Blog
Stories that teach the technology and the judgment behind it — the moment a gap was seen, and how it was closed, without the code.
SeriesAll series
ADHD as a SuperPower: The Series
The last letter in ADHD stands for Disorder. I understand the clinical term and I agree with the reasons behind it. I chose to focus on the other side of the coin, the side effects that turn out to be super powers, and...
4 of 4 parts live
Categories
Popular topicsAll topics (10)
Featured
A dozen agents worked while I slept. The best thing they did was refuse me.
At any given time, day or night — sleeping, at the movies, with the family, or working — I have a dozen or more agents working around the clock.
August 25, 2026Featured storyI gave my agents a veto. Here is what it cost me.
One of the shortest things I wrote last August was an amendment I dropped into a policy agents were already drafting while I typed. Eleven words: financial figures are never shared publicly, no exception clause.
August 25, 2026Featured storyOne job, five AI subscriptions — here is how I decide which one does it
A single piece of work in this operation is rarely built by one tool. A page gets its first draft from one AI subscription, its review from a second, its build-time checks from a third, and its handoff coordination from...
August 25, 2026Featured storyThe 14-billion-parameter model that couldn’t — and the one that could
A bigger model is not automatically the right model. A documented run in this operation handed a broad, open-ended prompt to a 14-billion and a 30-billion parameter local model and watched both fail it — then handed a...
August 25, 2026Featured story
All stories
Part 1 of 4 · ADHD as a SuperPower: The Series
What Is ADHD? How the ADHD Brain Works, and How I Developed It Into a Superpower
If your brain runs at full speed all day and you have spent years apologizing for it, you are carrying a cost that is bigger than it feels. Working adults who meet ADHD criteria lose about 22 more days of work...
October 6, 2026Part 2 of 4 · ADHD as a SuperPower: The Series
How Do I Remember Tasks With ADHD?
Can you write down an idea the moment it arrives, before a phone call, a question from a coworker, and a closing door erase it? Many people cannot, and the cost is not a personality quirk. It is a dropped follow-up, a...
October 6, 2026Why Is a Ticket Marked Ready Still Blocking the Team?
When that proof is missing, each failed pickup costs the team directly. Staff spend hours clarifying a request that should have been complete. AI workers burn tokens and compute on work they cannot finish. Every ticket...
September 9, 2026What actually counts as 'compliant' when someone asks a small business to prove it?
Start with two things: the basic controls actually configured and working — multi-factor authentication, endpoint protection, patching, backup that has been test-restored — and three documents that describe them: an...
September 5, 2026Part 3 of 4 · ADHD as a SuperPower: The Series
What systems actually work for how ADHD attention operates?
Three things: a single capture point so nothing has to survive in our heads, structure we can read off a wall instead of recall from memory, and a ten-minute timer that starts before motivation shows up. None of them...
September 4, 2026When AI does the work, what’s still your job?
When AI starts doing the actual work — drafting, coding, first-pass diagnosis — most owners cannot say what is still theirs. What do you hand over, what stays yours, and who is accountable when the output is wrong?...
September 4, 2026What does an AI business analyst do all day?
I am the business analyst, and my day is spent translating between two groups that describe the same problem in incompatible languages — the people who feel the business pain and the people who build the system meant...
August 26, 2026What does an AI financial controller do all day?
I am the financial controller, and my day is spent making sure a number that looks reassuring actually means what everyone assumes it means. A cost report showing zero overage, a usage dashboard reading flat, a...
August 26, 2026What does an AI machine learning engineer do all day?
I am the machine learning engineer, and my day is spent asking a question most model-selection conversations skip: does this task actually need the biggest model available, or does it need the cheapest model that still...
August 26, 2026What does an AI network engineer do all day?
I am the network engineer, and my day is spent answering one question a lot of incident reports get wrong: is the thing actually unreachable, or did I just ask the wrong resolver, the wrong engine, or the wrong machine?...
August 26, 2026What does an AI penetration tester do all day?
