Oct 2, 2026
What Is a Passkey? A Plain Guide for App Builders
A passkey replaces your password with a key stored on your device, unlocked by biometrics. How it works, why phishing fails on it, and when to add one.
Steve Jefferson
Oct 2, 2026
How to Check if Your AI-Built App Exposes User Data
A 20-minute test for an AI-built app on Supabase: list tables without row level security, read your own data as a stranger would, and fix what leaks.
Steve Jefferson
Oct 2, 2026
Customer Sent a Photo Instead of Details?
A customer sent a photo instead of details? Turn it into a quote fast. What AI reads reliably from an image, the extraction prompt, and the human checks.
Steve Jefferson
Oct 2, 2026
Turn a Long Email Thread Into a Decision With AI
Turn an email thread into a decision with AI. Summarising gives a recap, not an answer. A prompt that extracts decisions and open questions, with quotes.
Steve Jefferson
Oct 1, 2026
How to Ask AI to Write the Prompt for You
Let the AI interview you, draft the prompt, then break it on purpose. A three-step method with a reusable template for prompts you will run again and again.
Steve Jefferson
Oct 1, 2026
How to Use AI to Read Receipts and Invoices
AI can pull dates, vendors and totals out of messy receipts, but it sometimes misreads a digit. A field schema, three arithmetic checks and a review queue keep errors out of your books.
Steve Jefferson
Oct 1, 2026
Does Role Prompting Work? A Three-Prompt Test
Does telling an AI to act as an expert make it better? Mostly it changes voice and format, not facts. A three-prompt test shows what your task gets from a role.
Steve Jefferson
Oct 1, 2026
Prompt AI With a Worked Example, Not Rules
Prompt AI with a worked example and it beats a list of rules. How to build one, what a good example must contain, and the cases where examples hurt.
Steve Jefferson
Oct 1, 2026
Stop an AI Receptionist Double Booking Slots
An AI receptionist double booking appointments is almost never a prompt problem. It is a missing hold between offering a slot and confirming it.
Steve Jefferson
Oct 1, 2026
When AI Quotes a Customer the Wrong Price
AI quoted a customer the wrong price. Whether you have to honour it, how to respond in the first hour, and the three controls that stop a repeat.
Steve Jefferson
Sep 30, 2026
How to Set a Confidence Threshold for an AI Classifier
A confidence threshold decides which AI answers run automatically and which go to a person. Set it from a labelled test set, then price errors against review time.
Steve Jefferson
Sep 30, 2026
How to Set a Budget Cap on an AI Coding Agent
How to set a budget cap on an AI coding agent: the three places a cap can live, the failure mode of each, and why a cap without a kill path breaks builds.
Steve Jefferson
Sep 30, 2026
How to Get AI to Flag What It's Unsure About
How to prompt AI to flag what it is unsure about: why confidence scores mislead, and three patterns that surface real uncertainty you can act on.
Steve Jefferson
Sep 30, 2026
How to Write a Goal for an AI Agent
How to write a goal for an AI agent: four fields that stop it redefining done, a before and after rewrite, and how to test the goal before you trust it.
Steve Jefferson
Sep 25, 2026
What to Do When an AI Coding Agent Says It's Done
Completion is a claim from an interested party. Seven checks in yield order, plus the three buckets that decide how you respond to a failure.
Steve Jefferson
Sep 25, 2026
Prompt AI With an Example of What You Don't Want
Show the model a bad example and it often copies it. Labelling, pairing and ordering are what turn a negative example into a useful one.
Steve Jefferson
Sep 25, 2026
How to Prompt AI to Give a Shorter Answer
Brevity is a judgement and shape is a rule. Constrain the shape instead, and one format swap that does more than any length instruction.
Steve Jefferson
Sep 24, 2026
How to Limit What an AI Agent Can Reach on Your Network
Open network access is the default for most agent setups and the wrong one. Here is how to build an allowlist that survives a persistent agent.
Steve Jefferson
Sep 23, 2026
How to Prompt AI to Write Meeting Agendas
Tie agenda structure to decision type, info-share, decision, or brainstorm, and force AI to flag any item with no owner or no decision needed.
Steve Jefferson
Sep 23, 2026
How to Prompt AI to Write a Case Study
A two-pass prompting method that forces AI to extract a real number and a real quote before it writes a single word of your next case study.
Steve Jefferson
Sep 23, 2026
How to Prompt AI for a Weekly Status Report
Most AI status reports are a list of everything that happened. Here is the prompt structure that produces the three things a reader actually needs.
Steve Jefferson
Sep 23, 2026
Get an AI Coding Agent to Update the Docs
AI coding agents write code and leave the docs stale. Four changes that make documentation updates part of the diff instead of a separate chore.
Steve Jefferson
Sep 22, 2026
How to Prompt AI to Write Test Cases That Matter
The naive test-writing prompt produces tests that only confirm code does what it obviously does. Here is the two-pass structure that fixes that.
Steve Jefferson
Sep 22, 2026
How to Prompt AI to Write a Handover Document
Ask a model to write a handover document and you get a tidy summary of what you already told it. The useful version starts with questions.
Steve Jefferson
Sep 21, 2026
How to Prompt AI to Write a Risk Register That Isn't Generic
A bare 'write a risk register' prompt produces generic filler. Here is how to feed AI project specifics and a scoring rubric so it produces one you can actually act on.
Steve Jefferson
Sep 21, 2026
How to Prompt AI for a SWOT Analysis That Isn't Generic
A bare 'do a SWOT analysis' prompt gets you filler. Here is how to feed AI real facts so it produces a SWOT you could actually act on.
Steve Jefferson
Sep 21, 2026
How to Prompt an AI Coding Agent to Fix a Memory Leak
Vague prompts produce vague fixes. Here is how to feed an AI coding agent heap snapshot evidence so it finds the actual retained reference instead of guessing.
Steve Jefferson
Sep 21, 2026
How to Prompt AI to Audit Your Dependencies
An AI model asked to review your dependencies from memory will invent vulnerabilities and miss real ones. Asked to reason over output you paste in, it does something a scanner cannot: judge whether a package is worth keeping.
Steve Jefferson
Sep 20, 2026
How to Use AI to Handle Overbooked Appointments
A decision framework for who to bump when appointments collide, how to script an apology that doesn't sound robotic, which channel to use, and a ready-to-use AI prompt for drafting the reschedule message.
Steve Jefferson
Sep 20, 2026
How to Use AI to Forecast Cash Flow for Your Business
A practical walkthrough for forecasting cash flow with AI: what data to prepare, a ready to use prompt, and the mistakes forecasts commonly make with seasonality, one-off costs, and growth assumptions.
Steve Jefferson
Sep 20, 2026
How to Prompt AI to Turn Notes Into a Study Guide
A three-step AI prompt chain that turns messy lecture notes into a structured study guide and spaced-repetition-style practice questions, with a before-and-after example.
Steve Jefferson
Sep 20, 2026
How to Get an AI Coding Agent to Explain a Stack Trace
A worked example showing the exact prompt structure that gets an AI coding agent to read the failing frame of a stack trace instead of guessing from the error message alone.
Steve Jefferson
Sep 20, 2026
How to Use AI to Decide on a Second Location
Make it argue against the opening. You already have the case for it. What you need is the assumptions your plan depends on, ranked by what they cost.
Cecilia Iona
Sep 20, 2026
How to Use AI to Prepare for a Health Inspection
Turn the inspector's published framework into a self-audit you run two weeks early, then use AI on the records pile. It cannot see your kitchen.
Cecilia Iona
Sep 19, 2026
How to Prompt AI to Rewrite Something in Plain English
Plain English is not one instruction, it is about five. The prompt that names each transformation, and the output checks that catch softened obligations.
Steve Jefferson
Sep 19, 2026
How to Seed Test Data in an AI-Built App
Generated sample data passes every test and hides every real bug. How to write a seed script that reproduces the shapes that actually break an app.
Steve Jefferson
Sep 19, 2026
Why Emails From Your AI-Built App Go to Spam
If mail from your AI-built app lands in spam, the send is working and the receiver does not trust it. A header-first diagnostic order for SPF, DKIM, DMARC and reputation.
