Page 18
12 articlesLLM Self-Debugging: When the Explanation Is the Signal vs. When It's the Lie
LLMs answer fluently when asked why they failed — but the explanation and the actual failure mechanism are often two different things. A practical guide to telling them apart before you act.
LLM Tail Latency: Why Your P99 Is a Disaster When P50 Looks Fine
LLM response time distributions are fundamentally heavy-tailed in ways that conventional API monitoring misses entirely. Here's how to diagnose the P99 gap and fix it.
MCP Ambient Authority: The Tool-Chaining Attack Surface That Session-Scoped Permissions Create
MCP's session-scoped permission model grants agents access to entire tool surfaces at authorization time. Here's how that creates tool-chaining attack paths, and what least-privilege patterns actually look like in practice.
The Organizational Immune System: Why Companies Kill AI Features That Actually Work
Technically successful AI features get killed by organizational antibodies every day. Here's the pattern, why it happens, and the stakeholder playbook that gives working AI a path through.
PII in the Prompt: The Data Minimization Patterns Your AI Pipeline Is Missing
Customer personal data flows invisibly into context windows, vector stores, and fine-tuning datasets. Here are the classification, scrubbing, and architecture patterns that keep AI pipelines GDPR/CCPA-compliant without wrecking model quality.
The Ghost in the Weights: How Pretraining Residue Breaks Your Fine-Tuned Model in Production
Fine-tuning adjusts weights, it doesn't reset them. Pretraining priors bleed through on out-of-distribution inputs, producing confidently wrong answers your eval suite never catches. Here's how to detect and mitigate it before it reaches users.
Privacy Mode That Actually Keeps Its Promise: Engineering User-Controlled Data Boundaries in AI Features
Most AI privacy modes are retention theater — the toggle exists, the data flows anyway. Here's how to engineer user-controlled data boundaries that actually hold, from ephemeral inference to audit trails users can verify.
Profiling LLM Pipelines: The Bottlenecks That Aren't Inference
Most LLM pipeline latency doesn't live in inference. A breakdown of the real bottlenecks — preprocessing, double tokenization, synchronous retrieval, serialization — and how per-stage tracing makes them visible.
Prompt Injection in Multimodal Inputs: The Visual Attack Surface Your Text-Only Defense Misses
Text-based prompt injection defenses are blind to attacks hidden in images, PDFs, and audio. Here's the full attack surface enumeration and how to build layered defenses that actually work for multimodal AI pipelines.
Prompt Injection Is Not Primarily an Attacker Problem
Ordinary user content — product reviews, support tickets, documents — can override your AI's behavior at scale without any attacker involved. Here's why standard defenses miss the structural problem, and the architectural patterns that actually address it.
The Prompt Surface Area Problem: Why Adding a Tool Is Never Just Adding a Tool
Every new tool added to an LLM agent multiplies behavioral complexity non-linearly — creating interaction effects, evaluation blind spots, and security gaps that grow faster than the capability gains. Here's how to audit your agent's surface area before it outgrows your control.
Provenance Debt in AI Knowledge Bases: When Your RAG System Learns From Itself
AI-generated summaries, FAQs, and analyses accumulate in your RAG corpus without provenance markers — and each retrieval cycle compounds the errors. How to detect corpus contamination and build retrieval policies that prevent the feedback loop.
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.
