Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.anyshift.io/llms.txt

Use this file to discover all available pages before exploring further.

​
Natural language infrastructure queries

Annie Knowledge turns your infrastructure data into a queryable assistant. Ask in plain English. Get an answer in seconds. Annie understands context. Ask “Why can’t I access this RDS?” and Annie traces security groups, IAM policies, VPC configurations, and network ACLs to find the actual blocker. No console-hopping required.

​
Versioned graph backbone

The answers run on a versioned graph spanning cloud, code, containers, and monitoring. State is queryable across the last 7 days. Updates land in near real-time, typically within 60 seconds of a control-plane change. The methodology is documented in Agentic Context Engineering, accepted at ICLR 2026. The same loop runs in production today.

​
Connected data sources

Annie correlates data from all your connected integrations:
Source TypeExamplesWhat Annie Knows
Cloud ProvidersAWS, GCPLive resource state, configurations, relationships
Infrastructure as CodeGitHub, GitLab reposTerraform modules, resource definitions, variables
Terraform StateS3, HCP TerraformActual deployed state, outputs, dependencies
MonitoringDatadogMonitors, dashboards, host mappings
ContainersKubernetesPods, deployments, services, RBAC

​
Cross-source graph correlation

Annie’s real power comes from correlating across these sources. Ask questions like:
  • “Show me EC2 instances that exist in AWS but aren’t in Terraform”: finds orphaned resources
  • “Which Datadog monitors are watching this EC2 instance?”: links cloud to monitoring
  • “What Terraform module manages this Kubernetes deployment?”: traces code to containers
The drift query alone is hard to answer without Annie. Terraform state tracks declared resources. AWS console shows actual resources. Reconciling the two manually means exporting state, listing live resources, and diffing. Annie returns the diff in one query.

​
Onboarding context

  • “What are our core services and how are they connected?”
  • “Who is responsible for the payment service?”
  • “What dashboards should I bookmark for on-call?”
  • “Draw a map of our cloud architecture”
  • “What changed in production in the last 2 hours?”
  • “Show me the history of this RDS instance since yesterday”
  • “Which services depend on the database that’s having issues?”
  • “Why can’t the API reach the database?”
  • “What would be affected if I update this security group?”
  • “List all resources that depend on this VPC”
  • “Which Terraform modules reference this IAM role?”
  • “Show me the blast radius for this change”
  • “List all S3 buckets with public access”
  • “Which IAM roles have admin privileges but no MFA?”
  • “Find security groups allowing 0.0.0.0/0 on port 22”
  • “Are there any unencrypted databases?”
  • “Which EC2 instances aren’t managed by Terraform?”
  • “Find resources without cost-center tags”
  • “List idle resources in the staging environment”
  • “What GPU instances do we have running?”

​
Pre-change blast radius

Change-impact queries run against the live graph. Ask “what depends on this security group?” and Annie traverses dependents across EC2, RDS, ELB, and Lambda VPC configs. The same traversal underpins AWS IAM best practices on least-privilege scoping: you cannot scope safely without knowing the full dependency set.

​
Tag and cost queries

Untagged resources are the dominant source of cost-allocation drift. AWS tagging best practices recommends mandatory tags on every billable resource. Annie surfaces untagged resources in one query: “Find resources without cost-center tags.” The same query type catches drift in Kubernetes RBAC: “Which service accounts have cluster-admin?” and “Which roles haven’t been bound in 30 days?“

​
7-day state history

Every node in the graph is versioned. Ask about state at any point in the last 7 days. “What did the security group look like yesterday at 14:00?” returns the exact configuration, not a reconstruction.

​
How to access Annie

Slack

Ask Annie questions directly in Slack. Just mention @Annie with your question.

MCP (IDE Integration)

Access Annie from your AI coding assistant while you work.

​
Operational benefits

Instant Answers

Get answers in seconds instead of hours of manual investigation across consoles.

Always Current

Annie continuously syncs with your infrastructure, with no stale documentation.

Complete Context

Understand relationships across cloud, code, containers, and monitoring in one query.

7-Day History

Ask about infrastructure state at any point in the last 7 days.

​
Get Started

Create Account

Sign up for Anyshift

Request Demo

See Annie Knowledge in action