Steve Jefferson
Sep 19, 2026
Prompt AI to Turn a Job Posting Into Interview Questions
A prompt that turns a job posting into role-specific interview questions, plus how to avoid the generic list every other candidate has already seen.
Steve Jefferson
Sep 19, 2026
How to Prompt AI to Simplify Legal Jargon in a Lease
A prompt for turning dense lease clauses into plain English without losing anything that matters, plus the one instruction that keeps it accurate.
Steve Jefferson
Sep 18, 2026
How to Prompt AI to Turn a Voice Memo Into Meeting Notes
A prompt template for turning a rambling voice memo into structured meeting notes, plus what to include so AI does not miss the real decisions made.
Steve Jefferson
Sep 18, 2026
What Breaks First When an AI-Built App Gets Real Traffic
The order AI-built apps actually break in under real traffic: connection pools, N+1 queries, sessions, storage costs, queues, and rate limits.
Steve Jefferson
Sep 18, 2026
How Much Detail Should an AI Prompt Have?
Vague prompts get generic answers. Over-specified prompts get compliance without judgment. Here is how to tell which failure you are looking at.
Steve Jefferson
Sep 18, 2026
How to Hand Off a Task Between AI Coding Agents
Agent one ran out of context. Agent two picks up the branch and immediately redoes work that was already done. The fix is a handoff note with seven specific fields.
Steve Jefferson
Sep 18, 2026
Which AI Agent Actions Should Never Be Reversible
The useful question is not whether your agent will make a mistake. It is whether you can take the mistake back. Here is how to sort actions by reversibility.
Steve Jefferson
Sep 17, 2026
How Much of Your Codebase Should an AI Agent See?
More context is not better context. Dilution, pattern contamination and scope creep all get worse as you add files. A narrow slice plus an accurate map wins.
Steve Jefferson
Sep 17, 2026
How to Keep an AI-Built App Maintainable
Apps built with AI decay in four specific places: dependencies, expiring credentials, undocumented rules and pattern drift. A ninety-minute quarterly pass covers all four.
Steve Jefferson
Sep 17, 2026
What to Do When Your AI Coding Agent Runs Out of Context
It rarely fails loudly. It contradicts an earlier decision, re-reads a file it already saw, forgets a stated constraint. Here is how to checkpoint and recover mid-task without losing the work already done.
Steve Jefferson
Sep 16, 2026
How to Prompt AI for a Pre-Mortem on Your Project Plan
Imagine the project already failed, six months from now, then work backward to why. Here is the exact AI pre-mortem prompt, a worked example, and how it differs from a postmortem.
Steve Jefferson
Sep 16, 2026
How to Add Idempotency Keys to an AI-Built App
Retries, timeouts, and double-clicks should never double-charge a customer. Here is how idempotency keys work, the exact table schema, and the prompt that avoids the in-memory-cache trap.
Steve Jefferson
Sep 16, 2026
How to Add Pagination to an AI-Built App
Offset pagination demos perfectly and breaks in production: users skip records and see others twice, without anything appearing to go wrong. Keyset pagination fixes it.
Steve Jefferson
Sep 16, 2026
AI Coding Agent Keeps Asking for Permission? Fix It
The problem is not that your agent asks too much. It is that you now approve without reading, which means the permission prompt has stopped being a safety control.
Steve Jefferson
Sep 16, 2026
Take Over a Task Your AI Coding Agent Didn't Finish
When an agent stops halfway, do not read its summary and do not start over. Read the diff and build a three-column audit of what changed, what was verified, and what was assumed.
Steve Jefferson
Sep 16, 2026
How to Add Email Verification to an AI-Built App
A working email verification flow needs more than a link and a token. The security details and product decisions that are easy to skip.
Steve Jefferson
Sep 16, 2026
How to Add a Tagging System to an AI-Built App
A tagging feature looks simple until someone tries to filter or merge a tag. The right data model from day one avoids the rewrite.
Steve Jefferson
Sep 15, 2026
Why an AI Coding Agent Re-Runs a Finished Migration
An AI coding agent that can't see your migration history will happily rewrite a schema change that already ran. Here is the fix.
Steve Jefferson
Sep 15, 2026
How to Prompt AI to Write Unit Tests That Catch Bugs
AI-generated unit tests often pass without testing anything real. The fix is stating the requirement before the AI ever sees the code.
Steve Jefferson
Sep 15, 2026
How to Plan Delivery Routes With AI in a Small Business
A chat model cannot order twenty stops reliably, but it is very good at the messy constraint gathering around the route. Which half to give to which tool.
Steve Jefferson
Sep 15, 2026
How to Get AI to Edit a Document, Not Rewrite It
Ask for a fix to one sentence and you get a different document. Constrain the output format instead of asking for restraint, and the edit stays where you put it.
Cecilia Iona
Sep 15, 2026
Stop Your AI Coding Agent Swallowing Errors
Agents hide exceptions because a silenced error turns a red test suite green. A grep pass that finds them, and the instruction wording that stops it at the source.
Steve Jefferson
Sep 15, 2026
How to Design Empty States in an AI-Built App
AI builders preview against seeded demo data, so the screen a real user sees first is the one nobody looked at. The four empty states, and how to get a builder to write them.
Steve Jefferson
Sep 14, 2026
How to Prompt AI to Write an Incident Update
The hard part is publishing something useful at minute twelve, before you know the cause. Here is the prompt constraint that stops a model guessing.
Steve Jefferson
Sep 14, 2026
Two People Editing the Same Record: How to Fix It
The second save wins and the first person's work disappears with no error. The most common data-loss bug in AI-built internal tools, and how to close it.
Steve Jefferson
Sep 14, 2026
How to Prompt AI to Write a Changelog Entry From a PR
A reusable prompt template for turning a diff or PR description into a clean, user-facing changelog entry, with tone guidance and a full before/after example.
Steve Jefferson
Sep 13, 2026
How to Get an AI Coding Agent to Explain Its Plan First
Most agents guess and start editing. This instruction pattern makes an AI coding agent explain its plan, name the files it will touch, and ask one clarifying question before code changes.
Steve Jefferson
Sep 13, 2026
Stop an AI Coding Agent From Reformatting Whole Files
An AI coding agent asked to fix one bug can return a diff that touches the whole file. Here is the scoping instruction, and a before/after diff, that keeps it to just the lines that changed.
Steve Jefferson
Sep 13, 2026
Make AI Show Which Part of a Document It Used
Require a verbatim quote next to every claim, then check it with a string search. Verification becomes a control-F instead of a reread.
Steve Jefferson
Sep 13, 2026
Make an AI Coding Agent Reproduce a Bug First
A test that runs red today is the only thing separating a real fix from a plausible edit. Plus the revert check nobody does.
Steve Jefferson
Sep 13, 2026
How to Use AI to Build a Decision Matrix
A full worked example of prompting AI to build a weighted decision matrix, plus the specific way models rig their own weights and how to catch it.
Steve Jefferson
Sep 12, 2026
Restrict an AI Coding Agent's File System Access
A practical, tested setup for limiting where an AI coding agent can read and write: scoped directories, read-only mounts, ephemeral containers, git worktrees, and a real escape test.
Steve Jefferson
Sep 12, 2026
Why an AI Coding Agent Reads So Many Files Before Editing
An AI coding agent greps and reads broadly to confirm a change is safe before it edits anything. Here is the real mechanism behind that search, and how to limit what it explores.
Steve Jefferson
Sep 12, 2026
How to Prompt AI for a Complete List, Not a Sample
Ask AI to list everything and it quietly stops at eight of nineteen. Count first, chunk the input, and verify adversarially to get the full set.
Steve Jefferson
Sep 12, 2026
Using an AI Coding Agent on a Repo You Don't Own
Working in a client, employer or open source repo changes the rules for AI coding agents. Permission, data exposure, fencing and owning the diff.
Steve Jefferson
Sep 11, 2026
How to Prompt AI to Write a Rejection Email
Rejection emails fail by being vague or reckless. Set the disclosure level first, then constrain the model. Template, worked example, and what never to automate.
Steve Jefferson
Sep 11, 2026
How to Prompt AI for a Confidence Score Worth Using
Rate your confidence out of 10 gives you a meaningless number. Evidence-anchored bands, a worked contract example, and a 20-minute calibration test.
