Skip to main content

​
Assessments

An assessment is a structured evaluation that measures a candidate’s ability to use AI tools effectively for knowledge work. Think of it as a realistic work sample test - but instead of a whiteboard coding exercise, candidates produce real deliverables with AI assistance.

​
What’s in an assessment?

Each assessment contains:
  • Phases: A fixed three-phase model set by Gradient (see below). Gradient sets the Task phase. The Explore and Reflection phases are fixed.
  • Task brief: The realistic work prompt for the Task phase (for example, “Create a product strategy deck for entering the European market”).
  • Deliverable type: The output format the candidate produces: presentation (pptx), document (docx), email, or an AI workflow.
  • Connectors & data: The data sources a candidate’s AI can search (some useful, some distractors). Gradient configures them. See Connectors.
  • Candidate permissions: What candidates may do during the assessment (see Candidate permissions).
  • Admin guide: Reviewer-facing notes (overview, what good looks like, pitfalls, buried info) that calibrate scoring.
  • Scoring rubric: The criteria used to evaluate the candidate’s work. See Scoring.

​
The phase model

Every assessment runs on the same fixed three phases. Gradient sets the shape so results stay comparable across candidates and assessments. Explore is an ungraded orientation window. Task is the graded work Gradient designs for you. Reflection, when enabled, asks a locked, identical prompt so reflections are comparable. See Candidates & Sessions for the candidate’s view.

​
Assessment lifecycle

1

Gradient builds it

You add a role and email hi@trygradient.ai. The Gradient team builds the assessment by hand: the task brief, the data, and the rubric. Then Gradient adds it to your workspace.
2

Active

The assessment is ready to accept candidates. You can invite people and they’ll receive unique links. You can change settings such as the name, the due date, and feedback. You cannot edit the content.
3

Scoring

After candidates submit, the scoring engine evaluates their work automatically.
4

Review

You review scores and adjust if needed.

​
Signal vs. noise

A key feature of Gradient assessments is the signal/noise pattern in data sources. Gradient marks some documents in an assessment as signal (relevant to the task) and others as noise (distractors). This tests whether candidates can identify which information actually matters - a critical AI fluency skill.
A good assessment has a healthy mix of signal and noise. Too little noise makes the task trivial; too much makes it frustrating.

​
Candidate permissions

Each assessment controls what candidates may do in their workspace. There are three permissions: These govern the AI workspace. See connectors for how candidates use connectors, which have no permission of their own. The table above maps to the candidate_permissions object in the Assessments API. Whether candidates can read the data files is no longer a choice. They always see them in the workspace Files cabinet.