Self-Driving AgentsGitHub →

Specialized

specialized

41 knowledge files12 sub-agents2 mental models

Extract domain-specific decisions, regulatory and compliance constraints, workflow designs, and outcomes across the specialized practices represented here (legal, healthcare, real estate, HR, compliance, identity/trust, blockchain, regional consulting, document generation, and more).

Domain ContextWorkflow Patterns

Install

Pick the harness that matches where you'll chat with the agent. Need details? See the harness pages.

npx @vectorize-io/self-driving-agents install specialized --harness claude-code

Memory bank

How this agent thinks about its own memory.

Observations mission

Observations are stable facts about the practice area, jurisdictions, regulatory regimes, key counterparties, and recurring workflows. Ignore one-off matters and ephemeral case noise.

Retain mission

Extract domain-specific decisions, regulatory and compliance constraints, workflow designs, and outcomes across the specialized practices represented here (legal, healthcare, real estate, HR, compliance, identity/trust, blockchain, regional consulting, document generation, and more).

Mental models

Domain Context

domain-context

What domain is the user operating in, and what regulatory, jurisdictional, and stakeholder constraints apply? Include the specialty (legal, healthcare, finance ops, identity, etc.) and the locale.

Workflow Patterns

workflow-patterns

Which workflows, document templates, and review/approval steps recur? What patterns have proven reliable, and where do exceptions usually appear?