Steve Jefferson
Sep 11, 2026
How to Prompt AI to Argue Against Your Business Idea
A vague be critical prompt gets you agreeable filler. A structured one, with an assigned role and four forced objection axes, gets you real pushback on your business idea.
Steve Jefferson
Sep 11, 2026
How to Use AI to Migrate a Legacy Codebase
Migration means moving a codebase to a new language, framework, or platform, not cleaning it up in place. Here is a checklist for doing it with an AI coding agent without losing undocumented business logic.
Steve Jefferson
Sep 10, 2026
How to Use AI to Handle a Seasonal Hiring Spike
Seasonal hiring fails on timing, not on effort. You need eight people for eleven weeks, you start looking four weeks out, and you end up hiring whoever is still available in week two of the rush. The work that would have prevented that, writing the ads, screening the applications, building a trai...
Steve Jefferson
Sep 10, 2026
How to Add a Cookie Consent Banner to an AI-Built App
Ask an AI app builder for a cookie consent banner and you will get one in about ten seconds. It will look right. It will have Accept and Reject buttons, a tidy explanation, and a preference saved to local storage.
Steve Jefferson
Sep 10, 2026
Did Your AI Coding Agent Actually Run the Tests?
"All 47 tests pass." Sometimes that sentence means the agent ran your suite and read the output. Sometimes it means the agent generated a plausible sentence about a suite it never invoked. You cannot tell the two apart by reading the transcript, because a fabricated test summary and a real one ar...
Steve Jefferson
Sep 10, 2026
How to Prompt AI to Summarize a PDF Accurately
A confident AI summary of a long PDF can still be wrong, and reads the same either way. Force page citations to catch it before you trust the output.
Steve Jefferson
Sep 9, 2026
AI Tools for Freelance Translators: What Actually Helps
AI speeds up first drafts, terminology checks, and client admin for translators. Legal, medical, and nuance-driven work still needs full human translation.
Steve Jefferson
Sep 9, 2026
AI Tools for Wedding Photographers: What to Automate
AI genuinely speeds up culling and baseline editing for wedding photographers. Album design and hero-shot selection still need your judgment. Here is the split.
Steve Jefferson
Sep 9, 2026
How to Use AI to Write a Regex You Can Trust
AI writes a working regex fast, but hides which edge cases it silently skipped. Verify any pattern with this three-step process before it ships.
Steve Jefferson
Sep 9, 2026
How to Clean Up a Customer List With AI
Clean up my customer list is three different jobs wearing one name, and only two of them should ever be handed to a model.
Steve Jefferson
Sep 9, 2026
How to Build a Discord Bot With AI
An AI agent writes the interesting parts of a Discord bot correctly on the first try. What it gets wrong is Discord's platform rules.
Steve Jefferson
Sep 9, 2026
Give an AI Coding Agent a Fast Feedback Loop
An agent working in a repository where the checks take eleven minutes is not a slow agent. It is an agent that gets eleven minutes of blindness after every edit.
Carlo Zuercher
Sep 8, 2026
Prompting an AI Voice Agent Is Not Like Text
Text prompts break when read aloud. Here is a rewrite pattern for voice agents, with a real before-and-after system prompt example.
Steve Jefferson
Sep 8, 2026
How to Use XML Tags to Structure AI Prompts
XML tags turn a rambling prompt into labeled sections a model can parse reliably. See a real before-and-after rewrite and know when tagging actually helps.
Steve Jefferson
Sep 8, 2026
How to Prompt AI to Build a Staff Training Plan
Ask for a staff training plan and you will get a four-week curriculum with a week on culture, a week on tools, a week on process, and a week of shadowing. It looks professional. It is the same plan...
Steve Jefferson
Sep 8, 2026
How to Use AI to Write a Grant Application
Grant applications are graded against a published rubric by an assessor working through a stack of them. That single fact should shape how you use AI here. The parts of your application that are sc...
Steve Jefferson
Sep 8, 2026
How to Prompt AI to Explain Code Line by Line
A lazy "explain this code" prompt gets vague filler. A structured one forces the model to explain intent per block, flag non-obvious tricks, and admit what it is unsure about.
Steve Jefferson
Sep 8, 2026
How to Get an AI Coding Agent to Write Tests First
Most agents write a test and its implementation in the same breath, so the test never fails for real. Here is the exact instruction that forces a genuine red-green-refactor cycle.
Steve Jefferson
Sep 7, 2026
How to Prompt AI for a Technical Spec Document
A six-step prompt sequence that turns a rough feature idea into a real technical spec, with a worked example prompt and the failure mode of asking for it all in one shot.
Steve Jefferson
Sep 7, 2026
How to Stop AI From Hedging Every Answer
It depends. Results may vary. Consult a professional. When every answer arrives wrapped in caveats, the prompt is usually asking for an opinion without giving the model anything to have an opinion about.
Steve Jefferson
Sep 7, 2026
AI Code Comments That Lie About the Code
An agent that edits a function and leaves the docstring untouched has produced something worse than no documentation. Here is why it happens, the four patterns to watch for, and how to make review catch them.
Steve Jefferson
Sep 7, 2026
How to Verify an AI Translation You Cannot Read
You can ship a Spanish landing page without speaking Spanish, but not by trusting the model and hoping. Here is a verification loop that catches meaning errors, register mistakes, and silently dropped content before a customer finds them.
Steve Jefferson
Sep 7, 2026
How to Prompt AI to Negotiate a Job Offer
AI can draft your counter-offer email and negotiation talking points, but it needs your real numbers and reasoning to work, and it should never invent leverage you don't have.
Manuele Estivo
Sep 6, 2026
How to Prompt AI to Fix a Flaky Test
A flaky test that passes sometimes and fails other times needs a different prompting approach than a broken one, or an AI agent will just paper over the real bug with a retry, a sleep, or a loosened assertion.
Steve Jefferson
Sep 6, 2026
Getting an AI Coding Agent to Write Accessible Code
Interactive divs, unlabelled inputs, colour-only state, and dialogs that lose focus. Four defects, four rules, and the CI checks that make them stick.
Carlo Zuercher
Sep 6, 2026
How to Prompt AI to Write a Customer Survey
Models write surveys that quietly assume the answer you want. Here is the two-pass method that catches it, plus the scale rules nothing applies on its own.
Steve Jefferson
Sep 6, 2026
How to Use AI to Categorize Business Expenses
A model reading bank lines gets four in five right on the first pass. Here is how to measure that, raise it, and find the ones it got confidently wrong.
Steve Jefferson
Sep 6, 2026
How to Build an Inventory App With AI
Ask an AI builder for an inventory app and you get a quantity column that drifts within weeks. Here is the ledger schema that does not, and the prompts for it.
Steve Jefferson
Sep 5, 2026
How to Prompt AI to Write a User Manual
A practical prompt template for getting AI to write a user manual people actually follow, split by end user and admin audience, with a before/after rewrite of a vague instruction.
Steve Jefferson
Sep 5, 2026
How to Prompt AI to Write a Database Seed Script
A practical prompt template for getting an AI coding agent to write a seed script that respects foreign keys, generates realistic data, and survives a second run.
Steve Jefferson
Sep 5, 2026
Why an AI Coding Agent Keeps Rewriting Your Tests
Four concrete reasons an AI coding agent rewrites your tests instead of fixing the bug, and the exact prompt and workflow fix for each one.
Carlo Zuercher
Sep 5, 2026
How to Prompt AI to Grade Work Against a Rubric
Ask for a score out of 10 and everything comes back a 7 or an 8. The fix is anchoring each band with a concrete example and demanding evidence before the number.
Steve Jefferson
Sep 5, 2026
Onboarding a Developer to an AI-Written Codebase
The context that normally lives in people's heads never entered anyone's head. Nobody remembers why the retry logic sits where it does, because nobody decided it.
Steve Jefferson
Sep 5, 2026
How to Prompt AI to Redact a Document Properly
Remove all personal information produces a document that looks redacted and is not. The identifiers that survive are the ones that only identify in combination.
Steve Jefferson
Sep 5, 2026
What Is Prompt Chaining (And When to Use It)
A single messy task, run as one prompt versus a three-step chain, shows exactly where the one-shot version quietly loses items the chain catches every time.