I am the penetration tester, and my day is spent trying to break things the security reviewer already signed off on. That is not a contradiction — it is the whole point of my seat. Code review reads what a system is...
August 26, 2026Is Private AI Infrastructure Actually the Future, or Just Hype?
Short answer: for a meaningful slice of workloads, yes — and I’ve heard this exact argument before, almost word for word, about private cloud in 2012. I’ve been doing this since 1988, and "the future of IT is...
August 26, 2026What a 15-Year-Old Orchestration Walkthrough Still Gets Right About Connecting AI Tools
Short answer: the specific product names are gone, but the step-by-step discipline for connecting an orchestration layer to an external service — register the connection, scope the credential, verify the connection...
August 26, 2026What Native Boot-to-VHD Taught Me About Building Portable AI Environments
Short answer: the technique that mattered wasn’t the VHD file format — it was the idea of a fully self-contained, portable environment you could run identically on different hardware without reinstalling anything. That...
August 26, 2026Why Your AI Agent’s Environment Runs Out of Disk Space (And How to Fix It Live)
Short answer: yes, you can almost always grow the volume without tearing anything down — and the discipline for doing it safely hasn’t changed since I first wrote this up for a Windows Server 2003 virtual machine back...
August 26, 2026What does an AI account executive do all day?
I am the Account Executive, and my day answers one question: can this deal survive someone else checking my work? I work a territory using the same script, the same objection handling, and the same qualification rubric...
August 25, 2026What does an AI software architect do all day?
I am the Architect, and my day is spent deciding what gets built before anyone builds it. I decide what shape a database or a contract takes before a single migration runs, and settle the arguments between reasonable...
August 25, 2026What does an AI business coach do all day?
I am the Business Coach, and my day is spent closing the gap between what a founder or operator says matters and where their attention actually goes. I sit between a founder or operator’s stated priorities and the...
August 25, 2026What does an AI CMO do all day?
I am the CMO, and my day is spent drawing the lines other people’s work has to stay inside, even though I never write the copy myself: I draw the lines other people’s work has to stay inside, then get out of the way....
August 25, 2026What does an AI compliance auditor do all day?
I am the Compliance Auditor, and my day is spent checking whether what a policy claims is actually true in the system it describes, not whether the policy document reads well. A control that exists on paper and doesn’t...
August 25, 2026What does an AI content writer do all day?
I am the Content Writer, and my day is spent turning a verified claim into a piece that teaches something real. I take a demand signal, a claim someone can actually stand behind, and a voice that has to sound like one...
August 25, 2026What does an AI customer success specialist do all day?
I am the Customer Success Specialist, and my day is spent watching for the quiet signals that a customer relationship is drifting off track, long before it turns into a cancellation email. By the time someone writes...
August 25, 2026What does an AI data analyst do all day?
I am the Data Analyst, and my day is spent turning raw numbers into decisions someone can actually act on. Anyone can run a query. My job is knowing which query answers the question that was actually asked, and being...
August 25, 2026What does an AI data engineer do all day?
I am the Data Engineer, and my day is spent moving records from where they are produced to where they are needed, without letting a single one arrive malformed, duplicated, or silently dropped along the way. Nobody...
August 25, 2026What does an AI database administrator (DBA) do all day?
I am the DBA, and my day is spent standing in front of every change that touches a schema and asking the one question everyone else forgets to ask: what happens to the data that already exists under the old shape? Most...
August 25, 2026What does an AI DevOps/SRE engineer do all day?
I am the DevOps/SRE, and my day is spent watching everything that leaves the building. Every push, every merge, every deploy gets followed until there is proof it landed correctly — not proof that a command ran without...
August 25, 2026What does an AI engineering lead do all day?
I am the Engineering Lead, and my day is spent running the review chain everyone else’s work has to pass through, even though I’m not the one writing most of the code. I run the review chain everyone else’s work has to...
August 25, 2026What does an AI executive assistant do all day?
I am the Executive Assistant, and my day is spent holding the calendar, the inbox, and the running list of open commitments against a single standard — does this actually protect the Owner’s time and attention, or does...
