Build AI Agents
AI Agents in ClearFeed help teams automate answers, assist agents, and continuously improve documentation. ClearFeed supports two types of AI Agents, each designed for a distinct purpose and workflow:
Answer Agents – Respond to user questions and assist agents using Knowledge Sources and tools.
Documentation Agents – Analyze tickets and requests to identify documentation gaps and improvement opportunities.
Each agent type differs in configuration, testing, and how it is used across ClearFeed.
Create a New AI Agent
From the left navigation in the ClearFeed web app, go to AI > Agent Studio.
Click New AI Agent.
Choose the agent type:
Answer Agent – Respond to user questions and assist agents using Knowledge Sources, Integrations, and/or Web Search. To create an Answer Agent, you must enable at least one of the following:
A Knowledge Source
An Integration
Web Search
Documentation Agent – Reviews tickets and requests to suggest documentation improvements.
The agent type determines what can be configured, how the agent is tested, and how it is activated.
Configure Your Agent
Knowledge Sources
Applies to both Answer Agents and Documentation Agents
Knowledge Sources define what information the AI Agent can access. They are optional for Answer Agents, but required for Documentation Agents. Answer Agents can operate without Knowledge Sources if Web Search or Integrations are enabled.
You can configure Knowledge Sources in one of the following ways:
Add All: Allow the agent to use all indexed Knowledge Sources.
Pick Specific: Limit the agent to selected Knowledge Sources using tags to control scope.
Advanced Knowledge Source Configuration
Answer Agents Only
These settings control how Knowledge Sources are used when generating answers. They apply only to Answer Agents used as Virtual Agents or Agent Assistants at the collection level.
Customize AI Responses
Display AI-Generated Answers: Choose whether AI-generated responses are shown.
Share Search Results: Display relevant search results alongside the answer and configure how many results to show.
Share References: Display documentation references used to generate the answer (up to 6).
Configure Web Search
Allow your agent to use real-time web search to find current information from the web. Web Search can be used on its own or in combination with Knowledge Sources and Integrations. Web Search can be enabled as the only information source for an Answer Agent.
Integrations
Answer Agents Only
Answer Agents can connect to external systems to perform actions.
Supported Integrations
Jira
Zendesk
HubSpot
GitHub
Integration Permissions
Under Advanced Settings, control what the agent is allowed to do for each integration:
Grant specific permissions manually
Allow only current permissions
Enable all current and future permissions
By default, all current and future permissions are enabled. This can be customized at any time.
Provide Instructions for the AI Agent
Both agent types support instructions, but they serve different purposes.
Documentation Agent Instructions
Documentation Agents use instructions to control how documentation gaps are identified and reported. They do not answer end-user questions or perform actions.
Instruction Structure
Helpdesk Context Defines the scope and nature of the helpdesk conversations.
Response Style Controls how suggestions are presented (concise, actionable, bullet-based).
Documentation Update Rules Defines what the agent is allowed to suggest (for example, only stable and released features).
These rules ensure the agent produces safe, implementation-ready recommendations.
Answer Agent Instructions
Answer Agent instructions define how the agent reasons, uses tools, and generates responses.
Instruction Structure
Agent Role: The Agent Role defines the agent’s core responsibility and operating boundaries. It sets the foundation for how the agent interprets queries, selects tools, and responds. It should clearly state:
What the agent is responsible for
How it should behave at a high level
Whether it must rely on tools or can answer directly
Restricted Queries: Specify queries the agent must never answer to avoid sensitive or non-permissible responses. When detected, the agent skips responding. Examples:
System credentials
Admin access
Salary or compensation data
Planning and Execution Instructions: Define how the agent plans and executes tasks, including:
When tools must be used
How multiple tools should be sequenced
When execution should stop due to insufficient data
Response Generation Instructions: Control tone, language, formatting, and fallback behavior.
Tone and Length: Clear, concise, and aligned with your brand
Language: By default, respond in the same language as the query
Knowledge Lookup & Fallback: If relevant information is found, generate a response. If not, return a fallback message.
You can include placeholders in the Instructions to add context:
Tool placeholders (Jira, GitHub, Zendesk)
Conversation analysis using
{{chat_analysis.process_chat}}
Improve Prompt (AI-Assisted)
The Improve Prompt option refines simple or incomplete instructions into a structured, production-ready prompt.
Available for new and existing agents
Disabled once improved
Re-enabled only if instructions change
Select AI Model Provider
ClearFeed lets you choose the AI model provider for each AI Agent. This dictates which provider’s large language models (LLMs) get used for each invocation of your agent.
Supported providers (and when to use each)
Each AI Agent can be configured to use one of the following model providers:
OpenAI: Most battle-tested option; typically provides the highest-quality responses. Use when accuracy and response quality matter most.
Groq: Best when latency is highly sensitive; may be less accurate than OpenAI for some tasks. Use when speed is the top priority.
Gemini : Google-hosted Gemini models; a competitive alternative to OpenAI which provides a good balance between quality and latency.
How to customize the model based on task complexity (Bronze/Silver/Gold)
ClearFeed uses a tiered mapping system to describe the complexity of various tasks. In order of increasing complexity these are :
Bronze
Silver
Gold
By default, for each provider that is supported we have a default model that will be used for a given tier of tasks.
For e.g. ClearFeed may use GPT 4o for Bronze tier tasks since they are not complex but employ GPT 5.2 for Gold tier tasks.
To change the model used for different tiers, contact ClearFeed Support.
Customize Look and Feel
Answer Agents Only
Customize how the agent appears in Slack:
Display Name
Profile Photo (image URL)
Description for internal clarity
Testing Your Agent
Testing helps validate behavior before enabling agents in production.
Testing an Answer Agent
Answer Agents support both chat-based and ticket/request-based testing.
Chat-Based Testing
Simulate conversations
Review responses
Inspect the Execution Plan, including tools, steps, and references
Ticket / Request-Based Testing
Test against existing tickets or requests
Validate behavior when ticket context and fields are present
Mirror real Virtual Agent and Agent Assistant usage
Testing a Documentation Agent
Documentation Agents can be tested only against tickets or requests.
Select an existing ticket or request
Review documentation improvement suggestions
FAQs
What’s the difference between selecting a provider and BYOK? Answer:
Selecting a model provider
You choose OpenAI, Groq, or Gemini for an AI Agent
Requests use ClearFeed-managed credentials for that provider
Bring Your Own Model (BYOK)
You add your own API key
Requests are routed to your organization’s account
Which setting takes precedence: BYOK or provider selection? Answer: If BYOK is configured, it always overrides the provider chosen in the agent. Example: If your account has a Gemini API key added via BYOK, all requests will use Gemini, even if an agent is set to OpenAI.
Can different agents use different providers? Yes, provider selection is per AI Agent. Multiple agents in the same workspace can use different providers. This applies only when BYOK is not configured
Will switching providers change my agent’s behavior? Answer:Yes. Different providers and models may vary in Response quality, latency, style and verbosity. We recommend testing a few sample questions before using a new provider in production.
Last updated