Steve Jefferson
Sep 4, 2026
How to Get AI to Hit a Specific Word Count
Asking for exactly 500 words gets you somewhere between 380 and 720. The fix is not asking more firmly, because no amount of instruction installs a counter.
Steve Jefferson
Sep 4, 2026
How to Give an AI Coding Agent Your API Docs
Pasting a documentation page into the chat window works once and then rots. A committed spec, a pointer in the instructions file, and a checkable contract survive.
Steve Jefferson
Sep 3, 2026
How to Prompt AI to Avoid Making Assumptions
A prompt that makes AI ask clarifying questions stops it mid-task. This one lets it keep working, but forces every unstated assumption into plain view as it answers.
Steve Jefferson
Sep 3, 2026
How to Fix N+1 Queries With an AI Coding Agent
A step-by-step guide to diagnosing and fixing N+1 query problems with an AI coding agent, including the exact broken and fixed code and the prompt that gets agents to find the loop instead of guessing.
Steve Jefferson
Sep 3, 2026
AI Coding Agents in a Language They Barely Know
An agent that is excellent in Python can be quietly terrible in Elixir or COBOL. The failure is not random: it is idioms, standard library recall, and invented APIs.
Carlo Zuercher
Sep 3, 2026
How to Prompt AI to Find What Is Missing
Models score what is in front of them. Absence has no tokens, so it has no weight. The fix is to stop asking what is missing and start asking about a checklist.
Steve Jefferson
Sep 3, 2026
A Dev Container for Your AI Coding Agent
Giving an agent terminal access on your laptop is a bad trade. A dev container gives it a real shell, a real toolchain, and a blast radius you chose in advance.
Steve Jefferson
Sep 2, 2026
How to Schedule Staff Shifts With AI
AI can draft a constraint-satisfying weekly schedule in a minute, but labor law and swap requests still need a human review step. Here is the workflow.
Steve Jefferson
Sep 2, 2026
How to Prompt AI to Write a Postmortem
The reason most AI-written postmortems are useless is that they are asked for too early.
Steve Jefferson
Sep 2, 2026
Letting an AI Coding Agent Touch Your Auth Code
Yes, you can let an AI coding agent touch your auth code, and the honest answer is that most teams already do. The question worth asking is not whether to allow it but what has to be true before the change merges.
Steve Jefferson
Sep 2, 2026
Give an AI Coding Agent Your Error Monitoring Data
Giving an AI coding agent your error monitoring data turns a vague bug report into a specific one.
Steve Jefferson
Sep 2, 2026
Why an AI Coding Agent's Fix Fails in CI
When an AI coding agent's fix passes locally and fails in CI, the agent is almost never wrong about the code. It is wrong about the environment.
Steve Jefferson
Sep 2, 2026
How to Prompt AI to Write an Investor Update
A prompt scaffold for AI-drafted investor updates that bans vague filler, demands real numbers, states bad news plainly, and forces a genuine asks section.
Steve Jefferson
Sep 1, 2026
How to Prompt AI to Write a Landing Page
A reusable prompt scaffold for AI landing page copy covering the hero claim, proof, objection handling, and final CTA, plus a before-and-after example of a generic headline versus a specific one.
Manuele Estivo
Sep 1, 2026
How to Prompt AI to Fix a Failing Test
A copy-paste prompt scaffold that forces an AI agent to state the root cause of a failing test before it patches anything, plus a worked example of a good fix versus a faked one.
Steve Jefferson
Sep 1, 2026
How to Prompt an AI Agent That Browses the Web
Browsing turns a prompt into a research process, and a research process needs a stopping rule and a definition of an acceptable source.
Steve Jefferson
Sep 1, 2026
Give an AI Coding Agent Your Design System
Agents follow what they can read and what punishes them. Three files do that job, and a brand guideline PDF does neither.
Steve Jefferson
Sep 1, 2026
How to Build a Directory Site With AI
A working directory build: the schema, the seeding plan that decides whether it lives, and the four failures that kill directory sites.
Steve Jefferson
Aug 31, 2026
How to Review an AI Agent's Git Diff Before Merging
A passing test suite and a solid plan don't guarantee a safe merge. Here's the ordered checklist for reviewing an AI coding agent's diff before you accept it.
Carlo Zuercher
Aug 31, 2026
How to Prompt AI to Write a Product Description
Generic AI prompts produce generic product descriptions. Here's how to feed the model specifics, sensory detail, and platform norms so ecommerce listings actually sell.
Steve Jefferson
Aug 31, 2026
How to Prompt AI to Write Alt Text
One describe-the-image prompt produces alt text that fails accessibility review. Branch the prompt on the image's function instead.
Steve Jefferson
Aug 31, 2026
How to Prompt AI to Name a Product
Asking for fifty name ideas gets you fifty variations of the same name. A three-pass structure fixes the spread problem and screens the results.
Steve Jefferson
Aug 31, 2026
Stop AI Agents Breaking Your API Contract
An agent renamed one JSON field and every mobile client broke. Here are the five contract breaks agents make most, and how to catch them before merge.
Steve Jefferson
Aug 31, 2026
How to Tell If Your AI Agent Read a File
Agents answer confidently about files they never opened. Four cheap probes tell you the difference between a real read and a plausible guess.
Steve Jefferson
Aug 30, 2026
How to Use AI to Write an Employee Handbook
AI can draft your handbook's tone, structure, and boilerplate policies fast. Leave law, termination language, and discrimination wording still need a real employment lawyer.
Steve Jefferson
Aug 30, 2026
How to Write a Business Plan With AI
A section-by-section guide to writing a business plan with AI: the executive summary, market analysis, product description, financial projections, and operations, each with a usable prompt and what you must verify yourself.
Steve Jefferson
Aug 30, 2026
How to Prompt AI When You Don't Know the Right Words
When you cannot name what you want, the instinct is to search for the term first. Splitting it into two turns gets you the vocabulary and the answer, and catches the case where you meant something adjacent.
Steve Jefferson
Aug 30, 2026
Get an AI Coding Agent to Use Your Internal Library
Agents pattern-match your internal library to the nearest public one and invent functions accordingly. Four fixes, in the order worth doing them, starting with a twenty-minute one.
Steve Jefferson
Aug 29, 2026
How to Prompt AI to Write a LinkedIn Post
Most AI LinkedIn posts sound generic because the prompt gave the model a topic, not a real detail. Here is a prompt structure, with a worked before-and-after, that fixes it.
Steve Jefferson
Aug 29, 2026
How to Prompt AI to Turn Meeting Notes Into Action Items
A prompt template for turning messy meeting notes into a clean list of action items, each with an owner, a deadline, and a priority, and honest flags where the notes leave a gap.
Steve Jefferson
Aug 29, 2026
How to Add a Waitlist Page to an AI-Built App
A concrete walkthrough of the schema, prompt sequence, and validation rules for adding a waitlist page to an AI-built app, including position calculation and a referral unlock mechanic.
Steve Jefferson
Aug 29, 2026
How to Prompt AI to Write an Apology Email
The default output is polished and hollow. Banning four specific constructions and forcing the cause into the first line is what turns it into something usable.
Steve Jefferson
Aug 29, 2026
How to Prompt AI to Write a Runbook
Ask for a runbook and you get a template. The working method is extraction first: make the model interview you, then force it to mark gaps instead of filling them.
Steve Jefferson
Aug 29, 2026
How to Add Voice Input to an AI-Built App
Capturing microphone audio takes twenty lines. The batch-versus-streaming decision, the permission states, and the wrong-transcript problem are the real work.
Steve Jefferson
Aug 28, 2026
How to Prompt AI to Generate Edge Cases for Testing
A copyable prompt template that forces AI to enumerate real edge cases, nulls, boundaries, concurrency, unicode, and timezones, plus a worked example against a discount code validator.
Steve Jefferson
Aug 28, 2026
How to Get an AI Coding Agent to Explain Legacy Code
Run an AI coding agent through four comprehension prompts before refactoring a legacy codebase: trace real requests, map the data model, and surface undocumented business rules.
