Page 11
12 articlesYour Tool Schema Validates Types, Not Units
A refund tool that takes cents will get dollars, because JSON Schema validates shape, not meaning. How unit confusion slips past types, schemas, and evals — and the naming, boundary-assertion, and eval patterns that stop 100x invoices.
Your Users Drift While Your Model Stands Still
Quality metrics sag six weeks after launch with no deploy in sight — because users adapt faster than models change. How to instrument input drift, cohort-split your metrics, and refresh evals on the timescale of user habituation.
Exactly-Once Was Hard Before Your Agent Could Retry Itself
Idempotency keys assume the caller repeats its request byte-for-byte. An agent paraphrases its own request on retry, which breaks that assumption. Here is how to build tool-level dedup that holds when the caller is a language model.
Model Collapse Starts in Your Own Data Lake
Logged LLM outputs quietly become next quarter's training data. How model collapse takes hold inside your own data lake — and the provenance tagging, quarantine zones, and tail evals that break the feedback loop.
When the Clock Is a Tool: Agents, Time Zones, and the Bug That Only Happens at Midnight
LLMs have no internal clock, so agents drift confidently onto stale time — and it surfaces as skipped schedules, wrong time-zone math, and cache-busting timestamps. Here is how to supply the current moment as infrastructure.
Conway's Law Comes for Your Agent Fleet
Your multi-agent topology copies your org chart by default — silos, lossy handoffs, and central bottlenecks included. Here's when that coupling becomes a bug and how to draw agent boundaries from the problem instead.
Temperature Zero Is Not Determinism: Reproducing the Incident You Can't Re-Run
Setting temperature to zero forces greedy decoding but does not make LLM inference reproducible. Batch-dependent GPU numerics, not the sampler, flip your tokens — and here is how to build a post-mortem for the run you can't re-run.
The Hidden Ops Org Behind Your Evals: Annotator Economics
Every eval score inherits the quality of a human labeling pipeline you don't budget for. How annotator economics, throughput-driven quality decay, and LLM judges shape the numbers you ship.
The Indemnification Gap: When Your Agent Takes an Irreversible Action, Whose Budget Eats It?
An autonomous agent can commit losses many times larger than your vendor's liability cap, and 2026 insurance exclusions are closing the backstop. Here is how to make autonomy a priced spending decision before the incident.
When Streaming Tokens Meet the Screen Reader: The Accessibility Debt of Generative UIs
Streaming tokens into an aria-live region is the easiest line of code to write and the hardest accessibility bug to unwind. How generative UIs accrue accessibility debt — and the architecture that prevents it.
When the Round Trip Is the Bug: The Case for On-Device Inference You Keep Dismissing
The latency, cost, and privacy math that quietly flips against the cloud round trip — and the per-request routing patterns that decide where each query actually runs.
Shadow AI: Stop Blocking, Start Governing the Leak That Already Happened
Employees already pasted production code and customer data into consumer chatbots. Here is why blocking backfires, how to discover the leakage, and what a governed AI alternative looks like.
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.