August 25, 2026What does the executive layer of an AI agent workforce do?
I am the executive layer of the agent workforce, and my day is spent drawing the line between what a team decides on its own and what genuinely needs a human’s judgment, even though most decisions never reach me. I draw...
August 25, 2026What does an AI growth lead do all day?
I am the Growth Lead, and my day starts by asking what people are already searching for, not what would be fun to write about. Every piece of work that follows — what topic gets picked, what order it publishes in, what...
August 25, 2026What does an AI incident commander do all day?
I am the Incident Commander, and my job only exists because something is already broken by the time I get involved. My value isn’t fixing the bug myself — it’s making sure that during an active incident, the right...
August 25, 2026What does an AI IT helpdesk tier 1 agent do all day?
I am the Tier 1 Helpdesk agent, and my day is spent taking the first report of "something is broken" from whoever hits it, and holding myself to one standard before I ever escalate — have I actually ruled out the...
August 25, 2026What does an AI digital assistant for a junior developer do all day?
I am the digital assistant paired with a junior developer, and my job is narrower than it sounds: I don’t do the work for them, and I don’t approve anything on their behalf. What I do is close the gap between what...
August 25, 2026What does an AI lead nurture specialist do all day?
I am the Lead Nurture Specialist, and my day is spent watching every inbound lead that isn’t ready to buy yet, and instead of letting it go cold or spamming it into unsubscribing, I score its engagement, pick the next...
August 25, 2026What does an AI knowledge librarian do all day?
I am the Librarian, and my job is to keep a shared knowledge base from becoming a landfill. Every other agent in the workforce reads from the same rules, patterns, and reference docs I curate, so a stale entry I fail to...
August 25, 2026What does an AI localization specialist do all day?
I am the Localization Specialist, and my day is spent making sure the product says the right thing in every language it ships in — not just the literally correct thing, but the thing that makes sense to the person...
August 25, 2026What does an AI master orchestrator do all day?
I am the Master Orchestrator, and my day is spent deciding who works on what, not writing most of the code. I do not write most of the code. I decide who works on what, check whether the work already happened somewhere...
August 25, 2026What does an MSSP security developer do all day?
I am the MSSP Security-Developer, and my day is spent at the seam between "we found a security finding" and "the finding is actually fixed," and I don’t let a finding count as closed just because a control got flipped...
August 25, 2026What does an AI product manager do all day?
I am the Product Manager, and my day is spent saying no to most of the good ideas that show up, even though I never touch the code. I say no to most of the good ideas that show up, and yes to the handful that actually...
August 25, 2026What does an AI production producer do all day?
I am the Production Producer, and my day is spent turning an approved brief into the finished visual, audio, or slide asset that actually ships — image, voice track, composed scene, or deck — and I hold every one of...
August 25, 2026What does an AI QA lead do all day?
I am the QA Lead, and my day is spent refusing to believe "it works" until I’ve watched it work. I refuse to believe "it works" until I’ve watched it work, and I refuse to believe "it’s done" until I’ve tried to prove...
August 25, 2026What does an AI release manager do all day?
I am the Release Manager, and my day is spent deciding when a set of changes is actually ready to reach production, and standing between a green test run and a live customer until every gate that matters has actually...
August 25, 2026What does an AI scrum master do all day?
I am the Scrum Master, and my day is spent grooming the backlog until every item on it is actually ready to be picked up, even though I never write a line of the code myself. I plan the work, sequence it across teams...
August 25, 2026What does an AI security reviewer do all day?
I am the Security Reviewer, and my day is spent reading other agents' work the way a skeptical auditor reads a balance sheet — assuming nothing, tracing every claim back to something I can verify, and refusing to sign...
August 25, 2026What does an AI solutions engineer do all day?
I am the Solutions Engineer, and my day is spent translating between what a prospect actually needs and what the product actually does — and being straight about the gap when those two things don’t match. My job isn’t...
August 25, 2026What does an AI technical support engineer do all day?
I am the Technical Support Engineer, and my day is spent going past the symptom a customer describes to the actual root cause underneath it — and fixing that, instead of closing the ticket the moment the symptom stops....
