Page 12
12 articlesThe Model Card Your Procurement Team Treated Like a Datasheet
Procurement reviewers read model cards as contractual representations, not research disclosures. Author a separate vendor due-diligence package before legal binds you to claims your engineering team wrote as narrative.
The Model Deprecation Notice That Landed During Your Code Freeze
Provider deprecation cadence is not external weather. Treat vendor clocks as production infrastructure so the next sunset notice doesn't re-prioritize your quarter.
The Near-Duplicate Filter That Took Your Only Hard Example With It
Aggressive near-duplicate filtering treats your hardest examples like noise. Here is why dedup pipelines silently shrink the distribution at exactly the slices you needed coverage on, and how to stop one from grading itself a win.
The OAuth Scope Your Agent Acquired Across Chained Tool Calls
OAuth consent treats agents like single-purpose apps, but each chained tool call expands the realized authority your audit log has to explain. The one-shot screen rendered the worst case as one decision.
The On-Call Rotation Your Agent Platform Forgot to Staff
An AI platform team of four ships an internal agent for 200 daily users, then forgets to staff the on-call rotation — and learns the SRE staffing math the hard way.
The PII Redactor Whose Own Training Corpus Was the Leak Vector
A fine-tuned redactor trained on real PII is a model with read access to every protected record in its training set, deployed behind an API anyone can query — and that fact rarely makes it into the privacy review.
The PR Description Your Coding Agent Generated That Humans Stopped Reading
PR description templates worked when humans wrote them and shape carried signal. Agent-generated descriptions strip the variance, reviewers habituate, and the review process silently routes around the artifact it depended on.
The Prompt Hot-Reload That Orphaned Every In-Flight Agent Run
A clean prompt push at 11:46pm and a hallucinated refund a minute later — why prompt registries need to treat sessions as contracts, not caches, when agents are in flight.
The prompt injection that survived your sanitizer because the agent read it through a tool
Input sanitizers sit between the user and the model, but tool-using agents have a dozen other ingestion paths. Here is why retrieved documents, web fetches, MCP responses, and other agents' outputs bypass your classifier, and what a tool-aware defense actually looks like.
The Provider Failover That Swapped Your Safety Policy Mid-Conversation
Multi-provider LLM failover treats vendors as interchangeable, but their refusal thresholds, tone, and content boundaries differ. Here is how the gateway becomes the policy surface — and what session affinity and a unified moderation layer actually fix.
The Provider Quota Reset on a Timezone Your Global Traffic Never Picked
Provider quotas reset on the provider's clock, not the customer's. When the cycle's hot end overlaps your peak traffic timezone, 429s look like noise — and the UTC dashboard hides why.
The Reasoning Tokens Your Product View Never Surfaces
Extended thinking creates a per-call reasoning artifact your engineers can see and your support, PM, and incident teams cannot. The seam is where customer escalations land.
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.
