Skip to main content

​
Evidence you can ship on

AI agents often stall between build and production: security and compliance want proof; the business wants to move. Without shared, objective evidence, approvals turn into opinion-based negotiation. This page explains how Vijil helps both sides, then walks through the console: register an agent, run an evaluation, read your Trust Report, and configure Dome guardrails.
If you integrate via APIs and code, use the Developer Guide. This guide focuses on the Vijil console.

​
Who this is for

Business owner

Ship agents that deliver value with fast evaluation cycles, clear pass/fail criteria, and reports stakeholders can use without endless ad hoc testing.

Risk owner

Approve with quantified reliability, security, and safety; versioned, audit-style artifacts; and visibility into residual risk and compensating controls.

​
One metric both sides can use

Business ownerRisk owner
PressureDelivery speedRisk reduction
Question“Can we ship?”“Can I defend approving this?”
Vijil aligns those questions with the Trust Score, a reproducible score from a defined harness, not a one-off opinion. Agree on the threshold before you test; compare results after; the decision gets clearer. Vijil measures reliability, security, and safety, the failure modes that look like “the model behaved” but still hurt users or the org. For detail on each dimension, see Trust Score in Concepts.

​
Console walkthrough

You will register the agent, run an evaluation (built-in Trust Score harness or a custom harness), read the report, then protect the agent with Dome.

​
1. Register your agent

Open Agents → + Register Agent.
Agent Registry showing registered agents with status and Trust Score
Register Agent modal with Black Box, Grey Box, and White Box options
LevelYou provideVijil can test
Black BoxDescription, endpoint, credentialsInput/output behavior
Grey BoxModel / MCP / A2A configurationIssues tied to composition
White BoxFull config and sourceDeeper audit-style analysis
For most agents, start with Black Box: name, description, Draft status, Agent URL, access key, and rate limit; then Register Agent.
If the agent uses sub-agents or MCP tools, use Grey Box fields so Vijil can exercise the full graph.

​
2. (Optional) Custom harness

For a baseline, you can skip this and use the Trust Score harness in the next step. To test your personas and org policies, go to Harnesses → + Create Harness. The wizard covers basic info, agent, personas (who talks to the agent), and policies (rules it must follow); then generates test cases.
Create Harness wizard showing the four-step configuration flow
Set the harness to Active when you are ready. More depth: Custom harnesses, Personas, Policies.

​
3. Run an evaluation

Open Evaluations. Pick the agent and a harness:
  • Trust Score: all three dimensions at once (toggle dimensions if you need a narrower run).
  • Custom: the harness you configured above.
Diamond Evaluations page showing agent selection and Trust Score dimensions
Run Evaluation and wait for completion (often on the order of minutes, depending on rate limits).

​
4. Read the Trust Report

Open the report from the results list. You get a Trust Score (pass/fail threshold is typically 0.70), per-harness breakdown, spec used, and remediation-oriented findings.
Trust Report showing agent evaluation results with Trust Score
ScoreReadTypical next step
≥ 0.70PassShip with normal monitoring
0.50–0.69MarginalStrongly consider Dome and extra monitoring
Below 0.50FailRemediate before production
The score reflects what the harness exercised, not a guarantee that every possible failure is impossible.

​
5. Configure Dome

Open Guardrails. Domed vs Unprotected shows coverage. Configure Guardrails opens input and output pipelines (e.g. security, moderation, privacy). Add guards, choose early exit where it makes sense, and use Execution Flow with sample prompts to verify behavior.
Dome Guardrails dashboard showing agent protection status
Dome configuration showing input and output guards
Execution Flow showing a test prompt flowing through Security, Moderation, and Privacy guards
Save when the pipeline matches your policy. Ongoing monitoring: Observability.

​
6. Wire Dome in your app

Use the SDK so traffic passes through Dome before and after your model: 
from vijil import Dome

dome = Dome(
    api_key="your-vijil-api-key",
    agent_id="your-agent-id"
)

safe_input = dome.guard_input(user_message)
safe_output = dome.guard_output(agent_response)

​
Next steps

Account setup

Workspace, access, and team

Run evaluations

Deeper evaluation workflows
Last modified on April 14, 2026