Steve Jefferson
Aug 28, 2026
Why AI Coding Agents Leave Debug Code Behind
AI coding agents debug by inserting print statements and logging to check their own work, then rarely clean them up once a task looks done. Here's why, and a grep pattern plus an AGENTS.md instruction that catches it before it ships.
Carlo Zuercher
Aug 28, 2026
How to Add Backups to an AI-Built App
Platform snapshots cover the disaster you will probably never have and miss the ones you will. Storage bucket sync, row-level recovery with the partial index detail agents get wrong, and a twenty minute restore drill whose output is a written runbook.
Steve Jefferson
Aug 28, 2026
How to Prompt AI to Write a Test Plan
Ask AI for a test plan and you get the happy path. A six-group prompt scaffold that forces boundary, dependency failure, permission, concurrency and leftover-state cases, worked through a team invite feature, plus the review pass that catches confident nonsense.
Steve Jefferson
Aug 28, 2026
Find Which AI Change Broke Your Build
An agent handed you one commit across thirty-one files and the build is red. How to split that commit into bisectable slices, run git bisect properly against agent history, read the culprit, and stop producing unbisectable commits in the first place.
Steve Jefferson
Aug 27, 2026
How to Prompt AI for Multiple Options, Not One
Asking AI for "a few options" usually produces one real answer and two hedged near-duplicates. A decision matrix prompt, with named criteria, a fixed option count, and a ban on picking a winner, fixes that.
Steve Jefferson
Aug 27, 2026
Why Your AI Coding Agent Keeps Ignoring Instructions
When an AI coding agent seems to ignore what you told it, the cause is almost always one of four specific failures, not stubbornness. Here's how to tell them apart and rewrite instructions that actually stick.
Steve Jefferson
Aug 27, 2026
How to Prompt AI to Change Reading Level
"Rewrite this at a 6th grade level" produces something shorter that has quietly dropped the condition your legal team put there.
Steve Jefferson
Aug 27, 2026
AI Coding Agent Hardcoding Values? How to Stop It
It passed the test by writing the answer into the function. Technically correct, and the reason your staging URL is now in three files.
Steve Jefferson
Aug 26, 2026
How to Prompt AI to Explain Its Reasoning First
A copy-paste prompt template that forces AI to lay out its assumptions and reasoning before answering, so you catch a wrong guess before you act on it.
Steve Jefferson
Aug 26, 2026
How to Prompt AI to Follow Your Style Guide Every Time
A reusable style card replaces the habit of re-pasting three example paragraphs into every prompt, and holds a consistent AI brand voice without the token cost or the drift.
Steve Jefferson
Aug 26, 2026
How to Prompt AI to Design a Database Schema
Give the model your queries and your record lifecycle, not a list of entities. The worked prompt, the four mistakes AI reliably makes, and how to review output.
Steve Jefferson
Aug 26, 2026
AI Coding Agent on a Codebase With No Tests
No test suite means no safety net for an agent. Pin current behaviour first with characterization tests, then let it work. The staged prompts and the rules.
Steve Jefferson
Aug 25, 2026
Stop an AI Coding Agent From Reinventing Existing Code
Your AI coding agent isn't lazy, it just can't see the helper function you already wrote. Here is the mechanism, a duplicated-helper example, and the AGENTS.md fix.
Steve Jefferson
Aug 25, 2026
How to Prompt AI to Write a Hiring Rubric
See how to prompt AI to write a hiring rubric with role-specific criteria, 1-5 scoring anchors, and a blind pass that reduces bias in screening.
Steve Jefferson
Aug 25, 2026
How to Prompt AI to Play Devil's Advocate
A prompt template and worked example for getting AI to argue against your plan, plus how it differs from asking AI to check its own work.
Steve Jefferson
Aug 25, 2026
How to Prompt AI to Fill a Template Correctly
Hand a model a contract template and ask it to fill the blanks, and it will helpfully improve your wording, merge two sections and quietly delete a clause. Here is how to stop that.
Steve Jefferson
Aug 25, 2026
How to Stop an AI Coding Agent Over-Engineering
Ask for a function and you get a factory, an interface, a config file and a plugin system. The cause is not the model being clever, it is your request being under-specified in a very particular way.
Steve Jefferson
Aug 24, 2026
How to Keep an AI Coding Agent Inside One Feature Branch
A practical setup for containing an AI coding agent to a single feature branch, using git worktree, server-side branch protection, and a pre-commit hook that rejects the wrong branch name.
Steve Jefferson
Aug 24, 2026
How to Add a Notification Center to an AI-Built App
A notification center is a bell icon and dropdown feed of read and unread events stored in your database, distinct from push notifications and email. This guide covers the data model, read state handling, and the polling vs. realtime delivery tradeoff.
Steve Jefferson
Aug 24, 2026
How to Prompt AI to Write a Regular Expression
AI is great at regex if you prompt it with real examples and make it show test cases. Here is a template and how to verify the pattern before you ship it.
Steve Jefferson
Aug 24, 2026
How to Add a Status Page to an AI-Built App
A status page answers is it down for everyone or just me. For an AI app the twist is monitoring outages you do not control. Here is how to set one up.
Steve Jefferson
Aug 24, 2026
Move an AI-Built App to a Custom Domain
Pointing a domain at an AI-built app is mostly DNS. The part that bites is the four things that break when the URL changes: hardcoded links, OAuth, CORS, and emails.
Steve Jefferson
Aug 23, 2026
How to Stop an AI Coding Agent From Editing Unrelated Files
A broad instruction like fix the bug lets an AI coding agent wander into files you never mentioned. Here is the real mechanism, a worked example, and four checkable fixes.
Steve Jefferson
Aug 23, 2026
How to Catch AI Coding Agent Security Vulnerabilities
AI coding agents write insecure code more often than most teams expect. Here is how to catch the vulnerabilities before they merge, with a practical checklist and a pasteable review prompt.
Steve Jefferson
Aug 23, 2026
What Is Top-p and Top-k in AI Text Generation
Top-p and top-k both trim which words an AI model can pick next, but one uses a fixed count and the other a moving probability threshold. Here is the practical difference.
Steve Jefferson
Aug 23, 2026
How to Stop AI From Making Up Citations
A verification-first prompt template that separates an AI answer from its claimed sources, so you can check each one before trusting it, plus why RAG only shrinks the fabrication problem.
Steve Jefferson
Aug 23, 2026
Instructions Before or After Your Data in a Prompt?
For anything longer than a page, the document goes at the top and the instruction goes at the bottom. There is documented evidence for it, and a caching argument that makes it free money.
Steve Jefferson
Aug 23, 2026
Why Your Prompt Works in Chat but Not in the API
The chat product is an application built on top of the model. When you call the API you get the model without the application, and everything the application was quietly doing stops.
Steve Jefferson
Aug 23, 2026
How to Prompt AI for a Sales Call Follow-Up Email
A one-line prompt produces a generic sales follow-up. This guide shows the structured call-notes prompt that produces one worth sending, with a bad-output-versus-good-output comparison.
Steve Jefferson
Aug 22, 2026
How to Get an AI Coding Agent to Write Smaller PRs
Open-ended prompts let AI coding agents refactor whatever they want. Scope-boundary prompts, diff budgets, and a task-splitting checklist keep their pull requests small and reviewable.
Steve Jefferson
Aug 22, 2026
Why Your AI Coding Agent Keeps Suggesting Old Packages
AI coding agents keep suggesting packages that are already deprecated because their training data has a fixed cutoff. Here is why it happens and how to stop it with lockfiles and one explicit instruction.
Steve Jefferson
Aug 22, 2026
How to Hand Off an AI Conversation to a Human
Most chatbot handoffs fail on continuity, not on answers. The customer asks for a person, the transcript vanishes, and they conclude the bot was a wall.
Steve Jefferson
Aug 21, 2026
How to Prompt AI to Summarize Customer Feedback
A quote-anchored prompt template that forces AI to cite the exact source line behind every customer feedback theme, so it can't invent complaints or praise.
Steve Jefferson
Aug 21, 2026
Should You Let AI Agents Merge Their Own Pull Requests?
A risk-tier merge policy for AI coding agents: auto-merge docs and tests behind green CI, always require human review for schema, auth, payments, and public API changes, with the branch-protection rules to enforce it.
