Natural Language Queries
Ask questions about your infrastructure in plain English. RedQueen translates your questions into Prometheus queries, OpenSearch searches, and Kubernetes API calls.
How It Works
@mention RedQueen in any Slack channel to start a conversation.
Ask a Question
@RedQueen what's the average response time for the API?
AI Processing
Claude analyzes your question, selects appropriate tools, and generates queries.
Streaming Response
Results stream back to Slack with visualizations and context.
AI Tools
RedQueen has access to specialized tools for querying your infrastructure.
Metrics Analysis
Query Prometheus metrics using natural language. Get CPU, memory, latency, error rates and more.
Application Logs
Search application logs with container awareness. Filter by service, pod, or error patterns.
WAF Logs
Analyze AWS WAF security logs. Investigate blocked requests, attack patterns, and rule matches.
ALB Logs
Search Application Load Balancer access logs. Track requests, response codes, and latencies.
IP Intelligence
Look up IP addresses with geolocation, WHOIS data, and threat intelligence context.
Kubernetes
Query Kubernetes cluster state. Check pods, deployments, events, and resource usage.
Example Queries
Just ask in natural language. RedQueen figures out the rest.
Provider Agnostic
Not locked into any single LLM provider. Switch models or providers without code changes.
AWS Bedrock
Production-ready with Claude, Llama, Mistral and more. Runs in your AWS account.
Other Providers
Easily switch to OpenAI, Azure, Google, or any OpenAI-compatible API.
Self-Hosted
Run locally hosted models via Ollama or vLLM for full data privacy.
Switch Models from Slack
Users select their preferred model directly in Slack using native modals and selectors. No config files, no deployments — just pick and go.
Features
Thread Context
Conversations maintain context. Follow-up questions understand previous messages in the thread.
Streaming Responses
Responses stream in real-time. See tool invocations and results as they happen.
Tool Chaining
Complex queries automatically chain multiple tools. One question can trigger metrics, logs, and API queries.
Cost Tracking
Token usage and cost metrics published to CloudWatch. Track spending per query.