Page 11
12 articlesThe Onboarding Gap: Why New Engineers Take Three Months to Touch the AI Stack
AI codebases carry a hidden domain-knowledge tax that turns three-week ramps into three-month ones. The fix is decision history, not architecture diagrams.
The AI Wallet: Why Token Budgets Belong in the UI, Not the Engineering Dashboard
Hiding AI cost from users ships silent throttling and surprise downgrades. Treating the token budget as a real product surface — preview, caps, model selection — turns the cost ceiling from a churn driver into a monetization lever.
The Annotator Calibration Gap: When Human Raters Quietly Stop Agreeing
Six months into a human eval program, the inter-rater agreement number is a weighted average of three different implicit rubrics. The model didn't drift — the measurement instrument did.
The Audit Trail Mismatch: When User, Agent, and Tool Each Have Different Logs
Agent stacks emit four logs that don't agree. The fix isn't more logging — it's a transaction ID minted at the user-action boundary, a unified audit record, and retention sized to the compliance question, not the subsystem.
The Bypass Vocabulary: When Users Learn to Jailbreak in Polite English
Production AI products leak refusals to three-word framings — 'hypothetically,' 'for educational purposes,' 'for a story.' How to detect and defend against the bypass vocabulary your users pick up from social platforms.
Compliance Reviewer as Eval Author: Why Legal Should Be Writing Your Test Cases
Compliance reviewers spot LLM failure modes engineering evals systematically miss. Move them out of document-review gates and into the regression suite — legal sign-off becomes a statement about pinned test cases that run every commit.
Context Bloat: The AI Memory Leak You Cannot Grep For
Long-running agent sessions silently leak tokens — quadratic cost growth and quality degradation hide inside conversation history. How to instrument, prune, and compact it.
Conversational REST: When Your Chat UI Needs Pagination, Filters, and Sort
Chat is a great input modality and a terrible output one. The moment your agent returns more than three results, the right answer is to render UI — not to keep talking.
The Cost of Reversal: Why Pulling Back an AI Feature Is Harder Than Shipping One
Once users build workflows around an AI feature, removing it costs more than launching it did. Why kill switches go unused and how to design reversibility in from launch.
Cost-Per-Conversation as a Product Contract: When Pricing Drives Architecture
Pricing on AI features is an architecture input, not a finance afterthought. What to put in the PRD so engineering doesn't patch unit-economics leaks at midnight.
Cross-Channel Memory: When Your Agent Forgets the Email Thread
Multi-surface AI agents fragment memory across chat, email, SMS, and voice — leaving users with contradictory answers. A look at unified identity, write-through stores, and contextual privacy.
Diurnal Latency: Why Your AI Feature Is Slowest at 9am ET
Frontier model latency follows a daily curve set by other people's traffic. Hour-of-day cohorting, batch routing, and load-aware failover turn a phantom regression into a scheduling problem.
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.