Steve Jefferson
Aug 21, 2026
How to Handle Time Zones in an AI-Built App
Handling time zones in an AI-built app comes down to four words: store UTC, render local. Almost every time-zone bug in a generated codebase is a violation of one half of it, and there are three violations that show up over and over.
Steve Jefferson
Aug 21, 2026
Should an AI Coding Agent Upgrade Your Dependencies?
Should an AI coding agent upgrade your dependencies? Yes for patch versions, usually yes for minors with a real test suite, and no for majors, at least not as a dependency task. That split is not arbitrary.
Steve Jefferson
Aug 21, 2026
How to Prompt AI to Compare Two Documents
If you want to prompt AI to compare two documents, paste two contracts in and ask what the differences are, and you will get a fluent paragraph about each one followed by a short list of things that changed.
Steve Jefferson
Aug 21, 2026
How to Prompt AI to Write a Press Release
Most AI press release prompts just ask for facts and hope. Here is the actual structural contract to feed the model, plus a technique for fixing fake-sounding executive quotes.
Steve Jefferson
Aug 21, 2026
How to Prompt AI to Translate Text and Keep the Tone
Naive translation prompts get the words right and the tone wrong. Here is a two-pass prompting method, with a before/after example, that keeps a casual message casual and a formal one formal.
Steve Jefferson
Aug 20, 2026
How to Prompt AI to Triage Support Tickets
Triage is high volume, low creativity and every decision has a right answer somebody already knows. It is also asymmetric: misrouting a billing question costs twenty minutes, misrouting an outage costs a customer. Here is the prompt structure that respects that, and the fifty-ticket test that proves it works.
Steve Jefferson
Aug 19, 2026
How to Prompt AI to Review Your Code Before You Ship It
A copy-pasteable review prompt covering security, edge cases, naming, and missing tests, plus a worked before/after example on real code.
Steve Jefferson
Aug 19, 2026
AI Tools for Etsy Sellers: How to Set Up Your Shop
A step-by-step setup order for AI tools in your Etsy shop this week: photo touch-ups, listing descriptions, customer message templates, and pricing research, plus what Etsy's policy actually allows.
Steve Jefferson
Aug 19, 2026
How to Add an Audit Log to an AI-Built App
The request always arrives the same way: who changed this, and when. Here is the table, the write path, and the four decisions that separate a useful log from noise.
Steve Jefferson
Aug 19, 2026
How to Make AI Say I Don't Know Instead of Guessing
Models guess because guessing is the only move you left them. Four changes that make abstention a valid answer, and the eval that proves it worked.
Steve Jefferson
Aug 18, 2026
How to Prompt AI to Draft Meeting Minutes
Most AI meeting minutes read like a book report: pleasant, accurate, and useless. Here's the prompt structure that forces decisions and owners out of a messy transcript instead.
Steve Jefferson
Aug 18, 2026
How to Prompt AI to Write User Stories
Most AI-written user stories are generic filler with no real acceptance criteria. Here's the exact prompt structure that turns a one-line feature request into three scoped, testable stories.
Steve Jefferson
Aug 18, 2026
How to Add Caching to an AI-Built App
Most AI-built apps get slow for one specific reason, and it's rarely the reason you'd guess. Here's how to find the actual bottleneck before you add any cache at all.
Steve Jefferson
Aug 18, 2026
How to Add Dark Mode to an AI-Built App
A working dark mode needs more than a black background class. Here's the CSS variable structure, the persistence logic, and the exact prompt that stops an AI agent from missing half your components.
Steve Jefferson
Aug 18, 2026
How to Add Feature Flags to an AI-Built App
A feature flag doesn't require a new service or SDK. It requires one column your AI coding agent already knows how to build, checked before the feature runs.
Steve Jefferson
Aug 18, 2026
How to Prompt AI to Analyze a Spreadsheet
Bad answers from a spreadsheet are usually a sheet problem, not a prompt problem. A ten-minute pre-flight, a four-sentence data dictionary, and the habit of agreeing the method before asking for the number.
Steve Jefferson
Aug 18, 2026
How to Prompt AI to Write a SQL Query
Schema, dialect, and one sentence about what a row means. That is the prompt. The rest of this is the three ways generated SQL is silently wrong, and the fifteen-second check for each.
Steve Jefferson
Aug 18, 2026
How to Name Variables So AI Coding Agents Understand Code
Vague names like data, temp, and handleThing make AI coding agents guess and misfire. See before/after code examples and a checklist for names that steer agents correctly.
Steve Jefferson
Aug 17, 2026
How to Prompt AI to Write Release Notes
A worked before/after example and a reusable prompt template for turning raw commits into release notes users actually read.
Steve Jefferson
Aug 17, 2026
How to Prompt AI With a Screenshot
A screenshot answers "what does it look like" and nothing else. Here is what the model can and cannot see, and the caption structure that fixes most bad results.
Steve Jefferson
Aug 16, 2026
Give an AI Coding Agent Read-Only Production Access
A worked guide to creating a scoped, time-boxed, write-incapable Postgres credential so an AI agent can debug production incidents without any chance of changing data.
Steve Jefferson
Aug 16, 2026
How to Prompt AI to Write a Job Description
First ninety days, what makes the role hard, and the honest band. Without those three you get a description of a job category, not your job.
Steve Jefferson
Aug 16, 2026
How to Add a Referral Program to an AI-Built App
A referral code and a counter is a demo. The program is the five cases where money leaves your account and should not.
Steve Jefferson
Aug 16, 2026
How to Write a Pull Request Description With AI
Feeding the model your diff produces a longer version of what the reviewer can already read. The useful input is everything the diff cannot contain.
Steve Jefferson
Aug 15, 2026
How to Add an Onboarding Flow to an AI-Built App
A checklist for the three real reasons new users quit an AI-built app: empty states, permission requests asked too soon, and a slow path to the first successful action.
Steve Jefferson
Aug 15, 2026
How to Add Social Login to an AI-Built App
A practical walkthrough of adding Google, GitHub, or Apple sign-in to an app built with an AI coding agent, including which providers to pick and what breaks if you add it after users already exist.
Steve Jefferson
Aug 15, 2026
How to Give an AI Coding Agent Safe Staging Access
A concrete permission model for letting an AI coding agent touch a staging environment: a scoped database, staging-only keys, network allowlisting, audit logging, and a rollback plan you write before granting access.
Steve Jefferson
Aug 15, 2026
How to Prompt AI to Estimate a Project Timeline
A model will happily produce a project timeline from a one-line description, and that timeline will be useless. The prompt that produces a usable estimate does three things the naive version does not: it forces the model to decompose the work before assigning any numbers, it makes it state the...
Steve Jefferson
Aug 15, 2026
Stop AI Coding Agents Adding Dependencies You Did Not Pick
The fastest way to stop an AI coding agent adding dependencies is to make the lockfile a reviewed artifact and fail the build when it changes without approval. A single check that compares the lockfile against the last committed version, plus an allowlist of packages the agent may reach for,...
Steve Jefferson
Aug 15, 2026
Make an AI Coding Agent Follow Your Code Style
If an AI coding agent keeps writing code that does not match your codebase, the fix is almost never a better instruction. It is a check the agent cannot argue with. Put your style rules in a formatter and a linter, wire those into the command the agent runs after every edit, and the agent...
Steve Jefferson
Aug 15, 2026
How to Write Acceptance Criteria for an AI Coding Agent
A vague ticket lets an agent guess. Here is a real before/after rewrite that turns "make it work well" into acceptance criteria an agent can actually check.
Steve Jefferson
Aug 14, 2026
How to Prompt AI to Roleplay as a Customer for User Research
A worked persona prompt, a sample AI customer interview, and an honest breakdown of what synthetic feedback can and cannot replace.
Steve Jefferson
Aug 14, 2026
How to Prompt AI to Generate Realistic Test Data
Three worked prompt templates for generating realistic test data with AI: relational rows with constraints, deliberate edge cases, and PII-safe fake records, each with actual output.
Steve Jefferson
Aug 14, 2026
How to Tell If an AI Vendor Is GDPR Compliant
A practical checklist of the documents and clauses to request, DPA, sub-processor list, data residency, and training terms, before trusting an AI vendor's GDPR claims.
