Governed AI operations, explored by capability.
Build repeatable AI-assisted workflows, keep configuration reviewable, bind the policies and guardrails that constrain each step, authorize every runtime resource, execute on isolated runners, and preserve evidence from signal to outcome.
Seven capabilities, one operating model.
Each topic covers the execution model, the standard primitives, a Git-owned example and the controls that matter for enterprise rollout.
01 · Workflow orchestration
Combine scripts, LLM goals, approvals, reusable steps and child pipelines without splitting the operating model.
02 · GitOps configuration
Manage pipelines, scopes, access, knowledge, profiles, triggers and runtime defaults as versioned configuration.
03 · Governance and AAA
Apply default-deny access decisions before configuration reads, tool use, secret resolution, approvals and dispatch.
04 · AI and MCP
Select controlled agent, LLM and MCP profiles per pipeline or step while preserving permission-bound tool discovery.
05 · Knowledge and context
Write the guardrails, policies, ADRs, runbooks and architecture notes that bound AI work, and decide which of them constrains which step.
06 · Runtime and execution
Dispatch per-run agents to Docker or Kubernetes runners using scope, capacity, affinity, routing and runtime pools.
07 · Evidence and monitoring
Connect run history, system logs, outputs, AI usage, reliability, security, cost, alerts and recommendations.
One path from intent to evidence.
NopsAI connects control-plane decisions and data-plane execution without turning AI work into a separate, ungoverned system.
Normalize intent
Git, schedules, APIs, manual actions and external services enter one request model.
Resolve permission
AAA, scope, secrets, profiles and the knowledge bound to each step are resolved before dispatch.
Execute in isolation
The dispatcher selects an eligible Docker or Kubernetes runner for a per-run agent.
Keep the evidence
Logs, task state, approvals, AI usage and outputs remain attached to the run.
What the operator actually sees.
Configuration is Git-owned, but the operating surface is a product: teams, runs, approvals, profiles and evidence in one place.
Bring one workflow. We will map its controls, runtime, and evidence with you.
The fastest way to evaluate NopsAI is a single real workflow you already run manually and cannot safely hand to an unrestricted agent.