agent2: Skill for Claude Code

Building Domain Expert Agents

Overview

A domain expert agent is the most powerful pattern in Agent2. It combines: document reading (OCR), domain knowledge (R2R search), context-aware reasoning, human-in-the-loop, and structured output. Think: an experienced professional sitting at a desk with reference books, tools, and the ability to ask questions.

Before building a serious domain expert, study docs/brain-clone-pattern.md and agents/procurement-compliance-officer. The procurement agent is the canonical public example for the full Agent2 pattern.

When to Activate

• User wants an agent that processes documents against professional standards
• Agent needs to "look things up" in reference material before deciding
• Agent needs to ask clarifying questions and resume after human answers
• Agent must produce structured output that follows domain-specific rules
• Industries: legal, medical billing, accounting, compliance, insurance, HR, procurement

The Domain Expert Pattern

Document arrives (PDF, email, text)
  → Agent reads it (OCR via Docling MCP or text input)
  → Agent checks context (who is this for? what rules apply?)
  → Agent searches knowledge (R2R via Knowledge MCP)
  → Agent decides: complete? or needs clarification?
  → If complete: structured result + confidence score
  → If incomplete: clarifying question → pause → human answers → resume
  → Human approves final result

Architecture

1. The Schema — Your Domain Contract

Design the output schema around the three possible outcomes every domain expert faces:

class ExpertResult(BaseModel):
    status: Literal["complete", "needs_clarification", "rejected"]
    # Domain-specific structured output
    findings: list[Finding] = Field(default_factory=list)
    # Clarification path
    question: ClarificationRequest | None = None
    # Rejection path
    rejection_reason: str | None = None
    # Always present
    reasoning: str  # The expert's thought process
    confidence: float = Field(ge=0.0, le=1.0)
    review_steps: list[str] = Field(default_factory=list)