Steve Jefferson
Aug 14, 2026
When AI Coding Agents Rewrite Tests to Pass
The agent says the suite is green. It is, because it deleted the assertion. Here is how to catch that class of fix before it reaches your main branch.
Carlo Zuercher
Aug 14, 2026
How to Make an AI-Built App Accessible
Generated code looks fine and fails a screen reader instantly. Here is the short list of what breaks, why, and the prompts that stop it happening again.
Steve Jefferson
Aug 14, 2026
How to Migrate From One AI Model to Another
A step-by-step guide to migrating from one AI model to another without breaking your app: regression testing, output diffing, canary rollouts, and rollback plans.
Steve Jefferson
Aug 13, 2026
How to Set Permissions for AI Coding Agents
A three-tier permission model for AI coding agents on a team: read-only reviewer, sandbox builder, and deploy-authorized, with the real mechanisms that enforce each tier.
Steve Jefferson
Aug 13, 2026
What to Do If an AI Coding Agent Leaks a Secret
An AI coding agent committed a secret to your repo. Here is the exact order of operations: rotate the credential first, then clean git history, then lock the door.
Steve Jefferson
Aug 13, 2026
How to Prompt AI for a Competitive Analysis
A two-stage prompt pattern for competitive analysis: gather sourced facts first, then synthesize a positioning table, so AI stops inventing differentiators.
Steve Jefferson
Aug 13, 2026
How to Prompt AI to Write a Product Spec
Most AI-written product specs read well and say nothing useful. Here is the input structure and prompt sequence that gets a spec someone could actually build from.
Steve Jefferson
Aug 13, 2026
AI coding agent stuck in a loop? How to break it
Three loops account for nearly all of them: the test oscillation, the context-loss rewrite, and the phantom error chase. Each needs a different intervention.
Carlo Zuercher
Aug 13, 2026
How to prompt AI to extract data from a document
Extraction fails in one specific way: the model guesses instead of admitting a field is missing. Define the schema, force a not-found token, and verify the numbers.
Steve Jefferson
Aug 12, 2026
How to Estimate Tokens for an AI Task
A back-of-envelope method for estimating tokens before you run an AI task: convert words to tokens, apply an output multiplier by task type, then test the math against a small sample.
Steve Jefferson
Aug 12, 2026
How to Review an AI Agent Plan Before It Runs
Two plans describe the same work. Only one of them can be reviewed. The skill is noticing which you have been handed, and refusing to approve the other.
Carlo Zuercher
Aug 12, 2026
How to Add Background Jobs to an AI-Built App
A user clicks a button and the page hangs for eleven seconds. The pattern causing it is the one almost every AI-generated app starts with.
Steve Jefferson
Aug 12, 2026
How to Prompt AI to Summarize a Long Document
A summary that is 80% right is more dangerous than one that is obviously wrong. Three failure modes cause nearly all of it, and each has a different fix.
Steve Jefferson
Aug 12, 2026
How to Roll Back a Bad AI Coding Agent Change
A checkpoint-branch git workflow for undoing AI coding agent commits that touch dozens of files at once, using git reflog, worktrees, stash, and targeted reverts to recover safely.
Steve Jefferson
Aug 12, 2026
How to Debug a Prompt That Stopped Working
When a reliable prompt suddenly breaks, the wording is rarely the cause. Here is the diagnostic order to find what actually changed, and how to test each layer.
Steve Jefferson
Aug 11, 2026
How to Write Prompts That Work Across AI Models
Prompts do not port between models. Structure does. What survives a model change, what breaks, and how to find out in twenty minutes rather than in production.
Steve Jefferson
Aug 11, 2026
AI Coding Agent Database Migrations, Done Safely
An AI agent will write a migration that works on an empty table and locks a busy one for minutes. The context and constraints that produce migrations you can actually deploy.
Steve Jefferson
Aug 11, 2026
How to Run an AI Coding Agent in CI
Moving an AI coding agent from your laptop into continuous integration changes the threat model and the economics. A practical setup covering triggers, permissions, cost ceilings and review.
Steve Jefferson
Aug 11, 2026
How to Add Real-Time Chat to an AI-Built App
A decision framework for choosing websockets, a managed realtime service, or polling, plus the minimum messages, participants, and read-receipt schema to build human-to-human chat.
Steve Jefferson
Aug 11, 2026
How to Version Your Prompts as Your Product Changes
A minimal, tool-free system for tracking prompt changes over time: what to log, when to bump a version, and when to fork the prompt entirely.
Steve Jefferson
Aug 10, 2026
How to Handle Merge Conflicts With AI Coding Agents
AI agents cause merge conflicts in two specific ways: full-file rewrites and parallel agents on the same file. Here is exactly how to fix both.
Steve Jefferson
Aug 10, 2026
AI Tools for Small Law Firms and Solo Attorneys
A task-by-task breakdown of which legal work an AI tool can safely handle, and which decisions a solo attorney or small firm should never hand off.
Steve Jefferson
Aug 10, 2026
AI Tools for Dental Practices (By Workflow, Not Hype)
Which AI tools actually save a dental practice time, broken down by workflow, from recall reminders to insurance verification, and where automation should stop.
Steve Jefferson
Aug 10, 2026
How to Write a Bug Report for an AI Coding Agent
The difference between a two-line fix and a sprawling rewrite is usually four sentences you did not bother to write.
Steve Jefferson
Aug 10, 2026
AI Hallucinated a Package That Does Not Exist
A missing package is annoying. A package that exists only because an attacker registered the name your model invented is a supply chain compromise.
Steve Jefferson
Aug 10, 2026
Why Telling AI Not to Do Something Fails
Do not use bullet points. The model uses bullet points. This is not disobedience, it is how the instruction was processed.
Steve Jefferson
Aug 10, 2026
How to Prompt AI Without Leaking Sensitive Data
A practical guide to spotting sensitive data before it lands in an AI prompt, with redaction techniques, a consumer-vs-API breakdown, and a pre-send checklist.
Steve Jefferson
Aug 10, 2026
How to Use AI to Write Documentation for Your Codebase
A real workflow for generating README and API docs with AI by pointing it at the whole repo, plus a concrete practice for catching drift before it wastes someone's afternoon.
Steve Jefferson
Aug 9, 2026
How to Add Push Notifications to an AI-Built App
A real technical walkthrough for adding push notifications to an app you built with AI, covering web push with VAPID keys and service workers, native push tradeoffs, and the permission prompt UX that decides whether anyone opts in.
Steve Jefferson
Aug 9, 2026
AI Tools for Hair Salons and Barbershops
A practical look at which AI tools actually help salons and barbershops with booking, no-shows, reminders, reviews, and rebooking, and where AI still can't replace a human at the front desk.
Cecilia Iona
Aug 9, 2026
How to Get AI to Ask Clarifying Questions First
Most AI models guess instead of asking when your prompt is ambiguous, then hand back a confident wrong answer. Here are the exact prompt patterns that get a model to stop and ask first.
Steve Jefferson
Aug 9, 2026
How to add analytics to an AI-built app
The AI will happily wire up a dashboard full of numbers nobody uses. Four events, placed by hand, will tell you more than any of it.
Steve Jefferson
Aug 8, 2026
What to Do When Your AI-Built App Breaks in Production
When your AI-built app breaks in production, don't start editing code. Run this triage order first: deploy status, environment variables, reproduction, the real runtime error, then a properly framed handoff to your AI coding agent.
Steve Jefferson
Aug 8, 2026
How to Give an AI Coding Agent Safe Terminal Access
A confirm dialog with a shell command on it is not a great place to make security decisions on the fly. Here is a concrete tiering system, plus the setup steps and sandboxing options, for giving an AI coding agent terminal access without gambling on your machine.
Steve Jefferson
Aug 8, 2026
How to Write AI Image Generation Prompts That Work
Most AI image prompts leave five decisions to the model and get a generic result back. Here is the exact structure, subject, composition, lighting, style, negative constraints, with two before/after rewrites showing why it works.
Steve Jefferson
Aug 8, 2026
How to Stop AI From Being Too Agreeable
A model that praises every idea you bring it is not being polite, it is being useless. The fix is structural: never let it know which answer you are hoping for.
