Engineering, Leadership & Management
What a Week of AI Coding Agents Actually Cost Me
Aaron Wise
Real numbers from one week of Claude Code and Codex — cost, cache savings, CI minutes, what ran, and what broke.
Editor's Pick
View All
Leadership & Management
More in Leadership & ManagementWhat a Week of AI Coding Agents Actually Cost Me
Aaron Wise
Real numbers from one week of Claude Code and Codex — cost, cache savings, CI minutes, what ran, and what broke.
Leading Teams Where Agents Write Half the Code
Aaron Wise
Leading engineering teams with AI coding agents: make review the main job, keep a named human owner per system, and retrain juniors for judgment.
Reporting Engineering to the Board Without Vanity Metrics
Aaron Wise
Engineering metrics for the board: report predictability, reliability, cost, risk and capacity, drop activity counts, and adapt the page as you grow.
Product Management
More in Product ManagementPricing Is a Product Decision Engineering Needs to Be In On
Aaron Wise
SaaS pricing decisions set architecture: seats, plan limits and usage billing each have a build cost. Bring engineering in to cost options before launch.
Build, Buy or Wait Is a Different Call at Each Stage
Aaron Wise
Build vs buy decisions by company stage: buy by default, build where you differ, wait with a trigger, and revisit every vendor call at Series B.
Engineering
More in EngineeringWhat a Week of AI Coding Agents Actually Cost Me
Aaron Wise
Real numbers from one week of Claude Code and Codex — cost, cache savings, CI minutes, what ran, and what broke.
Your Coding Agents Are Making Supply-Chain Decisions
Aaron Wise
Coding agents and supply chain security: agents add packages and run install scripts nobody approved. Gate new dependencies, sandbox agents, pin builds.
Must Read
View All
Engineering, Insights, Leadership & Management, Must Read
The Wrong Kind of Early: When Startups Aren’t Ready for Senior Engineering Leadership
Senior engineering leaders need a clear problem, founder-market fit, and rough business plan before joining a startup.
Roadmap Roulette: Choosing the Right Prioritization Model for Every Stage of Growth
The right roadmap prioritization model depends on your company’s growth stage and strategic goals.
Data Science
More in Data Science
Evaluations Are the Spec for an LLM Feature
Aaron Wise
LLM evaluation sets are the spec: write twenty good-answer test cases before building, with product owning the bar and engineering keeping it green.
Beyond Words: How NLP Turns Flat Text into Context
Aaron Wise
NLP adds context to flat text through statistical and neural models, enabling machines to act on meaning rather than symbols.
Compressing the Clock: Scaling from Data Disarray to AI Impact in 18 Months
Aaron Wise
Azure builds a reliable AI platform by combining native services with third-party tools, structured environments, and a cross-functional team.
Recent Posts
Search all posts
The First Data Platform: What a 30-Person Company Actually Needs
A first data platform for a 30-person startup: one warehouse, managed ingestion, SQL transforms and one BI tool, plus the signals that justify more.
Evaluations Are the Spec for an LLM Feature
LLM evaluation sets are the spec: write twenty good-answer test cases before building, with product owning the bar and engineering keeping it green.
Reporting Engineering to the Board Without Vanity Metrics
Engineering metrics for the board: report predictability, reliability, cost, risk and capacity, drop activity counts, and adapt the page as you grow.
Build, Buy or Wait Is a Different Call at Each Stage
Build vs buy decisions by company stage: buy by default, build where you differ, wait with a trigger, and revisit every vendor call at Series B.
Crossing Organizational Boundaries
More in Crossing Organizational Boundaries
Product Management, Cross Organizational
Pricing Is a Product Decision Engineering Needs to Be In On
SaaS pricing decisions set architecture: seats, plan limits and usage billing each have a build cost. Bring engineering in to cost options before launch.
Cross Organizational, Engineering
Explaining Cloud and AI Spend to a CFO
How to explain cloud and AI costs to a CFO: unit costs, range forecasts with named drivers, commitments shown apart, and what changes by stage.