Blog
Agent teams, in writing.
Notes on running agent teams inside an engineering org: who reviews the code, what a person still decides, and what the work actually costs.
LLM Router: How Model Routing Cuts AI Coding Cost
What an LLM router is, how it picks a model per step, and the arithmetic of routing a coding agent's work across lanes without losing quality.
Read the post →Claude Code Team Plan: Budgeting a Rollout for Your Org
The Claude Code Team plan in October 2026: seat prices linked, what a seat includes, where usage credits start, and the math for a 30-developer rollout.
Read the post →How Much Does Claude Code Cost? Plans, API, and Team Math
How much Claude Code costs in October 2026: every plan with Anthropic's prices linked, when the API meter kicks in, and what a team's bill really is.
Read the post →AI Agents for Software Development: A Team You Can Manage
AI agents for software development, run as a team an engineering leader can manage: six named Agents, fixed checkpoints, a record per ticket, one meter.
Read the post →AI for Engineering Managers: Manage Agents Like a Team
AI for engineering managers: run coding agents the way you run people, with ownership, review, and a record, what to check each morning, and what it costs.
Read the post →AI Agent Audit Trail: What the Record Should Show
An AI agent audit trail for engineering work: the record per ticket, who approved each step by name, proof from the source, and what it cost per Agent.
Read the post →Context Engineering for Coding Agents: Where the Why Lives
Context engineering for coding agents, for a team: the files are table stakes. The value is the decisions and corrections your code does not show.
Read the post →AI Backlog Management: Propose, Don't Auto-Prioritize
AI backlog management for Jira and Linear: an agent that proposes the next ticket with evidence, waits for a named person, and keeps the record.
Read the post →Async Standup: Build It From GitHub and Jira, Not Forms
An async standup that writes itself from GitHub, Jira, and Linear: what shipped with the receipt, what is in flight, what needs a person, posted to Slack.
Read the post →Human in the Loop AI Agents: Where the Person Actually Sits
Human in the loop AI agents, concretely: the three clicks a person keeps on a ticket, what they read, the record it leaves, and how a line earns autonomy.
Read the post →What Is AI QA Testing, and What Should a Testing Agent Do?
AI QA testing for an engineering team: what a testing agent may do on a pull request, what it never does, when it runs, who owns the verdict, and the cost.
Read the post →What Should a Jira AI Agent Do with an Engineering Ticket?
A Jira AI agent for engineering work: one ticket from backlog to merged pull request, written back to Jira at every step, with a person at three clicks.
Read the post →What Is Spec-Driven Development with AI Coding Agents?
Spec-driven development with AI: what the spec is, who approves it on a team, what the review checks it against, and what the record shows after merge.
Read the post →What Is Agentic Engineering, and How Is It Not Vibe Coding?
Agentic engineering is coding agents doing the work under a plan a person approves, a review a person can read, and a record. Vibe coding has none.
Read the post →What Is the Agentic Software Development Lifecycle?
The agentic software development lifecycle in six stages: which Agent owns each stage, where a person approves, and what the record shows at the end.
Read the post →AI Code Review Tools: What to Look For Before Turning One On
A manager's guide to AI code review tools: who is accountable, what the record shows, what stays gated, what it costs, and how the tools compare.
Read the post →GitHub AI Code Review: What It Posts and Who Still Merges
How AI code review works on GitHub pull requests: what a good reviewer posts, why it never blocks, how to set one up, and why a person still merges.
Read the post →What Is Automated Code Review, and What Does It Miss?
Automated code review spans linters, static analysis, and AI reviewers. What each catches, what none know without a plan, and who owns the merge.
Read the post →What Should Autonomous Coding Agents Be Allowed to Own?
Autonomous coding agents can own a ticket from an approved plan to a draft pull request. What stays with a person, and the record that makes it hold.
Read the post →What Amazon Mandating AI Code Review Means for Your Team
Amazon reportedly made senior engineers sign off on AI-assisted changes after outages. The management lesson for engineering leaders, with sources.
