TRANXACT.AI Help
Agentic AI › Assess

Evaluations

Whether the agent was any good — graded by a person, by another agent, or by what happened to what it produced. A proposal accepted and still standing thirty days later is the strongest signal this table can carry.

Where to find it

  1. Module: Agentic AI
  2. Group: Running
  3. Section: Assess
  4. Screen: Evaluations

Address in the console: /agentic/evaluations

List · 11 columns · 9 fields on its form

What the list shows

These are the columns of the list, in the order they are drawn. Any of them can be sorted on, filtered on, hidden, or exported.

ColumnKindField name
WhenDate and timeevaluated_at
AgentTextagent_name
RunCoderun_no
Graded byStatusevaluator
PersonTextevaluator_name
OnTextcriterion
ScoreNumberscore
VerdictStatusverdict
OutcomeStatusoutcome_kind
ValueAmountoutcome_value
CommentTextcomment

The form

What is asked for when a record is created here. Required fields are marked; a choice drawn from a configuration list is one an administrator can extend without a release.

FieldTypeChoicesNotes
Run Choice Looked up from existing records
Agent Choice Looked up from existing records
Graded by Choice Configuration list
On Text
Score Number
Verdict Choice good, acceptable, poor, wrong, harmful
Comment Long text
Outcome Text
Value Number

The rules that apply here

Everything on this screen obeys the platform rules rather than rules of its own. The ones worth knowing before you use it:

Beside it in Assess