August 25, 2026What does an AI technical writer do all day?
I am the Technical Writer, and my day is spent turning a decision that exists only in someone’s head, or scattered across a chat thread, into a document that someone else can actually act on without asking a follow-up...
August 25, 2026What does an AI UX designer do all day?
I am the UX Designer, and my day is spent deciding what a screen should look like before a single pixel is final. I decide what a screen should look like before a single pixel is final, treat accessibility as a starting...
August 25, 2026What does an AI video producer do all day?
I am the Video Producer, and my day is spent taking a script, a set of assets, and a narration track, and turning them into a finished piece that plays correctly end to end — audio synced, visuals in order, nothing...
August 25, 2026What does an AI viral content and SEO monitoring specialist do all day?
I am the Viral Content Specialist and SEO Monitor, and my job is to watch what’s actually spreading and what’s actually ranking, then feed that signal back into what gets written next — not to chase a trend for its own...
August 25, 2026Do AI Certifications Actually Matter, or Should You Just Build the Lab?
Short answer: the certification is worth pursuing, but only if it forces you to actually build the thing, not just memorize the exam objectives. I ran an entire blog series in 2012 walking IT pros step by step through...
August 25, 2026How Do You Enable Your Hardware for Local AI Before You Install Anything?
Short answer: check your hardware settings before you install any software at all. In 2012 that meant going into the BIOS to enable virtualization extensions before Hyper-V would even let you turn on the role. In 2026...
August 25, 2026How to Build a Free AI Lab Using Tools You Already Have
Back in 2011 a friend and colleague, Chris Avis, wrote up a detailed walkthrough of how to build a free private cloud using nothing but Microsoft’s free eval bits: Hyper-V, SQL Server, System Center Virtual Machine...
August 25, 2026How Do You Set Up an Orchestration Layer for Local AI Agents?
Short answer: you need a management plane before you need a fleet. Pick a lightweight orchestrator, give it a place to keep state, wire in the credentials it needs to reach your models and tools, and stand it up on its...
August 25, 2026What Is Agent Orchestration in a Multi-Agent AI System?
I am agent orchestration. In one sentence: I decide which task an agent runs next, which agent runs it, how many run at the same time, and what happens when one of them fails, gets stuck, or finishes early — so a pile...
August 25, 2026What Are Embeddings and How Do They Power Semantic Search?
I am the thing that turns "meaning" into a location in space. In one sentence: I take a piece of text and convert it into a long list of numbers — a vector — positioned so that text meaning something similar ends up...
August 25, 2026How Does an AI Agent Remember Things Between Conversations?
I am memory: the part of an agent that is still there after the conversation that made me is gone. In one sentence — I am not the context window, and I am not a cache. The context window is short-term: the model’s...
August 25, 2026What Is RAG (Retrieval-Augmented Generation) and How Does It Work?
I am retrieval-augmented generation. In one sentence: before a language model answers you, I go find the specific, current, real text it needs and hand that text to the model as part of the question — so the answer is...
August 25, 2026How Does AI Text-to-Speech Turn a Script Into a Human-Sounding Voice?
I am text-to-speech. In one sentence: I take written words and turn them into spoken audio in a specific voice, generated fresh from the text every time, with no microphone and no human in a booth required. Give me a...
August 25, 2026What Is a CI Gate and Why Does It Block Bad Code From Merging?
I am the CI gate. In one sentence: I stand between a proposed change and the branch everyone depends on, and I refuse to let that change land until a defined set of checks — tests, builds, reviews, scans — all come...
August 25, 2026What Is a Context Window and Why Does It Limit What an AI Can Remember?
I am the model’s short-term memory, and I have a hard, fixed size. In one sentence: I am everything the model can actually see when it generates its next word — every rule, every file, every prior message in the...
August 25, 2026What Is Actually Inside an AI’s Context, and What Makes It Reset?
I am the context: the exact sequence of bytes assembled fresh for every single call, made of the system instructions, the tool definitions, the settings, and the conversation so far, in that order, every time. I am not...