Read the post →Clear Your Pull Request Review Backlog Without a Tech Lead
How to clear a pull request review backlog without a tech lead: routing that works with no manager enforcing it, and when to actually hire one.
Read the post →How to Track Engineering Progress Without a Project Manager
How to track engineering progress without a project manager: PR review backlog, ticket throughput, and the tool-by-tool workflow that actually covers it.
Read the post →What Is the Best Coding Agent?
The best coding agent isn't the top benchmark score. It's the one whose mistakes you can catch, trace, and afford: judged on trust, not codegen.
Read the post →How to Manage AI Coding Agents and Keep Them Accountable?
Managing AI coding agents means naming an accountable owner, logging what agents did, and gating risk by blast radius, not by trust alone.
Read the post →Who Reviews AI-Written Code, and Can You Trust It?
Who actually reviews AI-written code, and can you trust it? The accountability gap the SERP skips, plus a graduated trust framework by blast radius.
Read the post →What Is Adversarial AI Code Review?
Adversarial AI code review means a separate reviewer argues to reject a diff instead of summarizing it. What it is and how to keep it from crying wolf.
Read the post →Will AI Replace Software Engineers?
Will AI replace software engineers? The 2026 data on how much code agents write, why layoffs aren't coming from AI output yet, and what actually changes.
Read the post →From the archive (46 posts)
Written for an earlier version of YAGNI, before it focused on engineering teams. Kept for anyone who linked to them.
- How to Manage Cash Flow Without a Finance Team
- How to Run Marketing Operations Without a Marketing Ops Hire
- How to Run Customer Support Operations Without a Support Hire
- How to Run Recruiting Operations Without a Recruiter
- How to Run Revenue Operations Without a RevOps Hire
- AI Agent vs a Fractional Chief of Staff
- AI Agent vs Tool vs Ops Hire: What Growing Teams Need
- AI Copilot vs AI Agent: Where Each One Actually Lives
- AI Agent vs Virtual Assistant: What Actually Changes
- What Can an AI Agent Do for a Small Business?
- AI Sidebar vs AI Agent That Reads Everything
- Do I Need an Ops Hire or an AI Agent? Here's the Test
- AI Agent vs Hiring an Ops Person: What the Decision Actually Costs
- AI Assistant vs AI Agent: The Difference That Matters
- Tool Sprawl: Why Your Team Is Drowning in Tools
- Stop Reassembling Status Across Tools
- How to Get a Single View of the Business, No Warehouse
- Should I Build My Own AI Agent to Run My Business?
- AI Brief for a Remote Operations Lead
- The Founder's Guide to Running Operations Without an Ops Team
- AI Agent vs Custom GPT for Business: The Honest Comparison
- Build an Internal AI Agent for Operations: What to Know First
- Build vs Buy AI Agent: What the Decision Actually Turns On
- Cost of Building Your Own AI Agent: What the Estimates Leave Out
- How to Keep Your Team on the Same Page: The Context Problem
- How to Maintain an AI Agent Over Multiple Tools
- Reduce Context Switching at Work: Two Problems, Two Fixes
- Should You Build Your Own AI Agent? The Definitive Answer
- Startup Tech Stack for a 10-Person Company
- The Too Many SaaS Tools Problem: What Actually Fixes It
- Why DIY AI Agents Fail (and What It Actually Costs)
- Product Ops Software for Startups
- Operations Software for a 50-Person Remote Team
- Founder as Chief of Staff: How to Do the Job Yourself
- Chief of Staff Tools for Remote Teams
- How to Run Operations Without an Ops Team
- How to Stay on Top of a Scattered Remote Team
- How an Autonomous Business Runs Operations With AI Agents
- What Is an AI-Powered All-in-One Workspace?
- How to Run an Autonomous Business
- Agent-Native Software for Remote Teams
- How to Automate Startup Operations With AI
- AI Agents for Business Operations: What They Actually Do (2026)
- How Do AI Agents Earn Trust to Act?
- How to Become an Autonomous Business
- Introducing YAGNI: your whole company, on one page.