TRANXACT.AI 帮助
智能体人工智能 › 评估

评估

代理人的表现如何——可以由人来评判,可以由其他代理人来评判,也可以通过其产出的结果来评判。一份提案被接受并在三十天后仍然有效,这是这张表格所能提供的最有力信号。

在哪里可以找到它

  1. 模块: 智能体人工智能
  2. 团体: 跑步
  3. 部分: 评估
  4. 屏幕: 评估

控制台中的地址: /agentic/evaluations

列表 · 11 列 · 10 表单上的字段 · 2 其中需要

列表显示的内容

这些是列表的列,按绘制顺序排列。可以对任何列进行排序、筛选、隐藏或导出。

柱子种类字段名称
什么时候日期和时间evaluated_at
代理人文本agent_name
跑步代码run_no
评分者地位evaluator
人文本evaluator_name
标准文本criterion
分数数字score
判决地位verdict
结果地位outcome_kind
价值数量outcome_value
评论文本comment

表格

此处会显示创建记录时需要填写的信息。必填字段已标记;管理员可以从配置列表中选择所需选项,而无需发布新版本。

场地类型选择笔记
跑步 选择 从现有记录中查找 Optional: the run being graded, from this agent's runs. Empty grades the agent in general.
代理人 必需的 选择 从现有记录中查找 The agent whose work is graded.
评分者 必需的 选择 配置列表 Who judged it. A person: you or a colleague. Another agent: an agent acting as grader (choose it below). What happened next: the result of its work, e.g. a proposal accepted and still standing. A rule: an automatic check.
Graded by agent 选择 从现有记录中查找 The agent that did the grading — usually a reviewer agent set up to check other agents' work.
标准 文本 What the grade is for, e.g. overall, accuracy, tone. Leave blank for overall. The date is recorded automatically when the evaluation is saved (When).
分数 数字 Out of 100: 0 is the worst, 100 the best, e.g. 80. Optional — Verdict alone is enough.
判决 选择 好的, 可接受, 贫穷的, 错误的, 有害 good: right and useful; acceptable: usable with small fixes; poor: needed real rework; wrong: incorrect; harmful: would have caused damage if acted on. Kept beside Score; neither is worked out from the other.
评论 长文本 Why, in a sentence — the most useful part for whoever improves the agent.
结果 文本 For What happened next: what became of the work, e.g. accepted or rejected (filled in by Accept it and Reject it).
价值 数字 What that outcome was worth, in the company currency, e.g. the cost saved. Optional.

这里适用的规则

此屏幕上的所有内容均遵循平台规则,而非其自身规则。使用前,您需要了解以下规则:

旁边 评估