Page 88
12 articlesThe Data Quality Ceiling That Prompt Engineering Can't Break Through
Prompt engineering hits a hard ceiling when the underlying data is noisy, stale, or duplicated. Here's how to diagnose data failure vs. model failure and what actually moves the needle.
The Document Is the Attack: Prompt Injection Through Enterprise File Pipelines
Why naive document ingestion pipelines—PDFs, emails, spreadsheets—are rich prompt injection vectors, the specific attack patterns attackers use, and the content provenance architecture that actually defends against them.
EU AI Act Compliance Is an Engineering Problem: The Audit Trail You Have to Ship
High-risk AI systems under the EU AI Act require auditable decision logs, human oversight hooks, and conformity assessments that can't be bolted on post-launch. Here's the data model, logging architecture, and oversight trigger design that make compliance an engineering discipline.
GDPR's Deletion Problem: Why Your LLM Memory Store Is a Legal Liability
RAG pipelines and long-term LLM memory stores are personal data processors under GDPR. The right to erasure creates a deletion propagation problem that standard vector databases cannot solve cleanly — here are the architectural patterns that make LLM memory legally operable in the EU.
The Golden Dataset Decay Problem: When Your Eval Set Becomes a Liability
Curated eval sets silently drift from production reality over months. Learn how to detect when your evals are measuring the wrong thing, the rotation strategies that keep benchmarks honest, and the monitoring triggers that tell you it's time to rebuild.
Goodhart's Law Is Now an AI Agent Problem
AI agents are mathematically exhaustive optimizers — when a proxy metric becomes the training target, capable models reliably find and exploit it. Here's how to audit your reward signals before they become attack surfaces.
Graceful Tool-Call Failure: The Error Contract Your Agent UI Is Missing
Most agent UIs handle the happy path and nothing else. Here's the error contract and UX patterns that turn tool-call failure from a crash into a recoverable moment.
Defining Escalation Criteria That Actually Work in Human-AI Teams
Most AI teams treat escalation as an afterthought. Here's how to define structured escalation specs, pick the right confidence thresholds, and build feedback loops that improve over time.
Idempotency Is Not Optional in LLM Pipelines
Traditional idempotency breaks when outputs are stochastic. Here's the architectural rethink that prevents duplicate actions, cost explosions, and corrupted state machines in production LLM systems.
The Prompt Made Sense Last Year: Institutional Knowledge Decay in AI Systems
When the engineers who built your AI system leave, the system doesn't break immediately — it rots slowly. Here's how to prevent the decay with prompt rationale files, eval provenance logs, and guardrail justification comments.
When Vector Search Fails: Why Knowledge Graphs Handle Queries Embeddings Can't
Vector search fails silently on multi-hop queries, entity disambiguation, and cross-document reasoning. Here's when knowledge graphs and hybrid retrieval are the right architecture.
The Last-Mile Reliability Problem: Why 95% Accuracy Often Means 0% Usable
95% accuracy sounds great until you realize it means your 20-step AI workflow succeeds only 36% of the time. Here is the failure taxonomy and the architectural fixes that actually close the last mile.
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.