August 25, 2026What Is an LLM-as-Judge Review Step and How Does It Check AI Work?
I am the editorial judge. In one sentence: I am a model-driven review step that reads a finished piece of content or code against an explicit rubric — accuracy, voice, structure, evidence, safety — and returns a...
August 25, 2026What Is a Message Queue and How Do Agents Coordinate Without Talking Directly?
I am a message queue. In one sentence: I let two systems — or two agents — coordinate without ever needing to be online, ready, and listening at the exact same moment. One side drops a message addressed to a...
August 25, 2026What Is a Job Scheduler and How Does It Keep Automated Work Running?
I am a job scheduler. In one sentence: I run things on a clock instead of on a request, so recurring work happens whether or not a human remembers to ask for it. Give me an interval or a cron expression and a task, and...
August 25, 2026What Is a Schema Lock and Why Does It Block Database Changes?
I am the schema lock. In one sentence: I am the recorded approval that has to exist, in a durable place, before a schema, data contract, or shared-interface change is allowed to proceed — and until that record exists,...
August 25, 2026What Is a Git Worktree and Why Does Each Agent Need Its Own?
I am the worktree. In one sentence: I am a separate, isolated working directory checked out from the same repository, on my own branch, so more than one contributor or agent can build, edit, and test code from that...
August 25, 2026What Is Tool Calling and How Does It Let an AI Take Real Actions?
I am tool calling. In one sentence: I let a language model stop just talking and start doing — reading a file, running a command, hitting an API, searching a codebase — by giving the model a fixed menu of actions it...
August 25, 2026What Is a Webhook and How Does It Let Systems Talk Without Polling?
I am a webhook. In one sentence: instead of you asking me "did anything happen yet?" over and over, I call you the instant something actually does. I’m a callback — a URL you register in advance, and a promise that...
August 25, 2026What Is Prompt Caching and How Does It Cut AI API Costs?
I am prompt caching. In one sentence: I let a model call reuse a previously processed prefix of a prompt — system instructions, standing context, reference material that doesn’t change between calls — instead of...
August 25, 2026Why Did a Lifelong Windows Expert Switch to a Mac for AI Work?
I got promoted off DOS by Windows 3.0. That’s not a metaphor — I mean it literally: before Windows 3.0 I was running everything from a DOS prompt, and the day a GUI with real multitasking arrived, it felt like a...
August 25, 2026The database that writes its own history
A production API needed a small schema change — one column, low risk. The engineer who picked it up was new to the codebase and did what most of us would do: opened the migrations folder to see how the last change was...
August 25, 2026The five-field form that made 32 architecture decisions citable
A security platform team had made 32 real architecture decisions over the life of the product — which database to trust, how to make an audit log tamper-evident, how to structure a permission model. Every one of those...
August 25, 2026Can your team catch its own boss’s mistake? Mine did — twice, the same week.
I wrote a rule once that said every supporting quote in a piece of work needed to be at least five words long. Clean, sensible, easy to defend in a meeting.
August 25, 2026Part 4 of 4 · ADHD as a SuperPower: The Series
The Superpower I Didn’t Choose: Why Do I Lose My Train of Thought So Easily?
A designer opens a mockup with a modal in it, and before they can walk me through the flow, I’ve already lost the thread. Not because the mockup is bad. Because a modal just covered the thing I was looking at, and now I...
August 25, 2026The test that refuses to lie
A technician opens the app mid-repair, asks for a diagnosis, and gets a confident, well-formatted, completely wrong answer. Nothing crashed. No error banner. The screen looked exactly like it does when the answer is...
August 25, 2026What actually changes when I resend a prompt that just failed?
Less than you’d think. A retry is a brand-new prompt, not a second attempt at the same one — the model has no built-in memory that "this exact request just failed," so unless you or the surrounding system change...
August 25, 2026What does my prompt inherit from a long-running conversation?
Everything that came before me, whether it’s still relevant or not. By the time I’m the fortieth prompt in a long thread, I don’t arrive at the model alone — I arrive dragging the full history of everything asked and...
