Guides

Standalone decision guides and comparisons: the questions you hit while shipping LLM systems, answered with tables, trade-offs, and runnable code. For the structured curriculum, start with the AI Engineering track.

• A/B Testing Prompts in Production: Traffic Splits, Guardrail Metrics, and Automatic Rollback

  Run two prompt versions against live traffic with the feature flags you already have: consistent splits, guardrail metrics, and automatic rollback.

  Last verified August 8, 2026 · 9 min read

• Hybrid Search in Postgres: Full-Text + pgvector in One Query, No New Infrastructure

  Combine Postgres full-text search and pgvector with Reciprocal Rank Fusion in one SQL query: schema, the RRF query, tuning, and when you need more.

  Last verified July 29, 2026 · 6 min read

• LLM Fallbacks in Production: Routing, Retries, and Timeouts

  Build an LLM fallback that holds up in production: routing by health, cost, and capability, what to retry, stage-aware timeouts, and how to degrade.

  Last verified August 8, 2026 · 9 min read

• pgvector vs Pinecone vs Qdrant: Choosing a Vector Store for Your Existing Backend (2026)

  pgvector, Pinecone, or Qdrant for production vectors? A neutral comparison with a decision table, scale thresholds, and how to benchmark them yourself.

  Last verified August 8, 2026 · 10 min read

• How to Stream LLM Responses: SSE vs WebSockets (and the Fetch-Stream Option)

  SSE, raw fetch streaming, or WebSockets for LLM tokens? A decision table, a production relay with abort wiring, and the proxy failure modes.

  Last verified July 29, 2026 · 5 min read

• How to Add an LLM to Your Existing Backend Without Rewriting It: 6 Integration Patterns

  Six production patterns for adding LLM features to an existing backend, with code: inline endpoint, queue worker, gateway, pgvector, events, flags.

  Last verified July 30, 2026 · 10 min read