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.

🚀 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 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.

Set up the AI pluginsEverything 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.WorkflowsAutomations 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.ChecklistsApprovals that check themselves: rules evaluated by nullplatform, external checks answered by a workflow, and human sign-offs, in front of the actions you choose.Action itemsFindings with an owner: what's wrong, on which entity, and an AI-suggested fix the team reviews and applies in one click.InsightsAsk a question in plain language and get a live dashboard. Save and share it so your whole organization works from the same data.AI assistantAsk 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.

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
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
AMI rollout	Detects scopes running an outdated image and tracks the rollout with self-closing action items	Detect and roll out AMI updates
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, Audit every deploy against your architecture rules, Match approval friction to deploy risk
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

Learning paths

From hello world to a working AI Ops suite

1. 1Set up the AI pluginsInstall the plugins in your coding assistant and run a first prompt.10 min
2. 2Your first workflowDescribe a hello world, run it, activate it. The full loop in minutes.10 min
3. 3Roll out AMI updatesThe simplest scan-and-track suite: nightly detection and self-closing action items.25 min
4. 4Right-size Kubernetes costsPrice every scope daily and turn real waste into one-click savings.30 min

Gate deploys with checklists

1. 1Your first checklistDescribe a two-item gate, dry-run it, and watch it govern a real deploy.10 min
2. 2Gate deploys on a Jira ticketA person decides, Jira mediates: approvals in the tool your team already uses.20 min
3. 3Match friction to deploy riskA risk matrix scores every deploy and routes it to exactly the approval it deserves.25 min
4. 4AI architecture complianceAn agent audits every deploy against your architecture rules.25 min

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.

Data lakeQuery the state of your entire organization with SQL: applications, deployments, scopes, approvals, and more, all in one queryable place.ApprovalsDefine policies that require a human sign-off before sensitive actions run, like production deployments or secret access.NotificationsRoute platform events to Slack, webhooks, or your own services, and filter them so each team only gets what it needs.Entity hooksReact 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 to monitor AI consumption across your organization.