Clanker Cloud workspace walkthrough
A product walkthrough showing the main workspace and how operational context moves through it.
Workspace walkthrough
Clanker Cloud workspace walkthrough
Start here: see how context, findings, approvals, and handoffs move through the main Clanker Cloud workspace.
Clanker DevOps
Agnostic workspace for DevOps work
Clanker DevOps gives operators and agents one place to understand infrastructure before they act: cloud resources, Kubernetes state, repos, deploys, cost movement, security exposure, and live context.
It is provider-agnostic by design. Use it to investigate, plan, explain, and prepare reviewed changes across the environments your team already runs.
DevOps work usually fails at the context boundary. Clanker DevOps puts the relevant infrastructure, repo, cost, and security context in the same workspace.
DevOps work
What Clanker DevOps is built for
Incident investigation
Ask what broke, what changed, what is unhealthy, and which resources or deploys are involved.
Deploy planning
Turn an app, repo, or request into a reviewable deploy plan with runtime, secrets, domains, cost, and rollback path.
Cost review
Find spend movement, idle resources, missing tags, expensive paths, and practical savings plans before changing anything.
Security checks
Review exposed surfaces, risky settings, missing auth, public endpoints, and remediation plans with a clear approval boundary.
Kubernetes operations
Inspect pods, services, ingress, rollouts, events, namespaces, and provider context from the same workflow.
Agent handoff
Let Codex, Claude Code, OpenClaw, Hermes, or internal agents ask grounded questions through the local MCP surface.
Demos
Watch the DevOps workflows in motion
Use these demos to see how the same workspace handles FinOps investigation, security review, and deeper research workflows.
FinOps cost investigation
A cost review flow for spend movement, resource context, and reviewed optimization work.
Security scan workflow
A security review flow for exposed services, risky settings, and remediation planning.
Deep infrastructure research
A research workflow for larger estates where the answer needs evidence and a handoff trail.
DevOps screens
Infrastructure, security, Kubernetes, and cost in one workspace
Clanker DevOps uses the same workspace for read-only investigation, evidence gathering, planning, and reviewed action across the operational work that normally lives in separate tools.
The workspace starts from current system context instead of a pasted summary.
Cost movement is easier to review when it sits next to resources, ownership, and change context.
Exposure and auth reviews can produce a remediation plan without jumping straight to writes.
Pods, services, events, and rollout clues can sit beside provider and repo context.
Before and after
From scattered operations to a reviewed DevOps loop
Clanker DevOps is built for the moment before someone changes production: collect facts, understand the blast radius, explain uncertainty, and ask for approval.
Provider agnostic
Use one workspace for cloud providers, Kubernetes, GitHub, local tools, and agent workflows.
Read first
Investigate incidents, deploys, cost spikes, exposure, and drift before generating a plan.
Reviewed changes
Keep apply, delete, publish, and account changes behind explicit review and approval.
Agent compatible
MCP-capable agents can use Clanker Cloud for live context instead of guessing from repo files alone.
Supported providers
Works across the environments teams already run
The current product positioning covers cloud providers, Kubernetes, GitHub, and bring-your-own AI keys from one local operating surface.
Supports ->AWSGCPAzureOracle CloudTencent CloudKubernetesGitHubBYOK
Question to action
The DevOps workflow is ask, inspect, plan, then apply
Start with a grounded question, inspect live context, generate a plan, and only use maker mode when the plan is reviewed.
Query live infrastructure in plain English. Ask about incidents, topology, recent changes, or cost across the providers you already run.
Ground answers in real environment context. Scan resources, trace dependencies, and inspect topology without bouncing between consoles.
Generate a safe plan before changes. See the intended impact before anything is created, modified, or destroyed.
Use maker mode only when you are ready. Gather live context first, then let Clanker Cloud operate inside your safe, sovereign boundary.
Interactive example
Touch the live DevOps example
Explore a multi-service environment, pick a scenario, inspect topology, and see how Clanker DevOps keeps cloud, repo, logs, cost, security, and plan context together.
Copy this example as a real Clanker Cloud import payload and paste it into Import Infrastructure inside the desktop app.
100%
Workflow examples
Seven DevOps workflows Clanker keeps connected
Open the workflow map to see how Clanker DevOps helps with ideas and tickets, repo and build, CI and test, deploy and release, observability and cost, incident response, and automation.
Workflow
A safer DevOps loop
Connect context
Use the machine, profiles, and tools your team already trusts for infrastructure work.
Ask the question
Start with the operator question: why did it fail, what changed, what is exposed, what will this cost, or how should we deploy?
Review the evidence
Clanker DevOps returns the facts, likely cause, confidence, and gaps before suggesting action.
Approve the plan
Only apply, publish, delete, or change accounts after a human reviews the plan and accepts the risk.
Fit
Use Clanker DevOps when the job needs live context
| Job | What Clanker DevOps adds | Boundary |
|---|---|---|
| Broken deploy | Repo, runtime, rollout, logs, cluster, and provider context in one investigation. | No apply until a reviewed plan is approved. |
| Cost spike | Spend movement tied to resources, tags, regions, ownership, and recent changes. | No resize or delete from an analysis answer. |
| Security exposure | Public route, auth, DNS, ingress, and account evidence in one review. | Remediation stays behind approval. |
| Agent question | MCP access to live infrastructure context through Clanker Cloud. | Agents should not receive pasted credentials in chat. |
Trust boundary
Built for infrastructure trust boundaries
Clanker DevOps keeps the trust model close to the operational workflow: private credential custody, bring-your-own AI, agent-managed workflows, and explicit approval before anything changes.
Private by default
Credentials stay on your machine
Run checks against existing cloud accounts and cluster contexts without handing credentials to a hosted SaaS layer.
BYO AI
Bring your own model keys
Use the models you prefer and keep direct cost control instead of paying another token markup layer.
Agents
Can be managed by your agent, or manage your agent
Clanker Cloud can be managed from your own agent workflows, and Clanker Cloud can also manage your agent, so infrastructure context and controlled actions stay inside the tools you already run.
Read-only first
Plan inside your trust boundary
Clanker Cloud checks live context first, generates plans second, and runs work inside your local or private cloud boundary.
Related
Use it with the rest of Clanker Cloud
MCP setup
Connect agent clients to Clanker Cloud for grounded infrastructure work.
Cloud for Agents
Give agents hosted sandboxes before they need production context.
Security model
Review how Clanker Cloud handles local trust, credentials, model calls, and human approval.
FinOps workflow example
Walk through a cost spike investigation from evidence to reviewed next steps.
Local credentials
Read the trust boundary for credentials, model calls, and reviewed actions.
FAQ
Common questions
Is Clanker DevOps tied to one cloud?
No. It is intentionally provider-agnostic so DevOps work can cross cloud accounts, Kubernetes, GitHub, local tools, and agent clients.
Can agents use it?
Yes. Agents can connect through the local MCP workflow or use hosted sandboxes first, depending on whether the task needs live infrastructure context.
Next step
Use Clanker DevOps for the next infrastructure question
Start with read-only investigation, then promote a reviewed plan only when the evidence is clear.