Page 118
12 articlesPII in the Prompt Layer: The Privacy Engineering Gap Most Teams Ignore
How personally identifiable information flows uncontrolled into LLM inference calls, and the masking, tokenization, and logging architectures that close the compliance gap.
Pricing Your AI Product: Escaping the Compute Cost Trap
Traditional SaaS pricing assumes near-zero marginal cost per user. LLM features break that assumption — tokens can consume 20–40% of gross margin. Here's how to build a pricing architecture that survives.
Proactive Agents: Event-Driven and Scheduled Automation for Background AI
Most agent design literature assumes a human triggers execution. Production AI increasingly runs in the background — on schedules, change events, and system state transitions. Here's what that changes architecturally.
Prompt Canary Deployments: Ship Prompt Changes Like a Senior SRE
Prompt edits are as dangerous as code deploys — but almost nobody treats them that way. Here's the traffic-splitting, quality-monitoring, and rollback discipline that separates teams that catch regressions before users do from teams that find out on Twitter.
Prompt Diff Review as a Discipline: What Reviewers Actually Need to Ask
Traditional code review instincts don't map to prompt edits. Here's the checklist, the tooling, and the reviewer-author dialog that turn a prompt PR into a behavioral contract.
The Prompt Entropy Budget: Measuring Output Variance as a First-Class Production Metric
Most production LLM systems track accuracy but ignore variance. Measuring the distribution of outputs over identical inputs — your prompt entropy budget — is the missing metric that determines UX consistency at scale.
Prompting Reasoning Models Differently: Why Your Existing Patterns Break on o1, o3, and Claude Extended Thinking
Reasoning models like o1, o3, and Claude with extended thinking process prompts fundamentally differently than instruction-following models. The patterns that work for GPT-4 actively hurt performance on thinking models — here's the framework for adapting.
The Public Hallucination Playbook: What to Do When Your AI Says Something Stupid in Public
A practical playbook for engineers and product teams facing a public AI hallucination incident — covering triage, root cause classification, user-facing communications, and the post-incident eval work that actually prevents recurrence.
RAG-Specific Prompt Injection: How Adversarial Documents Hijack Your Retrieval Pipeline
Five carefully crafted documents in a corpus of millions can manipulate a RAG system's responses 90% of the time — and your input validation layer never sees them coming. Here's why the threat model for RAG is fundamentally different, and the defenses that actually work.
The Query Rewrite Layer Your RAG System Is Missing
Most RAG tuning effort goes into chunking strategies and embedding models. The highest-leverage intervention is earlier in the pipeline: transforming user queries before they hit the vector index.
The Retrieval Emptiness Problem: Why Your RAG Refuses to Say 'I Don't Know'
Vector search always returns top-k regardless of match quality, turning absent information into confident fiction. Fixing it takes more than raising a threshold — abstention has to be a first-class output.
Research Agent Design: Why Scientific Workflows Break Coding Agent Assumptions
Coding agents converge toward a single correct answer. Research agents must explore open-ended hypothesis spaces where success is undefined upfront. Here's what that difference demands architecturally.
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.
