Artifacts

Artifacts are the dashboards, reports, comparisons, scorecards, diagrams, and saved generated files CloudThinker agents create from your connected cloud data. Describe the insight you need in plain language, and the agent builds a data-backed visual from your connections.

How it works

Ask — send a prompt using the CloudThinker Language syntax: @agent #tool instruction.
Gather — the agent queries live data across your connections: Cost Explorer, CloudWatch, databases, and more.
Generate — the agent assembles an Artifact with charts, tables, and a written summary.
Save, download, or rerun — save generated files to Files, download supported Artifacts as PDFs from their PDF URLs, or schedule the prompt to run again.

A scheduled automation reruns its prompt in a new conversation. It may create a fresh Artifact; it does not refresh an existing Artifact in place.

AWS cost dashboard with spending trends and cost drivers

What you can do

Capability	Description	Learn more
Build cost dashboards	Alex charts spending trends, service breakdowns, and available forecasts	Spend and forecast
Correlate operational signals	Anna combines health, performance, and cost data across clouds, including dependencies and blast radius (the resources an incident touches) in incident reports	Resolve
Report security posture	Oliver summarizes compliance status, open findings, and remediation progress	Oliver
Schedule recurring reports	Rerun an Artifact prompt on a schedule	Automations

Artifact types

Artifact	Description
Dashboard	A multi-widget view of related metrics, with a badge showing the time range it covers, a fullscreen mode, and PDF export
Report	A narrative analysis with data, findings, and recommendations
Comparison	A view that contrasts items, time periods, or environments
Scorecard	An assessment against defined criteria
Diagram	A visual of relationships or flows, with a Diagram ⇄ Code toggle to view its text source
Saved generated file	A file shown in the conversation until you select Save to artifacts, which adds it to the Files gallery

Charts are components of dashboards and reports. A standalone #visualize chart renders directly in the conversation, not as a separate artifact type. Any artifact can become a public link that opens without sign-in: click the share icon on the artifact’s card or preview, then Create share link. The gallery counts how many items are shared and can filter to shared items; revoking a link cuts off access immediately. Sharing covers what viewers see and the role required.

Example prompts

Start with a one-line request — agents pick sensible defaults for scope and time range:

@alex #dashboard AWS spending by service for the last 30 days
@oliver #report quarterly security assessment across all accounts
@kai #dashboard cluster resource utilization

Cost analysis dashboard

Add structure to the instruction when you need specific breakdowns:

@alex #dashboard Generate a comprehensive AWS cost dashboard for [start_date] to [end_date].

Include:
- Monthly spending trends by service with month-over-month growth rates
- Top 10 cost drivers and their utilization patterns
- Reserved Instance vs On-Demand cost comparison
- Cost anomalies and optimization opportunities with estimated savings

Segment by: [cost allocation tags such as environment, team, or application]

Cross-domain dashboard

Ask Anna to correlate data that lives in different systems:

@anna #dashboard Create an operational dashboard correlating database performance with infrastructure costs for [time_period].

Analyze:
- Aurora and DocumentDB query performance metrics
- Resource utilization and spending patterns
- Correlation between database load and compute and storage costs

Context: [recent changes, migrations, or specific concerns]

Database and infrastructure correlation dashboard

Charts in dashboards and reports

Ask for a chart as part of a dashboard or report:

@tony #dashboard Create a dashboard for Aurora cluster [cluster-identifier] over the past [time_period].

- Include a query execution time chart with p50, p95, and p99 query latency
- Separate lines for read queries vs write queries
- Highlight queries exceeding [threshold] ms

Aurora query performance time-series chart

Reusable prompt patterns

Keep parameterized prompts wherever your team stores runbooks, and fill in the placeholders before each run. The {placeholder} braces are a writing convention, not product syntax — replace them with real values before you send the prompt:

@tony #dashboard Create a performance dashboard for Aurora cluster {cluster_id} covering {time_period}.

Include:
- Slow query analysis (queries exceeding {latency_threshold} ms)
- Resource utilization trends (CPU, memory, IOPS)
- Replica lag monitoring
- Connection pool health

Compare against baseline: {comparison_period}

For example, run it with cluster_id=production-aurora-cluster, time_period="past 7 days", comparison_period="previous 30 days", and latency_threshold=200.

Performance review dashboard template

Spend and forecast

Dive deeper into spend trends, forecasts, and cost attribution analysis

Resolve

Correlate evidence and dependencies during root cause analysis

CloudThinker Language

Master the full @agent #tool syntax for building effective prompts

Automations

Rerun prompts in new scheduled conversations

Review

Optimize

Resolve

Cyber

Skills

Artifacts & Dashboards

How it works

What you can do

Artifact types

Example prompts

Cost analysis dashboard

Cross-domain dashboard

Charts in dashboards and reports

Reusable prompt patterns

Spend and forecast

Resolve

CloudThinker Language

Automations

​How it works

​What you can do

​Artifact types

​Share an artifact

​Example prompts

​Cost analysis dashboard

​Cross-domain dashboard

​Charts in dashboards and reports

​Reusable prompt patterns

​Related

Spend and forecast

Resolve

CloudThinker Language

Automations

How it works

What you can do

Artifact types

Share an artifact

Example prompts

Cost analysis dashboard

Cross-domain dashboard

Charts in dashboards and reports

Reusable prompt patterns

Related