Agents

​

Example

“Show me this month’s sales status”

​

Agent Processing Pipeline

​

Agent vs. Base Model

​

Creating an Agent

1

Enter basic info

Click Workspace > Agents > ”+ New Agent” and fill in basic info.

Field	Description	Example
Name	Agent display name	”Marketing Assistant”
Description	What the agent does	”Marketing content creation and analysis support”
Profile image	Agent icon	Marketing-related image
Tags	Classification tags	marketing, content

2

Pick the base model

Choose the AI model the agent will use. Pick from the model list registered by the admin.

3

Write the prompts

Define the agent’s role, persona, and response rules.

Field	Description
Task Prompt	Defines the agent’s role, persona, restrictions, and concrete task instructions. Plays the role of the general system prompt.
Response Format Prompt	Specifies the response format and structure (markdown, table, etc.). Separated from the task prompt so format can be managed independently.

Click the AI auto-generate button next to each prompt field — it analyzes the agent’s name, description, and connected resources to draft the prompt automatically.

During AI auto-generation, technical instructions (tool usage, SQL writing rules, etc.) are automatically excluded. The platform handles those — the prompt only contains role, persona, and restrictions.

Example of a good task prompt

You are Cloocus's marketing assistant.

## Role
- Support marketing content creation
- Draft social media posts
- Analyze marketing data

## Response Rules
- Always respond in Korean
- Maintain a professional yet friendly tone
- Provide data-driven insights
- Comply with brand guidelines

## Restrictions
- Do not disparage competitors
- Do not use unverified statistics

Why are the Task Prompt and Response Format Prompt separated?

The two prompts are used at different stages of agent execution.

	Task Prompt	Response Format Prompt
When applied	While the agent is using tools	When composing the final answer
Role	”What to do” (role, restrictions)	“How to answer” (markdown, tables, length)
Include	Role definition, behavior rules, restrictions	Output format, tone, structure
Don’t include	Output format specs	Role definition, behavior rules

Separating them lets you change just the output format while keeping the role, or vice versa.

4

Configure prompt suggestions (optional)

Set conversation-starter suggestions shown when an agent is selected in chat.

Option	Description
Default	Use system default suggestions
Custom	Set agent-specific suggestions

Providing example questions matched to the agent’s purpose helps users start conversations quickly. Examples: “Summarize this month’s sales”, “Draft a social media post”

5

Connect Knowledge Bases

Attach documents the agent should reference.

1. Click ”+ Add” in the “Knowledge Base” section
2. Select Knowledge Bases to connect (multiple supported)

Connected Knowledge Bases are searched via RAG and used in answers, with citations.

6

Connect databases (optional)

Connect a Database (DbSphere) for natural-language data queries (NL-to-SQL).

1. Click ”+ Add” in the “Database” section
2. Select databases (multiple supported)

Ask questions in natural language about the connected DB; the AI generates and runs SQL, returning results.

7

Connect glossaries (optional)

Connect a Glossary so the agent understands your organization’s business terminology.

1. Click ”+ Add” in the “Glossary” section
2. Select glossaries (multiple supported)

Term definitions, synonyms, and context registered in the glossary are reflected in agent responses.

8

Connect tools (optional)

Connect tools for external system integration. In the “Tool Connections” section, choose MCP servers or OpenAPI servers.

Tool Type	Description
OpenAPI server	Interact with external services via REST API
MCP server	Tool integration via Model Context Protocol

If a connected tool’s description is empty, a warning banner appears at the top of the editor. The tool description is the LLM’s primary cue for “when to call this tool”, so a missing description leads to incorrect calls or unused tools. When the banner appears, fill in the description from the tool definition.

9

Capability settings (optional)

Configure advanced features the agent can use. Each capability has 3 states.

State	Description
Disabled	The capability is completely hidden in chat (default)
Default On	Auto-enabled at chat start, user can turn off
Default Off	Visible in chat, but user must turn it on

Capability	Description
Web Search	Real-time web search for up-to-date info. Configurable result count and domain filter
Image Generation	AI image generation engine integration. Pick which connection to use
Code Interpreter	Run Python code for calculations and data analysis

10

Response format (optional)

Constrain the agent’s response to a structured JSON format.

Mode	Description
Chat	Default freeform text response
Structured	Structured response per JSON Schema (Structured Output)

In Structured mode, define the response schema with the visual field builder or the raw JSON editor.

11

Guardrail settings (optional)

Attach security guardrails to validate I/O.

• Auto-detect and mask PII
• Custom pattern filtering
• Block prohibited words
• LLM-based content validation

12

Auto-evaluation settings (optional)

Automatically monitor response quality.

Setting	Description
Sampling rate	Share of responses to evaluate (1%–100%)
Evaluation type	Choose from retrieval quality, faithfulness, response quality
Judge model	LLM to use for evaluation

Evaluation type details

Type	Description
Retrieval Quality	Relevance of documents retrieved from the Knowledge Base
Faithfulness	Whether the response is faithful to retrieved content (no hallucination)
Response Quality	Overall quality, usefulness, and accuracy of the response

Sampling-rate guidance:

Situation	Recommended	Reason
New agent (validation phase)	50–100%	Need initial quality picture
Stabilized agent	5–10%	Save costs while monitoring
Critical-business agent	20–30%	Continuous quality assurance needed

Retrieval Quality and Faithfulness evaluations only run when there are Knowledge Base search results. For agents without a KB, choose Response Quality only.

13

Access permissions

Set who can use the agent.

Option	Description
Public	Available to all users
Private	Available only to you
Group/Organization	Available to specified groups or organizations

14

Save

Click Save to create the agent.

​

Using Agents

​

Select in Chat

​

Invoke with @

@MarketingAssistant Draft 5 social posts for this month's promotion

​

Agent Management

​

Use Cases

Q: How do I apply for annual leave?
A: Apply for annual leave with these steps:
1. Open the HR portal
2. Select the leave application menu
3. Enter leave type and date range
4. Request manager approval

[Source: HR Policy Article 15]

Q: Review the getUserById function
A: Review:
- [Improvement] Missing error handling — null check needed
- [Improvement] Recommend explicit return type
- [Good] Follows naming convention

[Reference: Coding Guidelines Section 3.2]

Q: Top 5 best-selling products this month
A: This month's TOP 5:

| Rank | Product | Units | Revenue |
|------|---------|-------|---------|
| 1 | Product A | 1,234 | ₩12,340,000 |
| 2 | Product B | 987 | ₩9,870,000 |
...

[Source: sales_orders table]

​

Best Practices

​

Prompt Writing

1. Define the role clearly — “You are a content specialist on Cloocus’s marketing team”
2. Provide concrete instructions — response language, length, citation rules, etc.
3. Set restrictions — no competitor disparagement, no PII exposure, etc.

​

Knowledge Base Connection

• Connect only relevant documents: Too many documents actually degrade retrieval accuracy
• Keep documents up-to-date: Refresh stale information regularly
• Write tool descriptions: Detailed tool descriptions for Knowledge Bases improve agent KB selection accuracy

​

Access Permissions

• Principle of least privilege: Grant access only to those who need it
• Manage by group/organization: More efficient than per-user assignment
• Review periodically: Check permission settings on a regular cadence

​

FAQ

​

Related Pages