> For the complete documentation index, see [llms.txt](https://docs.allganize.ai/alli-llm-app-market/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.allganize.ai/alli-llm-app-market/manual/for_admin/default-apps/ga-hr/personnel-evaluation.md).

# 人事評価のコメント下書き作成

人事評価のコメント下書き作成アプリでは、「被評価者からのコメント」「職種」「被評価者の良い点」「被評価者の要改善点」の入力のみで人事評価のコメントの下書きを作成することができます。

<figure><img src="/files/rlHRFIhSbyytYj8itVg1" alt=""><figcaption></figcaption></figure>

下記の入力例を基に人事評価のコメントを生成します。

## 入力例 <a href="#example1" id="example1"></a>

* **被評価者からのコメント：・**&#x76EE;標に対して98％の達成率で未達となった。 \
  　　　　　　　　　　　　・外部要因による決裁時期の遅れなどが発生し、顧客との\
  　　　　　　　　　　　　　コミュニケーションが十分ではなかった。
* **職種：**&#x30BB;ールス
* **被評価者の良い点：・**&#x6E96;備を怠らない \
  　　　　　　　　　・目標達成意識が強い \
  　　　　　　　　　・周囲に目を向けることができる
* **被評価者の要改善点**：・顧客に寄り添いすぎてしまう

<figure><img src="/files/SpkXLnu5kU5Hn7MAUfkr" alt=""><figcaption></figcaption></figure>

## 結果例 <a href="#example2" id="example2"></a>

入力例の内容で生成を実施すると下記のような人事評価のコメントが生成されます。

生成された文章は、その場で編集やコピー、ファイルとしてダウンロード(txt・PDF・docx)が可能です。

<figure><img src="/files/yreX7t18azPoUcmpilun" alt=""><figcaption></figcaption></figure>

```
部下の準備を怠らず、目標達成意識が強く、周囲に目を向ける姿勢は素晴らしいですね。
顧客に寄り添いすぎてしまうという点については、顧客とのバランスを保つことが重要ですね。
目標達成率が98％という高い数字を残したことは素晴らしいですが、外部要因による決裁時期の
遅れなどがあり、顧客とのコミュニケーションが不十分だったとのこと。今後は、顧客との
コミュニケーションを強化し、外部要因に左右されないような対策を考えることが大切ですね。
具体的な改善策として、顧客との定期的なフォローアップや、外部要因に左右されない目標設定などが
考えられます。部下の成長を期待しています。
```

## アプリ編集画面 <a href="#edit" id="edit"></a>

標準で用意されているインプット項目とLLMモデル・プロンプトは下記の内容になります。

### インプット <a href="#input" id="input"></a>

利用者に入力してもらいたい項目を4つご用意しています。

インプット項目は追加や削除、入力形式(インプットタイプ)の変更をすることができます。

<figure><img src="/files/Qn0lryGsFQw6sOq0ox21" alt=""><figcaption></figcaption></figure>

* **被評価者からのコメント**
  * 変数：@FB
  * インプットタイプ：パラグラフ
* **職種**
  * 変数：@Occupation
  * インプットタイプ：テキスト
* **被評価者の良い点**
  * 変数：@Good
  * インプットタイプ：パラグラフ
* **被評価者の悪い点**
  * 変数：@Bad
  * インプットタイプ：パラグラフ

#### インプットのOne Pointアドバイス <a href="#input_onepoint" id="input_onepoint"></a>

{% hint style="info" %}
職種が決まっている場合は、インプットを単一選択にし、固定化することも可能です。
{% endhint %}

### LLMモデル <a href="#model" id="model"></a>

標準モデルは「OPENAI GPT-4 TURBO」がセットされています。

{% hint style="warning" %}
モデルを変更することで生成結果の仕上がりが変わる場合があります。
{% endhint %}

### プロンプト <a href="#prompt" id="prompt"></a>

{}で囲まれているものはインプットで設定されている変数が当てはめられており、プロンプト記載欄の下にチップの形で表示されている変数をクリックすると簡単に記載ができます。

{% hint style="warning" %}
インプットの変数を変更した際は、プロンプト内の変数も変更する必要があります。
{% endhint %}

#### プロンプトのOne Pointアドバイス <a href="#prompt_onepoint" id="prompt_onepoint"></a>

{% hint style="info" %}
表現方法などをプロンプトで指定することで任意の表現で生成することができます。&#x20;

例：ネガティブな表現は利用しないでください。
{% endhint %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.allganize.ai/alli-llm-app-market/manual/for_admin/default-apps/ga-hr/personnel-evaluation.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
