Quickstart

You’ve already seen Veris work in the console with an example agent. This page walks through the same flow with your own agent: submit your repo, let Veris generate the sandbox config, then generate scenarios, run simulations, and produce a report.

Onboarding is managed: you run veris env submit, the platform generates .veris/veris.yaml and .veris/Dockerfile.sandbox, builds your image, healthchecks it, and a Veris engineer releases the env to you. One command on your side.

Prerequisites

An agent with a real production interface: HTTP, WebSocket, email, CLI (for cron-driven or single-shot commands), or a callable Python/Node function exposed as part of its public API (for agents triggered by webhooks, schedules, or other agents). Veris talks to your agent through the same interface it uses in production, not through a wrapper.
Docker running locally.
Python 3.11+ (for the CLI).

Install and authenticate


uv tool install veris-cli     # or: pip install veris-cli
veris login

veris login opens a browser for Google OAuth. For CI, pass an API key: veris login $VERIS_API_KEY.

Onboard your agent

Submit your repo

From your agent’s root directory:


veris env submit

This packages your repo (skipping .git and anything in .dockerignore), uploads it, and starts managed onboarding.

You’ll receive an email when the env is ready, typically within two business days.

While your environment is being set up, the console labels it with a “Setting up” badge. You can configure Datasets, Documents, Service Requests, and Variables right away. Scenarios, simulations, and reports unlock once setup finishes.

Add or update runtime env vars

At least one LLM provider key is required for your agent to run during onboarding and simulations. The submit step prompts for these inline; use the command below if you skipped that prompt or need to add more keys later.


veris env vars set OPENAI_API_KEY=sk-... --secret
veris env vars set ANTHROPIC_API_KEY=sk-ant-... --secret

Always pass --secret for credentials. All keys are stored securely and encrypted at rest. Non-secret defaults belong in the generated agent.environment block in veris.yaml (visible after release).

Pull the generated config and iterate

Once your env is ready:


veris env config pull   # writes .veris/Dockerfile.sandbox + .veris/veris.yaml into your repo
veris env push          # build a new image tag locally, upload, register

Commit the pulled files to your version control. They’re the source of truth for future iterations. After that, veris env push is the routine code-change loop.

What the generated config looks like

veris.yaml and Dockerfile.sandbox follow the same shape the platform produces for everyone. There’s nothing custom about the format. If you want to read or tweak them after release:

veris.yaml: services, actor channel, agent entry point. See veris.yaml reference and the services catalog. Working examples: cookbook .
Dockerfile.sandbox: extends the Veris base image with your agent’s code and deps. See Dockerfile reference.

Want to understand what these pieces mean before running them? Read Environment, Scenario, Simulation, Evaluation, Report.

Generate scenarios


veris scenarios create
veris scenarios status <SET_ID> --watch

Async job. Explores your repo, infers what the agent is supposed to do, produces test cases plus a matching grader. 2–5 minutes for a small agent.

Run the loop


veris run

Interactively: pick the scenario set, watch simulations run, watch the evaluation, optionally generate a report. veris run chains simulations → evaluations → report in one command. For non-interactive / CI use, pass flags:


veris run \
  --scenario-set-id <SET_ID> \
  --grader-id <GRADER_ID> \
  --report

You can also run each step on its own: veris simulations create, veris evaluations create, veris reports create.

What’s next

Iterate on your agent → Development loop. The simulate → fix → re-simulate cycle, with tips on reading reports.
Framework-specific notes → Frameworks. If you’re on LangGraph Platform, Vercel AI SDK, or hit a framework-specific snag, start here.
See the other use cases → Use Cases. CI regression gating, RL training, SFT training, regulatory QA.
Reference material → veris.yaml schema, CLI commands, services catalog.

Need help with a tricky integration? Managed onboarding handles the standard cases. For agents with custom service mocks, bundled infrastructure, or unusual frameworks, reach out about enterprise support. Our team can hand-tune .veris/ for you.