Page 170
12 articlesGoverning Agentic AI Systems: What Changes When Your AI Can Act
When AI agents can call APIs, write to databases, and spawn sub-agents, governance shifts from controlling outputs to controlling actions. A practical engineering framework for authorization, minimal footprint, prompt injection defense, and structured human oversight.
Agent Engineering Is a Discipline, Not a Vibe
Why most AI agents fail in production — and the six structural dimensions (intent, memory, planning, control flow, authority, tools) that separate reliable systems from ones that only work in demos.
Designing an Agent Runtime from First Principles
A production agent runtime is not a function runner — it is an execution substrate. Here is how to design one correctly, covering graph execution models, checkpointing, human-in-the-loop, and observability from first principles.
Why Your Agent Should Write Code, Not JSON
Code-action agents let LLMs emit and run Python instead of JSON — achieving 20% higher task success rates and 30% fewer LLM round-trips. Here's how they work, where they fail, and how to run them safely in production.
Why Your AI Agent Wastes Most of Its Context Window on Tools
Every tool definition your agent loads is a token tax paid upfront. With 50+ MCP tools connected, definitions alone can consume 130K tokens before any work begins. Here are the three bottlenecks breaking production tool use and the patterns that fix them.
Why Your AI Agent Should Write Code Instead of Calling Tools
Code-executing agents can cut token usage by 98–99% compared to standard tool-calling patterns — and that's just the start. Here's how the architecture works, where it breaks, and when to use it.
Why Multi-Agent AI Architectures Keep Failing (and What to Build Instead)
Multi-agent AI systems fail in production at rates of 41–87%. Here's why parallel agents compound errors, fragment context, and resist debugging — and what simpler architecture actually works.
Building a Generative AI Platform: Architecture, Trade-offs, and the Components That Actually Matter
A practitioner's guide to the infrastructure layer around LLMs—RAG pipelines, model gateways, caching strategies, guardrails, and observability—and when to actually add each component.
12-Factor Agents: A Framework for Building AI Systems That Actually Ship
Most AI agent projects stall at 80% quality and never ship. The 12-Factor Agents framework documents the principles that production teams converged on independently to build reliable, observable LLM-powered systems.
The Lethal Trifecta: Why Your AI Agent Is One Email Away from a Data Breach
When an AI agent can access private data, consume untrusted content, and communicate externally, a single poisoned email becomes a data breach. Here's the architectural pattern behind these attacks and how to stop them.
Valuable. Doable. Mine.
Reflecting on the historical lessons of Xerox PARC and Apple to explore how, in a rapidly changing technological environment, one can judge the true value of a technology and whether it aligns with personal business pursuits.
LLM Observability in Production: Tracing What You Can't Predict
Standard monitoring dashboards miss most of what goes wrong in LLM applications. A practical guide to distributed tracing, cost attribution, latency profiling, and debugging non-deterministic agent behavior at scale.
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.
