Cuiar
Sign inDownload

Review take-home assignments with your rubric

Each submission scored against your rubric, with evidence from the code or document for every score.

  • You start it: When you start it
Use in CuiarRun from your AI agent

What it does

The task

Read the rubric in the Google Doc rubric doc. Open each submission in this list, and use the candidate IDs, not the names: submissions. Read the code, the README and the tests on GitHub, or the document for tasks with no code. Score each rubric item from 1 to 4 with a short quote or a file name as evidence, and note what you could not check, such as code that must run. Write the scores in a table with one row per candidate. Score only what the rubric asks for.

  • It works in GitHub and Google Docs, in the workspace you pick, and signs in with passwords from your Cuiar vault.
  • It runs once, when you start it.

What you give it

BlankWhat to giveExample
rubric docThe Google Doc with your rubrichttps://docs.google.com/document/d/1RubricRefundAPI
submissionsEach candidate ID with the link to the submissionC-104: github.com/brightleaf-hiring/c104, C-109: github.com/brightleaf-hiring/c109, C-112: github.com/brightleaf-hiring/c112

What you get back

An example run with the example values above. Your run uses your own data.

Take-home task: refund API. 3 submissions, rubric of 5 items, 20 points

CandidateDesignCorrectnessTestsReadabilityDocsTotal
C-1044343317
C-1093324214
C-1122413414

C-104, Tests: "tests/refund_test.go covers partial and double refunds"

C-112, Tests: one test file, happy path only

Not checked: run time and the Docker setup, because the code must run

Run it in Cuiar

  1. 01

    Open it

    Click Use in Cuiar on this page. The side panel opens with the task in the composer.

  2. 02

    Fill in 2 blanks

    Type rubric doc and submissions. Tab moves to the next blank.

  3. 03

    Run it

    Run sends it to the agent. Follow each step in the panel, and stop it at any time.

From the terminal

cuiar exec "Read the rubric in the Google Doc https://docs.google.com/document/d/1RubricRefundAPI. Open each submission in this list, and use the candidate IDs, not the names: C-104: github.com/brightleaf-hiring/c104, C-109: github.com/brightleaf-hiring/c109, C-112: github.com/brightleaf-hiring/c112. Read the code, the README and the tests on GitHub, or the document for tasks with no code. Score each rubric item from 1 to 4 with a short quote or a file name as evidence, and note what you could not check, such as code that must run. Write the scores in a table with one row per candidate. Score only what the rubric asks for."

Run it from your AI agent

Claude Code, Codex, Cursor and other MCP clients reach Cuiar at https://mcp.cuiar.com/mcp. Add the server one time, then ask for the task in plain words, or call run_task yourself.

1. Add Cuiar to Claude Code

claude mcp add --transport http cuiar https://mcp.cuiar.com/mcp

2. Ask your agent

Use the Cuiar tool run_task to run my "Review take-home assignments with your rubric" template with rubric doc = https://docs.google.com/document/d/1RubricRefundAPI; submissions = C-104: github.com/brightleaf-hiring/c104, C-109: github.com/brightleaf-hiring/c109, C-112: github.com/brightleaf-hiring/c112.

Setup for other agents: AI agents.

The tool call

{
  "name": "run_task",
  "arguments": {
    "task": "Read the rubric in the Google Doc https://docs.google.com/document/d/1RubricRefundAPI. Open each submission in this list, and use the candidate IDs, not the names: C-104: github.com/brightleaf-hiring/c104, C-109: github.com/brightleaf-hiring/c109, C-112: github.com/brightleaf-hiring/c112. Read the code, the README and the tests on GitHub, or the document for tasks with no code. Score each rubric item from 1 to 4 with a short quote or a file name as evidence, and note what you could not check, such as code that must run. Write the scores in a table with one row per candidate. Score only what the rubric asks for."
  }
}

Related templates

All recruiting templates