Decision Guide

Use this guide to identify which patterns are most relevant to your current situation. Start with the question that best describes your primary concern.

I need to reduce costs

How are you currently calling LLMs?

• Direct API calls with no intermediary → Start with LLM Gateway Pattern
• Single provider, single model for everything → Start with Model Router Pattern
• Seeing many repeated or similar queries → Start with Semantic Caching
• Long context windows eating your budget → Start with Prompt Compression Pattern
• No visibility into per-feature spend → Start with Cost Attribution Pattern

I need to improve reliability

What kind of failures are you seeing?

• Provider outages causing downtime → Start with Fallback Chain and Circuit Breaker for LLMs
• Quality degradation after prompt or model changes → Start with Prompt Regression Guard
• Silent quality drops nobody notices → Start with Quality Drift Detection
• No safe way to roll out model changes → Start with Canary Deployment for Models

I need better retrieval / RAG

What does your knowledge base look like?

• Static documents, FAQ-style → Classic RAG Pattern
• Complex relational data, multi-hop questions → GraphRAG Pattern
• Need both keyword and semantic matching → Hybrid Search Pattern
• Retrieval quality is inconsistent → Reranking Pattern
• Need to remember across user sessions → Contextual Memory Pattern

I need to handle security and compliance

What is your primary concern?

• Prompt injection and jailbreak attempts → Input Sanitization Pattern
• PII in model inputs or outputs → PII Scrubbing Pipeline
• Need structured, type-safe outputs → Structured Output Enforcement
• Audit requirements for model interactions → Audit Trail Pattern
• Regulatory compliance (EU AI Act, HIPAA) → Policy-as-Code Pattern

I need observability

What can you not see today?

• What is happening inside multi-step chains → Span-Level Tracing Pattern
• How much each feature or user costs → Cost Attribution Pattern
• Whether output quality is changing over time → Quality Drift Detection
• How to set meaningful SLAs → SLO Pattern for AI

I am building agent systems

Agents combine multiple patterns. A typical production agent stack includes:

1. LLM Gateway Pattern for routing and observability
2. Least-Privilege Tool Access for safe tool use
3. Agent Action Log Pattern for auditability
4. Human-in-the-Loop Gate for high-risk actions
5. Cost Circuit Breaker for runaway prevention
6. Contextual Memory Pattern for session persistence

I need graph-based intelligence

What are you trying to achieve with graphs?

• Multi-hop questions that connect information across documents → Start with GraphRAG
• Non-linear reasoning with branching and merging approaches → Start with Graph of Thoughts
• Deduplicating entities across multiple data sources → Start with Entity Resolution Graph
• Building a knowledge graph for your domain → Start with GraphRAG for the retrieval layer and Entity Resolution Graph for clean entity data

I need to evaluate and test AI quality

What is your primary evaluation challenge?

• Need automated quality scoring at scale → Start with LLM-as-Judge
• Quality is degrading after prompt or model changes → Combine LLM-as-Judge with Span-Level Tracing
• Need a quality gate before deploying changes → Build an eval pipeline with LLM-as-Judge scoring