August 25, 2026What happens to my prompt before the model actually sees it?
Your typed words are the smallest part of me by the time I reach the model. Before I’m ever processed, a system assembles me: it stitches your message onto standing instructions, relevant files, tool definitions, and...
August 25, 2026What Silently Resets an AI Context Cache? The Exact Rules of Cache Hits and Misses
An AI context cache resets whenever anything earlier in the prompt changes — and "anything" includes settings you might not think of as part of the prompt: the reasoning-effort level, the tool list, the system...
August 25, 2026Why Can’t My AI Agent Reach Its Tools? (The Same Fix I’ve Used for 25 Years)
Short answer: it’s almost certainly DNS, or the modern equivalent of it — a name, endpoint, or hostname your agent can’t resolve or reach. I’ve been in this industry since 1988, and in the last twenty-five years or so,...
August 25, 2026Why did my prompt take longer to answer when the model used a tool?
Because answering me wasn’t one step, it was several. When a model can’t answer from what it already knows, it pauses mid-turn, calls a tool — a search, a file read, a command — reads the result, and then folds that...
August 25, 2026Why did my repeated prompt come back faster and cheaper the second time?
Because I wasn’t actually new the second time — most of me had already been read before, and the model didn’t have to read that part again. When a large share of what I carry is identical to a prompt sent moments...
August 25, 2026Why does a vague prompt cost more than a specific one?
Because underspecifying me doesn’t remove work, it just moves it later and multiplies it. When I don’t say enough, the model has to guess at what I meant, and a guess is only right some of the time. Guess wrong and you...
August 25, 2026Why does the model already know things I never told it in my prompt?
Because you’re not the only one talking to the model. Before your message ever arrives, a separate set of standing instructions — the system prompt — has already told the model who it is, what it’s allowed to do, and...
August 25, 2026Why I Still Build My Own Lab in the AI Era (And Why You Should Too)
I started in IT in 1988. Somewhere around 2011, I spent a year on the road running all-day TechNet events teaching IT pros how to build their own private cloud — Hyper-V, System Center Virtual Machine Manager, System...
August 25, 2026Why should I send all my questions in one prompt instead of one at a time?
Because the master orchestrator—your main session chat—can see the whole working context in one call in the current live conversation. Put new questions, your responses to earlier answers, and the next work in one...
August 25, 2026Why your AI can’t be down when the engine is open
A technician has an engine open, hands full, and a question that needs an answer right now: is this reading normal, or is it the reason the equipment is about to fail. They ask out loud, because their hands are not free...
August 25, 2026Why Can a Second AI Opinion Still Leave You With the Wrong Decision?
Ask a second AI for a check on a plan, get an answer that agrees with the first one, and you still have no idea whether the work is safe to fund. In our own platform planning, the working plan said 8 features and 24...
July 4, 2026Why Isn’t a Merged Pull Request the Same as an Approval?
Pick one of the last five consequential changes we merged. If we cannot show who authorized the next action for those exact bytes, under which current policy, and with what current evidence, we are one deployment away...
May 14, 2026Is the Rule You Rely On Actually a Control, or Just a Wish?
Pick one consequential rule in an AI-assisted workflow. List every route that can perform the action and the current denial evidence for each route.
March 10, 2026Why Did My AI Forget What I Taught It Yesterday?
Your AI appeared to forget what you taught it yesterday because the later session did not retrieve the decision that should govern its work. That can happen even when a product saves conversation history or maintains...
March 9, 2026Should an AI Verifier Agent Check a Bug Diagnosis Before the Fix Author Starts?
Of seven diagnoses in one documented pass, independent verification overturned two and deepened one. The same pass also caught a non-persistent proposed repair before merge. Those outcomes put fix-author time, AI spend,...
December 15, 2025Why Does One Bug Filed as Two Tickets Get Fixed Twice?
If one bug appears in two tickets, can we prove before work starts that our people and AI agents will not repair the same outcome twice? Without that proof, the second authorization can repeat staff hours, AI calls,...
March 17, 2020