasleemat.pmo/schemas/completed/PMO-05.09.schema.json",
  "title": "Completed Prompt Library Log Data Contract",
  "description": "Additive structural schema validating completed Prompt Library Log artifact data payloads (PMO-05.09).",
  "type": "object",
  "properties": {
    "artifact_id": {
      "type": "string",
      "const": "PMO-05.09"
    },
    "metadata": {
      "type": "object",
      "properties": {
        "project_name": {
          "type": "string",
          "minLength": 1
        },
        "project_code": {
          "type": "string"
        },
        "date_prepared": {
          "type": "string",
          "format": "date"
        },
        "project_manager": {
          "type": "string",
          "minLength": 1
        },
        "prepared_by": {
          "type": "string",
          "minLength": 1
        },
        "version": {
          "type": "string"
        },
        "status": {
          "type": "string",
          "enum": [
            "draft",
            "baselined",
            "in_review",
            "approved"
          ]
        }
      },
      "required": [
        "project_name",
        "date_prepared",
        "project_manager",
        "prepared_by"
      ]
    },
    "prompt_library": {
      "type": "object",
      "properties": {
        "prompt_id": {
          "type": "string",
          "minLength": 1,
          "description": "A short identifier, so a prompt can be referred to in a meeting without its text being read out. A number is enough if it is the only one in use."
        },
        "use_case": {
          "type": "string",
          "minLength": 1,
          "description": "What the prompt is for, in one line: the task it was written to do and the situation it was written in. A prompt filed without its use case cannot be told apart from another one that reads almost the same."
        },
        "prompt_text": {
          "type": "string",
          "minLength": 1,
          "description": "The prompt as it is actually sent, not a description of it. What is filed here has to be usable by pasting it, because a paraphrase is a different prompt and will behave differently."
        },
        "expected_output": {
          "type": "string",
          "minLength": 1,
          "description": "What a good answer looks like, specifically enough to be checked. This is the column that makes the library auditable: without it there is nothing to compare a later response against."
        },
        "status_version": {
          "type": "string",
          "minLength": 1,
          "description": "Where the prompt stands, and which version this is. A prompt that has been revised without the version moving leaves every earlier result attached to a text that no longer exists."
        }
      },
      "required": [
        "prompt_id",
        "use_case",
        "prompt_text",
        "expected_output",
        "status_version"
      ]
    }
  },
  "required": [
    "artifact_id",
    "metadata",
    "prompt_library"
  ]
}

{
  "form_name": "Prompt Library Log",
  "document_reference": "PMO-05.09",
  "_llm_instructions": "Populate the fields of 'Prompt Library Log' and write the value of each field under 'Generated Value', based on the project context. Context: the project carrying reference PMO-05.09.",
  "fields": {
    "f01_Prompt_ID": {
      "section": "Prompt Library",
      "label": "Prompt ID",
      "guidance": "A short identifier, so a prompt can be referred to in a meeting without its text being read out. A number is enough if it is the only one in use.",
      "value": ""
    },
    "f02_Use_Case": {
      "section": "Prompt Library",
      "label": "Use Case",
      "guidance": "What the prompt is for, in one line: the task it was written to do and the situation it was written in. A prompt filed without its use case cannot be told apart from another one that reads almost the same.",
      "value": ""
    },
    "f03_Prompt_Text": {
      "section": "Prompt Library",
      "label": "Prompt Text",
      "guidance": "The prompt as it is actually sent, not a description of it. What is filed here has to be usable by pasting it, because a paraphrase is a different prompt and will behave differently.",
      "value": ""
    },
    "f04_Expected_Output": {
      "section": "Prompt Library",
      "label": "Expected Output",
      "guidance": "What a good answer looks like, specifically enough to be checked. This is the column that makes the library auditable: without it there is nothing to compare a later response against.",
      "value": ""
    },
    "f05_Status_Version": {
      "section": "Prompt Library",
      "label": "Status/Version",
      "guidance": "Where the prompt stands, and which version this is. A prompt that has been revised without the version moving leaves every earlier result attached to a text that no longer exists.",
      "value": ""
    }
  }
}