Customize Agents

Create custom agents with your team’s instructions, choose what each one can reach, and manage them per workspace

CloudThinker, the built-in assistant, works out of the box. A custom agent adds your own expert alongside it, with its own instructions, reply language, and connections.

What you can change

Go to Settings → Agents. The sidebar lists your workspace’s Custom agents; the built-in assistant has no settings entry. Click an agent to open its two tabs, Identity and Connections.

Customizing agents requires the workspace Admin role. Developers and Viewers can chat with agents but can’t edit them.

Field	Can you change it?
@mention	Set once on creation
Name, Role, Goal, Instructions	Yes
Model Tier, Language, Skill Learning	Yes
Connections	Yes — attach and detach
Active state	Yes — and the agent turns off automatically when it has no connections

Plan tiers

The number of custom agents depends on your plan.

Plan	Custom agents
Free	1
Team	5
Scale	10
Scale+	10
Enterprise	Unlimited

Hit the limit? Delete an unused agent or upgrade your plan.

Create a custom agent

Need an agent with your team’s rules built in — a billing analyst, an on-call summarizer, a documentation specialist? Build your own.

Go to Settings → Agents, click Create agent, then choose Create with AI or Build with form.

Create with AI

Best when you know what the agent should do but don’t want to fill every field yourself.

Describe what you want in one sentence — CloudThinker takes it from there. It typically confirms:

• Name and @mention — suggests options based on your description.
• Role and Goal — drafts both for you to approve or tweak.
• Model Tier — recommends Light / Pro / Ultra based on task complexity.
• Instructions — generates a first draft you can refine.
• Connections — asks which to attach (cloud, database, Kubernetes, or MCP — an open standard for plugging in external tools).
• Skill Learning — whether the agent saves new skills (reusable know-how it picks up from your work) automatically (Auto), asks first (Offer), or never (Off).

Example prompt: “I need an agent that watches AWS spend and pings me when daily cost jumps more than 20%.”

You can edit any field afterward from the agent’s settings dialog.

Build with form

Best when you want full control over every field upfront. The dialog walks you through three steps. The header shows your custom-agent quota for the current plan (e.g. “1 of 10 custom agents used” on Scale).

1. Identity

   • Avatar — click the tile to change it (defaults to your initials on a gradient).
   • Name — e.g. “Cost Guardian”.
   • @mention — chat handle (e.g. @cost-guardian). Lowercase letters, numbers, dots, underscores, and hyphens, starting with a letter, up to 63 characters. Must be unique and can’t reuse a name reserved by CloudThinker. Set once — can’t change later.
   • Role — short title (e.g. “FinOps Specialist”).
   • Goal — one sentence on what this agent does.

   Click Next.

   
2. Configuration

   • Model Tier — pick Light (fast, lowest credit cost), Pro (balanced), or Ultra (max capability, highest credit cost). See model tiers and credit cost for current credit multipliers.
   • Instructions — one textarea describing how the agent should behave: what to focus on, how to respond, what to avoid. Write as plain sentences — guidelines, constraints, tone, and response format all live here. Up to 4,000 characters.
   • Language — reply language.
   • Skill Learning — Auto saves new skills automatically, Offer asks before saving, Off never saves.

   Click Next.

   
3. Connect

   Optional. Use the Builtin and MCP tabs to pick which connections this agent can reach. You can attach more later from Agent Settings.

   Click Skip and Create to finish.

   

The agent appears under Custom and is reachable via its @mention handle in chat.

Attach connections

Connections are how a custom agent reaches your cloud, databases, Kubernetes, or MCP servers. You decide what each agent can touch. Every agent has the same set of builtin tools — there is no per-agent tool toggle, so scope an agent by choosing its connections. An agent accepts up to 64 connections.

1. Open the Connections tab

   From the agent dialog, click Connections. The header shows the count (e.g. “3 connections”).

2. Pick Builtin or MCP

   Use the sub-tabs to switch between Builtin (cloud, database, Kubernetes) and MCP.

3. Add or remove

   Click Add to attach, Remove to detach. Save to apply.

Attach only the connections the agent’s job needs — a database reviewer doesn’t need production IAM access. A custom agent with no connections is automatically off; attach at least one to turn it back on.

Examples

What you want	What to do
An agent that replies in Vietnamese	Set Language to Vietnamese on the agent’s Identity tab.
An agent that only recommends, never changes	Create a custom agent with Instructions: “Recommend only — never propose changes that need write access.”
Cost reported in EUR with weekly digests	Create a custom agent with Instructions: “Report cost in EUR. Summarize spend weekly.” Attach a cloud connection.

Good instructions cover three areas: role context (expertise for your environment), scope limits (what the agent should and shouldn’t touch), and operational guidelines (procedures and escalation paths). For example:

You are the Cloud Engineer for Acme Corp.

Environment:
- Primary cloud: AWS (us-east-1, us-west-2)
- Secondary cloud: GCP (for ML workloads)
- Cost target: Reduce by 20% this quarter

Guidelines:
- Flag every security group change for review before recommending it
- Prioritize production stability over cost savings
- Flag any resource costing >$1000/month for review

Things to know

• Edits apply on the next message — in-flight chats finish under the old settings.
• Pick a custom agent’s @mention carefully — it’s set once and you’ll be living with it.
• Custom agents act under your workspace’s autonomy mode — Manual or Auto. See Approval mode.

Next steps

Set up connections

Wire up cloud, database, Kubernetes, and MCP connections

Agents

How CloudThinker, subagents, and custom agents share the work

Custom skills

Add domain knowledge to any agent

Commands

Save reusable prompts and run them with /