Page 17
12 articlesBuild vs. Buy Is the Wrong Question for Your AI Feature
An AI feature is a stack of five layers, not one thing to make or purchase. The decision that matters is which layer compounds your differentiation and which one a competitor can simply buy.
Capacity Planning When Every Request Thinks a Different Amount
Agent requests don't have a stable cost — one resolves in 200 tokens, the next burns a million. Why p50 forecasts fail for agent workloads, and how to plan in token and tool-call distributions instead.
The Carbon Line Item Nobody Puts in the AI Feature Spec
Every AI feature review argues latency, token cost, and accuracy — and never energy. Here is how to measure per-request carbon and make it a number a team owns.
The Eval Budget Your CFO Cannot See on a Spreadsheet
Eval investment compounds like a test suite, but it shows up as cost with no revenue line — so it loses every prioritization fight to a feature with a demo. Here is how to make its counterfactual value legible to finance.
The Fault You Never Inject: Feeding Your Agent a Tool That Lies
Your agent is fault-tested against timeouts and 500s, but never against a tool response that is fast, well-formed, and confidently wrong — the failure it is least equipped to catch.
The GUI Agent That Clicked the Right Button on the Wrong Screen
Computer-use agents fail not because they ground the wrong element but because the screen moves between observation and action. A look at screen-state drift and how re-grounding fixes it.
Hiring for AI Roles That Have No Career Ladder Yet
The title 'eval engineer' didn't exist two years ago, so there's no leveling rubric and no resume that matches. Define the role around a real failure, screen for judgment over tools, source sideways from QA and platform, and write the ladder before you make the offer.
MCP Server Sprawl: The Unbounded Tool Surface Nobody Owns
Every team wires in another MCP server, and the agent's tool surface grows with no owner, no budget, and a token tax on every turn. How sprawl breaks selection accuracy and what curation discipline fixes it.
The Postmortem Where the Root Cause Was a Prompt Nobody Owned
A production incident traced back to a system prompt edited weeks earlier with no PR, no reviewer, and no owner. Why prompts keep escaping change management, and how to put them back under review without killing iteration speed.
Your Retry Logic Is Teaching the Agent the Wrong Lesson
Retry policies built for flaky networks assume the caller is correct. Agents make the caller the unreliable part, and a blind retry quietly launders real bugs into green checkmarks.
Your Synthetic Training Data Is Collapsing Toward the Mean
Synthetic data generated to fill dataset gaps quietly contracts toward the mean, erasing the rare cases you needed. Why per-example quality checks miss it, how to measure set-level diversity, and how to anchor generation to real data.
The Token Budget Is a Product Decision, Not a Config Value
The line that sets your context window split — history versus retrieval versus tool output — is a product decision hiding in an f-string. Here is how to surface it, measure it, and give it an owner.
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.
