skills.rest
joaopelegrino
joaopelegrinoCOMMUNITY
Explore all skills by this author →
GitHub

cva-concepts-agent-types

Classifies AI agents by data-enabled capabilities into Types A, B, C, D for architecture decisions.

Updated Aug 27, 2026
Search Tags:#architecture#AI agents#system design#multi-agent#latency#cost optimization#taxonomy
One-click install
npx skills add https://github.com/joaopelegrino/hello-word-closure --skill cva-concepts-agent-types
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: cva-concepts-agent-types
Source: https://github.com/joaopelegrino/hello-word-closure/tree/main/.claude-plugin/clojure-vertex-adk/skills/cva-concepts-agent-types
Command: npx skills add https://github.com/joaopelegrino/hello-word-closure --skill cva-concepts-agent-types

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Developing AI agents in regulated domains often leads to over-engineered or under-optimized systems. This Skill provides a clear A/B/C/D taxonomy to classify agents by their data access capabilities, enabling developers to select the most appropriate agent type for a task, thereby optimizing cost, latency, and complexity.

Core Features & Use Cases

  • A/B/C/D Taxonomy: Understand agent types from Pure AI (Type A) to maximum context (Type D - AI + Database + Web), with detailed cost and latency profiles.
  • Decision Tree: Use a structured approach to select the optimal agent type based on whether external data or tenant-specific database context is required.
  • Cost & Performance Optimization: Learn how to reduce costs by up to 67% and improve latency by selecting cheaper, simpler agent types when appropriate.
  • Use Case: When building a healthcare content pipeline, use the taxonomy to assign Type A agents for simple data extraction, Type B for personalized SEO, Type C for scientific reference search, and Type D for final, compliance-critical consolidation.

Quick Start

You need an agent to extract entities from text. Consult the decision tree to determine if it needs database or web access. If not, select a Type A (Pure AI) agent for lowest cost and fastest execution.

Frequently Asked Questions about cva-concepts-agent-types

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I choose between different AI agent types for cost and latency optimization?▼

AI agents vary by data-source capabilities: Type A (pure AI) offers lowest cost and fastest execution; Type B adds database context; Type C adds web search; Type D combines both. Select based on whether your task needs external data or tenant-specific database access to reduce costs by up to 67% while maintaining performance.

What's the difference between Type A, Type B, Type C, and Type D agents?▼

Type A agents use only AI reasoning for lowest latency and cost. Type B adds database access for personalized context. Type C adds web search capabilities. Type D combines database and web access for maximum context. Each type trades cost and speed against information richness based on task requirements.

When should I use a Type A agent versus a Type D agent in multi-agent workflows?▼

Use Type A agents for simple tasks like entity extraction that need no external data—they're fastest and cheapest. Use Type D agents for compliance-critical tasks requiring both database context and current web information. In multi-agent workflows, mix types strategically: assign simpler types to simpler subtasks to optimize overall cost and latency.

How does agent type selection apply to regulated domains like healthcare?▼

In regulated domains, classify agents by required data access: use Type A for data extraction, Type B for personalized analysis with tenant data, Type C for external research, and Type D for final compliance-critical consolidation. This taxonomy ensures you don't over-engineer simple tasks while maintaining necessary safeguards for sensitive operations.

Can I use this taxonomy to determine if my agent needs web access?▼

Yes. Use the decision tree to assess whether your agent task requires external web data. If it does, select Type C or Type D agents. If web access isn't needed but database context is, select Type B. If neither is required, Type A is optimal for cost and speed.

What are the cost implications of selecting different agent types?▼

Agent type selection directly impacts cost: Type A (pure AI) is cheapest; adding database context (Type B) increases costs; web search (Type C) adds more; Type D (database + web) is most expensive. Strategic type selection can reduce costs by up to 67% by matching agent capabilities precisely to task requirements.

Related Skills

Explore More Software Engineering Skills→
synaptiaisynaptiai
4

classify

Classify items into taxonomy labels with confidence and evidence anchors.

Official
Intermediate
z1439527767z1439527767

agent-orchestration-multi-agent-optimize

Profile multi-agent workloads and optimize orchestration for cost efficiency.

Community
Advanced
BasedHardwareBasedHardware
13.1k

omi-api-integration

Guide Omi API integration with OAuth, MCP, and webhooks.

Official
Advanced
rysweetrysweet
1

consensus-voting

Execute weighted multi-agent voting with configurable consensus thresholds.

Community
Advanced