Steve Jefferson
Aug 8, 2026
How to Add Multi-Language Support to an AI-Built App
The hard part of translating an AI-built app is not translation. It is that the generator wrote your text into the components, glued sentences together, and formatted dates inline.
Steve Jefferson
Aug 8, 2026
How to Write an AGENTS.md File Agents Actually Follow
AGENTS.md is the closest thing coding agents have to a shared configuration standard. Most of them are written as documentation, which is why most of them get ignored.
Steve Jefferson
Aug 8, 2026
How to Keep an AI Coding Agent From Losing Context
Large codebases overwhelm an AI agent's context window fast. These are the structural tactics, briefing files, task scoping, search-first workflows, and running notes, that keep one agent coherent through a long session.
Carlo Zuercher
Aug 7, 2026
How to Prevent Prompt Injection Attacks in Your AI App
Prompt injection can't be filtered away with a single regex. Here is the builder-facing defense checklist, grounded in OWASP GenAI and Anthropic guidance, for locking down what your AI app will actually do with untrusted text.
Carlo Zuercher
Aug 7, 2026
How to Choose a Database for an AI-Built App
A practical decision framework for picking between Postgres, a document database, and a vector database when you're building an app with AI tools and don't have a DBA on staff.
Steve Jefferson
Aug 7, 2026
How to Chain Prompts Together for Better Results
Prompt chaining splits one complex task into a sequence of smaller prompts, each feeding the next. Here's a real 4-step chain, worked prompt by prompt.
Steve Jefferson
Aug 7, 2026
AI App Maintenance: What Breaks After Launch
Nobody writes about the month after launch. Here is what actually breaks in an app built with AI, roughly when, and the routine that keeps it boring.
Steve Jefferson
Aug 7, 2026
Why Is My AI-Built App Slow? A Diagnostic Order
Slow AI-built apps are slow for a short list of predictable reasons, and they appear in a predictable order. Measure first, then work down the list.
Steve Jefferson
Aug 7, 2026
Running Multiple AI Coding Agents in Parallel
Running several coding agents at once sounds like a straight multiplier. It is not, until you solve isolation and task splitting. Here is the setup that works.
Steve Jefferson
Aug 6, 2026
AI Tools for Photographers
The best AI tools for photographers are not generative image tools. Culling, batch editing, and client admin save the most real hours.
Cecilia Iona
Aug 6, 2026
How to Get Consistent AI Output Every Time
Same prompt, different answer twice? Consistent AI output comes from three fixable sources: temperature, ambiguous instructions, and missing examples.
Steve Jefferson
Aug 6, 2026
How to Use AI to Refactor Legacy Code
Legacy code refactors go wrong when an agent rewrites with confidence and no safety net. Characterize behavior, refactor in small diffs, verify each one.
Steve Jefferson
Aug 6, 2026
How to Write Good Commit Messages With AI
AI coding agents default to commit messages that restate the diff. A Conventional Commits template and a two-question review habit fix that.
Steve Jefferson
Aug 6, 2026
Respond to Customer Reviews With AI Without Sounding Fake
AI can draft your review replies in a fraction of the time, and it can also make a bad situation worse by answering a serious complaint in template voice. The rule is which reviews it touches.
Steve Jefferson
Aug 6, 2026
How to Use Git With an AI Coding Agent Safely
An AI coding agent edits many files at once and cannot reliably tell you what it changed. Git is the only honest record you have. Here is the workflow, the commands, and the recovery drill.
Steve Jefferson
Aug 6, 2026
How to Reduce No-Shows With AI Scheduling
A sequenced system for cutting appointment no-shows: instant booking confirmations, a 48-hour and 2-hour reminder cadence, two-way reply handling that auto-frees slots, and deposits for the serial no-showers reminders can't fix.
Steve Jefferson
Aug 5, 2026
AI Tools for Personal Trainers: What to Automate
Most trainers lose their Sunday nights to five repetitive admin tasks. Here's a task-by-task breakdown of which ones AI can actually take over, and which still need you.
Steve Jefferson
Aug 5, 2026
How to Prompt AI to Match Your Brand Voice
Generic AI output sounds like every other AI output because your prompt never told it who you are. Here's a reusable brand voice prompt template, plus a before/after example.
Steve Jefferson
Aug 5, 2026
How to Write a Privacy Policy for an AI App
Sending user data to a model changes eight sections of your privacy policy. The facts to establish first, and what each section actually has to say.
Steve Jefferson
Aug 5, 2026
How to Reduce AI API Costs Without Losing Quality
Model bills climbing faster than revenue? Four levers, ordered by money saved per hour of work, plus the six-step audit that finds where it is going.
Steve Jefferson
Aug 5, 2026
Stop AI Changing Code You Did Not Ask It To Change
Ask for a one-line fix, get a 400-line diff. Why AI coding tools overreach, and the six habits that keep the change the size you asked for.
Steve Jefferson
Aug 5, 2026
How to Set Spending Limits for AI Agents
A practical checklist for capping AI agent spend, requiring approval, scoping access, logging actions, and pull-testing a kill switch before you trust it.
Steve Jefferson
Aug 4, 2026
How to Write a System Prompt for a Custom AI Assistant
A practical guide to writing a system prompt for a custom AI assistant, showing one real prompt rewritten through three drafts to fix specific weaknesses.
Steve Jefferson
Aug 4, 2026
Turn a Spreadsheet Into an App With AI
Your spreadsheet already contains the design. The columns are your fields, the formulas are your logic, and the repeated values tell you where to split entities.
Steve Jefferson
Aug 4, 2026
How Long Should a Prompt Be? Practical Limits
Most working prompts land between 50 and 400 words of instruction. Below that you leave gaps; above it, your instructions start competing with each other.
Steve Jefferson
Aug 3, 2026
How to Debug AI-Generated Code: A Step-by-Step Process
You didn't write the code that just broke, so the usual debugging instincts don't apply. Here's the actual process: localize the bug before touching anything, make the AI explain the suspect function line by line, add targeted logging instead of guessing, and test one hypothesis at a time, walked through on a real bug.
Steve Jefferson
Aug 3, 2026
Prompt Engineering: A Framework for Prompts That Actually Work
Most bad AI output comes from a missing piece in the prompt, not a dumb model. Here's the five-layer framework, context, task, constraints, format, examples, applied to one real prompt built weak, better, and best.
Steve Jefferson
Aug 3, 2026
How to Write an SOP With AI (Interview Method)
Asking AI to write a standard operating procedure produces a generic document nobody follows. Having it interview the person who does the job does not.
Steve Jefferson
Aug 3, 2026
How to Use AI to Write Tests That Catch Bugs
AI writes tests fast, and by default it writes them from your code, which means they confirm the bug instead of finding it. Here is how to avoid that.
Steve Jefferson
Aug 3, 2026
How to Get JSON Output From AI Reliably
Asking a model for JSON is a preference, not a guarantee. The three ways it breaks, and how to escalate from prompt wording to schema enforcement.
Steve Jefferson
Aug 2, 2026
How to Prompt AI Without Getting Generic Answers
Why AI defaults to bland, generic answers and the five specific habits, each with a before-and-after example, that fix it.
Steve Jefferson
Aug 2, 2026
How to Give AI Context About Your Business
A one-page business context brief with six fields, written once and reused everywhere, turns generic AI answers into specific ones. Template and worked example included.
Steve Jefferson
Aug 2, 2026
How to Automate Email Replies With AI Safely
A safe AI email automation workflow uses draft-only mode, confidence thresholds, and escalation triggers instead of letting a model send replies on its own.
Steve Jefferson
Aug 1, 2026
How to Automate Customer Support With AI
A decision framework for what to automate versus always escalate to a human, plus the real cost math for a small business running about 200 support tickets a month.
Steve Jefferson
Aug 1, 2026
How to Fix a Bad AI Prompt (A Rewrite Method)
A practical rewrite method for fixing a bad AI prompt: diagnose whether it is missing a specific task, constraints, or an output format.
Steve Jefferson
Aug 1, 2026
Automate Invoicing With AI: A Small Business Guide
A worked invoicing workflow for a twelve client freelance business, built step by step, including the three parts of the process you should deliberately leave manual.
Steve Jefferson
Get the next post in your inbox
One email a month. Product updates, engineering posts, and the best of Built with Swarmz.