> Source: https://builder-docs.ema.ai/agent-reference/core/custom-agent > Title: Custom Agent # Custom Agent The Custom Agent is a general-purpose LLM agent that accepts any combination of inputs and produces text or structured outputs. It is the most flexible agent in the platform -- use it when no specialized agent fits your needs, or when you need to implement custom logic with LLM reasoning. ## Use Cases - No existing agent covers your specific task. - You need a flexible LLM step with custom instructions. - You want to prototype a new capability before requesting a dedicated agent. - You need to transform, analyze, or reason about data in a way not covered by other agents. - You need structured (typed/JSON) output from an LLM step. ## Inputs Input Type Required Description `role_instructions` Text Yes Role instructions defining the agent's behavior and personality (e.g., "You are a legal contract reviewer"). `task_instructions` Text No Specific instructions for the task to accomplish. Use this for per-invocation guidance that is separate from the agent's role. `named_inputs` Any\[\] Yes At least one input must be provided. Accepts any type: text, search results, documents, conversations, entities, etc. `output_fields` ExtractionColumn\[\] No Define a structured output schema. When set, the agent returns typed fields instead of free-form text -- useful for downstream agents that expect structured data. ## Outputs Output Type Description `response_with_sources` Text The LLM-generated output based on your instructions, with source attribution when available. ## Configurations Parameter Description Default `role_instructions` The primary prompt that defines the agent's behavior and personality. Set this in the agent's configuration panel. Required `task_instructions` Per-task instructions that supplement the role. Useful when the same agent handles different tasks via different workflow paths. None `model_config` Override the EmaFusion model selection for this agent. Auto-wired from the AI Employee's EmaFusion configuration unless overridden. EmaFusion default ### Advanced Configuration Parameter Type Description `process_entire_document` Boolean When enabled, processes the full content of input documents rather than chunking. `use_citation_based_filtering` Boolean Enforces citation grounding -- the agent must ground its response in the provided sources. `disable_sources` Boolean Removes source attribution from the output. `glossary` GlossaryItem\[\] Custom terminology definitions to ensure consistent, domain-accurate language in the response. `user_tags` String\[\] User metadata tags for prompt personalization (e.g., country, role, department). `data_protection_config` DataProtectionConfig PII handling configuration -- controls how sensitive data is obfuscated before being sent to the LLM. ## How to Use This Agent A custom agent that extracts action items from meeting notes: ``` document_trigger -> custom_agent("Extract all action items with assignee and deadline from these meeting notes. Return as a numbered list.") -> send_email -> workflow_output ``` A custom agent that rewrites a knowledge base answer for a specific audience: ``` chat_trigger -> knowledge_search -> respond_to_a_query -> custom_agent("Rewrite the response for a non-technical audience") -> workflow_output ``` ## Related Agents - [Respond to a Query](/legacy-docs/agent-reference/core/respond-to-a-query) -- similar but optimized for response generation with source grounding. - [Extract Entities](/legacy-docs/agent-reference/core/extract-entities) -- for structured entity extraction; prefer this over Custom Agent for that task. - [Custom Code Agent](/legacy-docs/agent-reference/core/custom-code-agent) -- for deterministic JavaScript logic; prefer this when you do not need LLM reasoning. - Specialized agents in the [Specialized Agents Catalog](/legacy-docs/agent-reference/specialized) -- pre-trained Custom Agent variants for specific domains.