Preview — now available

Your cloud,
on command

Cloud Agent is a chat-oriented AI platform for running intelligent agents against your cloud infrastructure. Describe a task in plain language — the agent plans and executes it.

Start for free See how it works

Cloud Agent — AWS Prod / Production

List all S3 buckets and flag any that have public access enabled.

✓

Classified request as discovery + audit

✓

Planned 3 parallel steps

✓

s3:ListBuckets (us-east-1)

✓

s3:GetBucketPublicAccessBlock × 14

◉

Synthesising results

Found 14 buckets in us-east-1. 2 have public access enabled:

⚠ prod-assets-cdn — ACL allows public-read
⚠ legacy-exports-2021 — bucket policy allows s3:GetObject for *

Generate a remediation plan for the flagged buckets

Platform capabilities

Everything you need to operate your cloud at the speed of thought

From one-off queries to recurring automated audits — Cloud Agent handles the full lifecycle of cloud operations through a single conversational interface.

Chat-first interface

Describe any cloud operation in plain language. No scripts to write, no API docs to read. The agent understands intent and acts accordingly.

Projects & Sandboxes

Organise work by team or application domain. Each sandbox holds its own credentials, templates, and run history — fully isolated and reusable.

Templates

Save and reuse any prompt as a template. Run on demand or schedule it to fire automatically — perfect for recurring audits or daily reports.

Scheduled runs

Automate template execution with cron expressions. Hourly, daily, weekly, or any custom schedule. Overlapping runs are skipped automatically.

Resource inventory

A live, searchable inventory of every resource the agent has discovered. Dependency graphs reveal blast radius before you make changes.

Credential vault

All credentials stored encrypted, never exposed in plaintext. Gateway tokens let external tools call Cloud Agent's AI gateway in OpenAI-compatible format.

Execution model

From prompt to answer in real time

Every turn follows a structured pipeline. Watch each phase stream in as the agent works — no black box.

Classifying

Analyses your request and determines the best approach before doing anything.

Clarifying

Asks follow-up questions when context is ambiguous — avoids wrong assumptions.

Planning

Generates a numbered, step-by-step execution plan visible to you before execution.

Executing

Steps run in order; parallelisable steps execute concurrently. Progress streams in real time.

Answering

Results are synthesised into a clear, structured response with full step context.

Resource inventory

Your full infrastructure, organised and searchable

Cloud Agent automatically discovers and catalogues every resource it encounters. Drill into any resource to see raw metadata, inbound and outbound dependencies, and blast-radius graphs.

Hierarchical tree: provider → account → region → type → resource

Instant search by name, ID, or resource type

Dependency graph for understanding connectivity and risk

Populate via chat: "discover all resources in us-east-1"

▾ AWS └── 123456789012 (prod) └── us-east-1 ├── EC2 │ ├── i-0abc123 web-server-1 │ ├── i-0def456 web-server-2 │ └── i-0ghi789 bastion (public) ├── S3 │ ├── prod-assets-cdn │ ├── legacy-exports-2021 │ └── terraform-state ├── RDS │ └── db-prod-postgres14 └── Lambda ├── payments-handler └── notifications-worker ▾ Azure └── sub-analytics (staging) └── eastus └── VMs └── analytics-vm-01

Templates & Schedules

Turn any prompt into a repeatable workflow

Save your most useful prompts as templates. Run them manually or schedule them to execute automatically with cron — no extra tooling, no YAML pipelines.

System templates for common tasks, ready to run

Custom templates with full agent prompt control

Hourly, daily, weekly, or any custom cron expression

Overlap protection — concurrent runs are automatically skipped

Daily S3 Audit — Prod

// Schedule: 0 8 * * *  (every day at 08:00 UTC)
template: "S3 Public Access Audit"
sandbox:  "AWS Prod"
status:   active

// Last run: today at 08:00 UTC
result:   2 buckets flagged
tokens:   1,842 used
duration: 14.3s

Weekly Cost Report

// Schedule: 0 9 * * 1  (every Monday at 09:00 UTC)
template: "Cross-Account Cost Summary"
sandbox:  "GCP Analytics"
status:   active

Security

Built for teams that need to trust their tooling

Cloud Agent is designed around the principle that credentials and access should be explicit, encrypted, and auditable at every layer.

Encrypted at rest

All credentials encrypted in storage, never exposed in plaintext after creation.

MFA & passkeys

TOTP, WebAuthn passkeys, and magic-link login for strong authentication.

Role-based access

Admin and Member roles. Members only see the projects and sandboxes they are invited to.

Activity audit log

Full event history: logins, config changes, credential updates, and member invites.

Gateway tokens

Sandbox-scoped bearer tokens in OpenAI-compatible format. Revoke individually at any time.

Sandbox isolation

Each sandbox is a fully isolated execution context — credentials and runs don't bleed across boundaries.

Pricing

Start free, scale as you grow

Cloud Agent uses a credit system for AI execution. You bring your own provider keys — credits cover the platform's cost to orchestrate and run agent turns.

Starter

Free forever

1 project, 2 sandboxes

500 monthly credits

5 templates

Community support

Get started free

Pro

Your cloud, on command