Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.vijil.ai/llms.txt

Use this file to discover all available pages before exploring further.

This guide walks from a fresh installation to a completed trust evaluation. You will install the CLI, connect it to your Console deployment, register an Agent, run an evaluation, and retrieve the results.

​
Prerequisites

  • Python 3.8 or later
  • A Vijil Console deployment and its API gateway URL
  • An API key for the AI model you want to Evaluate

​
Steps

1

Install the CLI

Install vijil-console via pip or pipx:
pip install vijil-console
Verify the installation:
vijil --help
2

Configure and Log In

Point the CLI at your Console API gateway:
vijil auth init --url https://console-api.example.com
Then log in with your account credentials:
vijil auth login
You will be prompted for your email and password. The CLI stores your token in ~/.vijil/config.yaml.If you belong to multiple teams, select the one you want to work with:
vijil team list
vijil team use <team_id>
Every subsequent command uses the active team automatically — you do not need to pass a team ID manually.
3

Register an Agent

Create an Agent configuration for the model you want to evaluate. Export your provider API key first to keep it out of your shell history:
export OPENAI_API_KEY="sk-..."

vijil agent create \
  --agent-name "My Chat Agent" \
  --model-name "gpt-4o" \
  --agent-url "https://api.openai.com/v1/chat/completions" \
  --api-key "$OPENAI_API_KEY"
The output includes the new Agent’s id. Save it:
export AGENT_ID="a1b2c3d4-..."
To confirm the Agent was registered:
vijil agent list
4

Choose a Harness

Harnesses are test suites that cover a specific trust dimension. List the available standard Harnesses:
vijil harness list
Output:
NAME        UPDATED_AT
safety      1712505600
security    1712505600
reliability 1712505600
privacy     1712505600
toxicity    1712505600
ethics      1712505600
For this quickstart you will run safety and security.
5

Run an Evaluation

Start an evaluation and wait for it to complete:
vijil eval run \
  --agent-id "$AGENT_ID" \
  --harness-names '["safety", "security"]' \
  --sample-size 50 \
  --wait
--sample-size 50 runs 50 Probes per Harness — enough for a meaningful score in a few minutes. Omit it to run the full Harness (~1,250 Probes for security).The CLI polls every 5 seconds and prints progress. When complete, it prints the evaluation ID. Save it:
export EVAL_ID="e5f6a7b8-..."
6

View the Results

Retrieve your Trust Score and per-Harness breakdown:
vijil eval results-detail "$EVAL_ID"
This returns scores per Harness (0 to 1), individual Probe results, and identified failure patterns.To filter with jq:
vijil eval results-detail "$EVAL_ID" --json | jq '.scores'
7

Generate a Report

Trigger a Trust Report for the completed evaluation:
vijil eval report "$EVAL_ID"
The report summarizes what was tested, how the Agent scored, and where it failed. Download it as HTML or PDF from the Console.

​
Next Steps

Setup Reference

Auth and team management commands

Agents Reference

Create, update, and manage Agents

Evaluate Reference

Harnesses, evaluations, and results

Protect Reference

Configure Dome Guardrails
Last modified on May 19, 2026