Skip to main content

What is Console?

Console is Amplify Security’s AI harness for security work. It supplies the machinery — LLM orchestration, tool execution, isolated sandboxes, sub-agent delegation — and you supply the domain logic: the agents that reason, the skills they follow, and the detections they enforce. Teams get the most out of Console by writing their own agents and detections — encoding the security questions that matter for their codebase and their stack, then pointing those agents at them.
Console is currently in alpha, undergoing rapid development. Contact support@amplify.security if you would like to try it out and work with us to help our project come to fruition!

Three ideas

Everything in Console fits into one of three layers, and they build on each other in this order.

Agents & detections

The agents, skills, and detections that do the work. All of them are yours to write.

Data & connections

Repositories and vendor connections, so agents reason about your actual environment.

Workflows

Chain agents into automation that runs on every pull request and produces real artifacts.

1. Agents and detections

An agent is a Markdown file with YAML frontmatter: the frontmatter declares its name, model, and which tools it may use, and the body is its instructions. That’s the whole format — you write an agent in a text editor, and it runs. Agents delegate to sub-agents, load skills for specialized procedures, and run detections — reusable rules that outlive any single conversation. Console ships a library of agents and skills to start from; detections are yours to build up as you go. Anything you write sits alongside the built-ins as an equal.

2. Data and connections

An agent with nothing to look at is just a chatbot. Console draws on two sources:
  • Projects — the repositories it clones and reads.
  • Connections — your source control provider, plus the security and IT vendors you already run, added from the connector catalog.
You put that to work two ways: interactively in chat, or declaratively in a workflow.

3. Workflows

Workflows are where it comes together. A workflow chains agents into an ordered sequence, fires on the triggers you configure, and routes whatever it produces to the outputs you attach. Run one on demand, or let events in your connected systems start it for you.

Two interfaces

The same agents run in both places. What differs is where they run and what code they can reach. See Chat and The CLI for the differences in detail.

Get started

Quickstart

Connect a repository, ask an agent a question, and build your first workflow.

Install the CLI

Run Console in your terminal on Linux or macOS.