Agentic Workflows
Tool-agnostic habits for getting dependable work out of any coding agent.
Write The Spec First
A short spec — what, why, constraints, tasks — stops your coding agent from guessing the details you didn’t mention.
Tip #020Match Effort To Task Size
Running several agent sessions at once? Set each one’s reasoning effort to match its task so quick questions don’t wait behind deep ones.
Tip #021Bash Or MCP
Don’t wire an MCP server for tools your agent can already reach with bash. A decision rule for when a server actually earns its keep.
Tip #137Order CI Stages Cheapest and Most Likely to Fail First
Stop wasting ten minutes to catch a typo — order your CI so the cheapest, most likely-to-fail checks run first and fail fast.
Tip #138Never Make a Flaky Test a Required Gate
A test that passes on retry is a defect, not a hiccup — quarantine it so the required gate keeps meaning something and your team never learns to just hit retry.
Tip #141Plan the Funeral Before You Build
When you design anything new, ask how you’d delete it in three years — the answer forces clean interfaces, flags, and a small surface area that stays cheap to kill.
Tip #142Hyrum’s Law: With Enough Users, Even Bugs Get Depended On
With enough users, every observable behavior of your system becomes an API someone depends on — which is why deprecation is a migration you run, not a memo you send.
Tip #143Ask What Your Agent Didn’t Touch
Make every agent change end with a Changes / Didn’t-touch / Concerns summary so scope creep surfaces before your reviewer finds it.
Tip #146Stop Your Agent Every 100 Lines to Test
Never let a coding agent write more than ~100 lines before you test — thin vertical slices keep bugs small, local, and cheap to fix.
Tip #147Tell Your Agent to Note, Not Fix, Out-of-Scope Issues
One CLAUDE.md rule keeps a coding agent from bloating your pull request — when it spots an unrelated problem, it writes it down instead of fixing it.
Tip #148Make Your First Task a Tracer Bullet
Your first task should be a tracer bullet: the thinnest slice through every layer that proves the path before you build wide.
Tip #149If a Task Title Contains “And”, Split It
The word “and” in a task title usually hides two tasks. Split until each fits in ~5 files, ≤3 acceptance bullets, and one focused agent session.
Tip #150The Bug in an AI PR Lives in the Callers
The bug in an AI-generated PR usually isn’t in the diff — it’s in the callers the diff never shows you. Review the blast radius, not just the changed lines.
Tip #151Read the Tests Before the Code
In a pull request, read the tests first and the code second — the tests encode the author’s intent, and a risky path with no test is itself a finding.
Tip #152Make Your AI List Its Assumptions Before It Writes Code
One instruction — 'list every assumption, then wait for my correction' — catches the misunderstanding while it still costs a sentence to fix instead of an afternoon of rework.
Tip #153An Untested Rollback Is Not a Rollback
A rollback plan you have never exercised is a hope, not a plan. Prove the kill switch turns the feature off in seconds — before launch, not during the incident.
Tip #184Add One Line to Every AI Research Prompt
Ask an AI a broad research question and it mirrors back what you already believe. One line forcing contrarian evidence and downside cases turns confirmation bias into a real decision brief.
Tip #185When Structure Won’t Come, Skip the Outline
Forcing an outline before you have the spine of a piece builds a skeleton you write to, and it reads like it. Dump every fragment into one file and let structure emerge one paragraph at a time.
Tip #186Ban AI From Simulating Specificity
AI cold email’s deadliest move is faking specificity. Ban the model from inventing anchors and require one real, verifiable observation per email, or flag the draft as not ready.
Tip #188Force Ambiguous Choices Into a Strict 3-Line Brief
When an AI hits an ambiguous choice it hands back three hedged paragraphs that end in 'it depends.' Force a three-line decision brief — ELI10, Stakes, Recommendation — so it must commit to one pick.
Tip #189Make the Stakes Concrete: Blast Radius, Reversibility, Time Cost
'Could cause issues' is not a risk assessment. When an agent surfaces a decision, make it name the blast radius, whether it’s reversible, and the time cost of getting it wrong.
Tip #190Never Pass Your Conclusion to a Reviewer Agent
Hand an AI reviewer your conclusion and it validates your conclusion. Give it only the artifact and the contract, prompt it to find what is wrong, and it surfaces the issues you could not see.
Tip #191Cap Adversarial Review at Three Cycles
Adversarial self-review catches blind spots, but looping it forever just stalls on the same findings. Cap it at three cycles; if real issues survive, that’s information about the artifact, not a reason to loop again.
Tip #192Block Your AI’s First Edit
Agents edit files they never actually read. Block the first mutation until the agent lists importers, names affected public functions, and shows real data shapes. No facts, no edit.
Tip #193Make Your AI Quote Your Instruction Verbatim
Agents quietly reinterpret your request and build a polished version of something you never asked for. One line — quote my instruction back word for word before touching code — surfaces the drift instantly.