CloudThinker Language

CloudThinker Language is the structured prompt syntax that works identically across every agent, in chat, Slack, and automations. Mention an agent, tag the output you want, then write your instruction in plain language.

Syntax

Every prompt follows one canonical form:

@agent #tool instruction

Component	Required	Description
`@agent`	Yes	Routes the request to a specific agent. Mention several agents for cross-domain work.
`#tool`	No	Output format or capability. Place it immediately after the mention; combine tags for multiple outputs.
`instruction`	Yes	What you want, in your own words — include scope, timeframe, thresholds, and constraints inline.

Agent mentions

Mention	Role	Best for
`@alex`	Cloud Engineer	Cost analysis, resource optimization, multi-cloud infrastructure
`@oliver`	Security Engineer	Audits, vulnerability scans, IAM, compliance
`@tony`	Database Engineer	Query optimization, performance tuning, backups
`@kai`	Kubernetes Engineer	Cluster management, pod optimization, scaling
`@anna`	General Manager	Multi-agent coordination, executive reporting

See the agent reference for each agent’s full capabilities.

Tool tags

Typing # in the chat composer opens a two-column picker: Tools — output and capability tags — and Knowledge Base — your knowledge bases, so retrieval can be pointed at one collection. Picking an entry inserts its tag; you can also type a tag by hand.

Picker entry	Inserts	Output
Visualize	`#visualize`	Standalone charts from data in the conversation — `@alex #visualize spending by service`
Dashboard	`#dashboard`	Interactive visualizations for monitoring and presentations — `@alex #dashboard monthly cost trends`
Report	`#report`	Detailed analysis documents with findings and evidence — `@oliver #report SOC 2 compliance assessment`
Tabular Engine	`#tabular_engine`	SQL analysis over tabular files you attach, such as CSV exports and spreadsheets
Slide	`#slide`	Slide decks built from the conversation’s findings
Push Alert	`#alert`	Monitoring notifications on the conditions you define — `@kai #alert on pod OOMKilled events`
Schedule Task	`#schedule`	A scheduled or recurring run of the instruction
Search Internet	`#search`	Web research alongside your infrastructure data
Search Knowledge Base	`#search-knowledge-base`	A search across every knowledge base in the workspace

The Tools column reflects your workspace, so it can carry more entries than this table. #recommend — prioritized, actionable recommendations with implementation steps — is a typed tag with no picker entry: @tony #recommend index changes for slow queries. Combine tags when you want more than one output: @alex #dashboard #recommend cost optimization opportunities.

Mention a knowledge base

The Knowledge Base column lists your workspace’s knowledge bases by name. Picking one inserts its name as a tag and scopes the agent’s retrieval to that collection:

@oliver #runbooks what are the incident escalation steps?

Use #search-knowledge-base instead when the answer could live in any collection. See Knowledge Base for creating and filling collections.

Context modifiers

Add context inside the instruction to narrow scope and improve accuracy.

Type	Examples
Timeframe	`over the last 30 days`, `since January`, `in the last 24 hours`
Scope	`in us-east-1`, `on the production cluster`, `on the orders database`
Threshold	`with CPU below 15%`, `costing over $1,000/month`, `P95 above 500ms`
Exclusion	`excluding production-tagged resources`, `except backup buckets`
Priority	`prioritizing quick wins`, `critical severity first`

Other tokens

The chat composer accepts two more token types alongside mentions and tags.

Token	Trigger	What it does
`/command`	Type `/` at the start of a message	Runs a skill — packaged instructions agents follow — or a saved command — a reusable saved prompt — from the picker. Only works as the first token in the message.
`$CREDENTIAL`	Type `$` anywhere in a message	References a stored workspace credential by name, so agents can use the secret without you pasting it. The picker appears for members who can edit workspace settings.

Composer behavior beyond tokens — attachments, keyboard shortcuts, and what happens to messages you send while an agent is working — is covered in Chat features.

Prompt patterns

Pattern	Form	Example
Analyze	`@agent #tool analyze <target> <context>`	`@alex analyze EC2 spending by instance family over the last quarter`
Audit	`@agent #tool audit <target> for <criteria>`	`@oliver audit S3 buckets for public access and encryption`
Optimize	`@agent #recommend <target> <constraints>`	`@kai #recommend HPA policies for variable workloads`
Investigate	`@agent investigate <issue> <scope>`	`@tony investigate slow query performance on the orders table`
Coordinate	`@anna coordinate <project> with <agents>`	`@anna coordinate quarterly review with @alex @oliver @tony @kai`

In Slack, the same syntax works with a bot prefix: @CloudThinker @alex what's our AWS spend this week? — see Slack integration.

Examples

Direct requests — pick the agent, tag the output, state the target:

@alex #dashboard AWS spending by service and region
@oliver #report SOC 2 compliance assessment with evidence
@tony #recommend index changes for queries slower than 500ms

Stack context modifiers to make results precise and safe to act on:

@alex #recommend right-sizing for EC2 instances in us-east-1 with CPU below 15% over the last 30 days, excluding production-tagged resources

Mention multiple agents for cross-domain problems:

@alex @tony investigate the cost spike on database infrastructure last week
@anna coordinate security remediation with @oliver leading and @alex @kai supporting

Refine progressively — start broad, then drill into what the agent finds:

@alex #dashboard cloud spending trends
@alex #visualize November cost spike broken down by service
@alex #recommend RDS optimization prioritizing underutilized instances

Be specific. @alex #recommend right-sizing for EC2 in us-east-1 with CPU below 15% gets an actionable answer; @alex check our servers gets a clarifying question.

Agents

Each agent’s expertise, capabilities, and prompt patterns in depth

Capabilities

What #dashboard, #report, #recommend, and other tool tags produce

Skills

Reusable expertise agents apply automatically or on demand

Slack Integration

Use the same syntax in Slack with the @CloudThinker prefix

Start here

Use CloudThinker

Core concepts

Syntax

Agent mentions

Tool tags

Mention a knowledge base

Context modifiers

Other tokens

Prompt patterns

Examples

Agents

Capabilities

Skills

Slack Integration

​Syntax

​Agent mentions

​Tool tags

​Mention a knowledge base

​Context modifiers

​Other tokens

​Prompt patterns

​Examples

​Related

Agents

Capabilities

Skills

Slack Integration

Syntax

Agent mentions

Tool tags

Mention a knowledge base

Context modifiers

Other tokens

Prompt patterns

Examples

Related