Page 142
12 articlesAgentic Coding in Production: What SWE-bench Scores Don't Tell You
SWE-bench Verified hit 80%—yet the same models score 23% on harder benchmarks, and a controlled study found AI tools made experienced developers 19% slower. Here's where agentic coding agents actually deliver value and where they silently fail.
CI/CD for LLM Applications: Why Deploying a Prompt Is Nothing Like Deploying Code
Deploying a new prompt version silently breaks production in ways no dashboard catches. Here's how to build a proper CI/CD pipeline for LLM applications — from prompt versioning and shadow testing to canary rollouts and behavioral drift detection.
The Context Stuffing Antipattern: Why More Context Makes LLMs Worse
Dumping full documents, raw tool outputs, and long chat histories into the LLM context window is a reliability trap. Here's how to detect when context is hurting your system — and the budget-aware curation patterns that fix it.
Continuous Batching: The Single Biggest GPU Utilization Unlock for LLM Serving
How iteration-level scheduling replaces static batching to deliver 4–8x GPU throughput gains in production LLM serving—and the failure modes that appear at high concurrency.
Your Database Schema Is Your Agent's Mental Model
Poorly normalized schemas cause AI agents to hallucinate joins, misread relationships, and chain unnecessary tool calls. Here's how to design a schema layer that your agent can actually reason about.
Embedding Models in Production: Selection, Versioning, and the Index Drift Problem
Picking the wrong embedding model—or failing to manage upgrades—silently kills RAG retrieval quality. A practical guide to model selection beyond MTEB scores, detecting index drift, and zero-downtime versioning strategies.
Feature Flags for AI: Progressive Delivery of LLM-Powered Features
Rolling out LLM-powered features requires more than traditional feature flags. A guide to prompt variant management, the three-tier metric stack, cohort consistency for multi-turn sessions, silent degradation detection, and rollback strategies that actually work.
Fine-Tuning Economics: The Real Cost Calculation Before You Commit
Most teams underestimate fine-tuning costs by 3–5x because they only budget the training run. Here's the complete cost model — data curation, failed experiments, deployment, maintenance — and a decision framework for when LoRA/PEFT actually beats months of prompt engineering.
GraphRAG in Production: When Vector Search Hits Its Ceiling
Vector search fails predictably on multi-hop reasoning queries. GraphRAG addresses that gap — but introduces a different cost structure, failure modes, and maintenance burden that most teams underestimate.
Knowledge Distillation Economics: When Compressing a Frontier Model Actually Pays Off
The real cost math behind compressing frontier models into specialized smaller ones — when distillation beats fine-tuning, when it doesn't, and the failure mode where students inherit their teacher's confident wrongness.
Releasing AI Features Without Breaking Production: Shadow Mode, Canary Deployments, and A/B Testing for LLMs
Shipping a new model version or prompt change to production carries risks that standard deployment processes don't catch. Here's how shadow mode, canary deployments, and A/B testing work together for safe LLM releases.
Where Production LLM Pipelines Leak User Data: PII, Residency, and the Compliance Patterns That Hold Up
Most LLM data leaks don't come from the model — they come from unredacted RAG chunks, verbatim prompt logs, and injectable retrieval pipelines. A practical guide to PII handling, data residency routing, and compliance logging for production AI systems.
About Tian Pan
I'm Tian Pan, an engineer-founder focused on agentic engineering — building autonomous AI systems and scaling engineering teams. I write practical guides on system design, technical leadership, and shipping with AI agents. Previously an early engineer at Uber, Brex, and IoTeX.
