---
title: AI Ops
sidebar_label: Overview
toc_max_heading_level: 2
doc_id: 8c9a69f5-8ed6-4c2d-b407-a705be2c445b
description: >-
  AI Ops in nullplatform: workflows, checklists, action items, and Insights
  that detect problems, gate deploys, and act on their own, all driven from
  your coding assistant.
keywords:
  - AI Ops
  - workflows
  - checklists
  - action items
  - Insights
  - AI plugins
  - governance
  - automation
  - nullplatform
---

import FeatureGrid from "@site/src/components/FeatureGrid";
import LearningPath, { LearningPathRow } from "@site/src/components/LearningPath";

# AI Ops

Checking whether a deploy degraded something, whether a runtime fell behind, whether the bill moved: that work usually lands on one person. AI Ops is the set of nullplatform features that run it continuously, on your own data and under the rules your organization defined.

:::info 🚀 Early release

AI Ops features are in early release and may not be available in your organization yet. If you'd like to try them or want to know more, [reach out to us](https://docs.nullplatform.com/docs/support) and we'll get you set up.

:::

## The pieces

Each feature does one job, and they compose: a workflow detects a problem and opens an action item, a checklist gates the deploy that fixes it, Insights shows how the rollout is going. You describe each piece to your coding assistant, refine it in the UI, and activate it.

<FeatureGrid
  accent="violet"
  items={[
    {
      title: "Set up the AI plugins",
      href: "/docs/ai-ops/ai-plugins",
      icon: "terminal",
      description:
        "Everything below starts from your coding assistant (Claude Code, Kiro, Cursor, and others). Install the plugins once, configure your API key, and describe what you need.",
    },
    {
      title: "Workflows",
      href: "/docs/workflows/",
      icon: "workflow",
      description:
        "Automations that connect action items, the data lake, notifications, agents, and your own tools: scheduled scans, event-driven fixes, and AI analysis where judgment is needed.",
    },
    {
      title: "Checklists",
      href: "/docs/approvals/checklists",
      icon: "checklist",
      description:
        "Approvals that check themselves: rules evaluated by nullplatform, external checks answered by a workflow, and human sign-offs, in front of the actions you choose.",
    },
    {
      title: "Action items",
      href: "/docs/action-items/",
      icon: "box",
      description:
        "Findings with an owner: what's wrong, on which entity, and an AI-suggested fix the team reviews and applies in one click.",
    },
    {
      title: "Insights",
      href: "/docs/insights/overview",
      icon: "chart",
      description:
        "Ask a question in plain language and get a live dashboard. Save and share it so your whole organization works from the same data.",
    },
    {
      title: "AI assistant",
      href: "/docs/ai-assistant/overview",
      icon: "chat",
      description:
        "Ask questions, investigate failures, and generate CLI commands or configurations from the console, with the context of what you're viewing.",
    },
  ]}
/>

## What you can run today

These are the suites nullplatform runs on its own production. Each one has a tutorial you can follow in about half an hour, and every suite is open source in [nullplatform/workflows](https://github.com/nullplatform/workflows).

| Suite | What it does | Start here |
|---|---|---|
| Cost intelligence | Prices every Kubernetes scope daily, turns real waste into right-sizing suggestions, and verifies the savings | [Right-size Kubernetes workloads](/docs/tutorials/cost-optimization) |
| Runtime lifecycle | Keeps a catalog of AWS Lambda runtimes from the AWS docs and opens a migration item per affected scope | [Migrate deprecated Lambda runtimes](/docs/tutorials/lambda-runtime-lifecycle) |
| AMI rollout | Detects scopes running an outdated image and tracks the rollout with self-closing action items | [Detect and roll out AMI updates](/docs/tutorials/ami-drift) |
| Smart checklists | Gates deploys on a Jira ticket, an AI architecture audit, or a risk score that decides who approves | [Gate deploys on a Jira ticket](/docs/tutorials/jira-approval-gate), [Audit every deploy against your architecture rules](/docs/tutorials/ai-architecture-compliance), [Match approval friction to deploy risk](/docs/tutorials/deploy-risk-matrix) |
| Deploy analysis and library inventory | Scores the risk of every deployment and records what each deployed asset depends on | The `deploy-analysis` and `lib-inventory` suites in [nullplatform/workflows](https://github.com/nullplatform/workflows) |

## Learning paths

<LearningPathRow>
  <LearningPath
    title="From hello world to a working AI Ops suite"
    steps={[
      {
        label: "Set up the AI plugins",
        href: "/docs/ai-ops/ai-plugins",
        note: "Install the plugins in your coding assistant and run a first prompt.",
        time: "10 min",
      },
      {
        label: "Your first workflow",
        href: "/docs/workflows/getting-started",
        note: "Describe a hello world, run it, activate it. The full loop in minutes.",
        time: "10 min",
      },
      {
        label: "Roll out AMI updates",
        href: "/docs/tutorials/ami-drift",
        note: "The simplest scan-and-track suite: nightly detection and self-closing action items.",
        time: "25 min",
      },
      {
        label: "Right-size Kubernetes costs",
        href: "/docs/tutorials/cost-optimization",
        note: "Price every scope daily and turn real waste into one-click savings.",
        time: "30 min",
      },
    ]}
  />
  <LearningPath
    title="Gate deploys with checklists"
    steps={[
      {
        label: "Your first checklist",
        href: "/docs/approvals/your-first-checklist",
        note: "Describe a two-item gate, dry-run it, and watch it govern a real deploy.",
        time: "10 min",
      },
      {
        label: "Gate deploys on a Jira ticket",
        href: "/docs/tutorials/jira-approval-gate",
        note: "A person decides, Jira mediates: approvals in the tool your team already uses.",
        time: "20 min",
      },
      {
        label: "Match friction to deploy risk",
        href: "/docs/tutorials/deploy-risk-matrix",
        note: "A risk matrix scores every deploy and routes it to exactly the approval it deserves.",
        time: "25 min",
      },
      {
        label: "AI architecture compliance",
        href: "/docs/tutorials/ai-architecture-compliance",
        note: "An agent audits every deploy against your architecture rules.",
        time: "25 min",
      },
    ]}
  />
</LearningPathRow>

## Automation & control

The building blocks the suites above stand on. Each one is useful on its own, and every workflow reaches for at least one of them.

<FeatureGrid
  accent="green"
  items={[
    {
      title: "Data lake",
      href: "/docs/data-lake/",
      icon: "database",
      description:
        "Query the state of your entire organization with SQL: applications, deployments, scopes, approvals, and more, all in one queryable place.",
    },
    {
      title: "Approvals",
      href: "/docs/approvals/",
      icon: "shield",
      description:
        "Define policies that require a human sign-off before sensitive actions run, like production deployments or secret access.",
    },
    {
      title: "Notifications",
      href: "/docs/notifications/",
      icon: "bell",
      description:
        "Route platform events to Slack, webhooks, or your own services, and filter them so each team only gets what it needs.",
    },
    {
      title: "Entity hooks",
      href: "/docs/entity-hooks/",
      icon: "hook",
      description:
        "React to entity changes with your own logic: enforce naming rules, update repositories, or trigger external systems when something changes.",
    },
  ]}
/>

Also see [AI usage and quotas](/docs/ai/ai-usage) to monitor AI consumption across your organization.