Author profile

Keith Pattison

Founder, Black Flag Design

Keith leads Black Flag Design, a studio that ships production-ready software with AI-assisted development. He writes about the disciplines — small scope, weekly evidence, and human oversight — that keep AI-built systems reliable in the real world.

Articles

Writing by Keith Pattison

18 published articles in the Black Flag Journal.

A small-business owner at their workbench with a calm advisor figure beside them pointing at a simple cash-flow timeline, suggesting a recommendation while the owner keeps a hand on the decision.

applied ai June 24, 2026 5 min read

The banking layer non-expert owners actually need

Most small-business owners aren't finance people, yet the tools they live in still ask them to make expensive cash calls alone. Embedding judgment — not just dashboards — inside those tools is the real applied-AI opportunity. Here is how to build it without breaking trust.

An applied-AI take on embedding cash-flow and risk judgment inside the everyday tools that non-expert small-business owners already use.

Keith Pattison

Founder, Black Flag Design

A pane of frosted glass coming into focus over a diverse line of people, with two distinct mechanical gears separated by a clear divider above them, one etched with rigid grid lines and one holding a human silhouette

applied ai June 24, 2026 4 min read

When being misread costs people money: applied AI in community-centered banking

Inclusion-focused fintech doesn't fail at automation. It fails at judgment — the moment a model decides who looks creditworthy and who looks suspicious. The fix is architectural, not just better data.

In community-centered banking, the hard AI problems are judgment problems: who gets approved, who gets flagged, and whether the customer can trust the answer. Here's how to build for that.

Keith Pattison

Founder, Black Flag Design

A path splits at a junction; an automated guide walks the young traveler along the easy stretch, then stops and hands off to a human advisor at the harder branch.

applied ai June 24, 2026 4 min read

When the coach should stop talking: building AI for first-time earners

AI financial coaches are excellent at the repetitive, low-stakes guidance that builds a young earner's confidence. They become dangerous the moment they keep talking through a decision that should have been handed to a human.

An applied-AI playbook for coaching first-time earners: automate the repetitive judgment, escalate the costly one, and earn trust by showing your work.

Keith Pattison

Founder, Black Flag Design

A large crowd of small hands passing coins toward a single distant figure standing on a podium, with a balance scale positioned between the crowd and the figure

applied ai June 24, 2026 4 min read

When the crowd is the underwriter: applied AI for funding outcomes you can't see yet

Crowd-funded outcome markets ask strangers to bet on a future that hasn't happened. That makes trust, fraud, and incentive design the whole product. Applied AI helps, but only if you point it at the expensive judgment and keep humans on the costly calls.

In markets where crowds fund uncertain outcomes, trust is the product. Here's where applied AI actually earns its place, and a two-day way to start.

Keith Pattison

Founder, Black Flag Design

A person's hands resting on the faders of a large audio mixing board, with the upper bank of channels glowing as if operated automatically while the hands stay on the lower controls.

applied ai June 24, 2026 5 min read

Keep your hands on the dials: applied AI for the high-touch services agency

In a people business, the relationship is the product — and that is exactly what teams fear automating away. The way through is not to replace judgment but to industrialize everything around it, so your best people spend their hours where being human actually pays.

How a relationship-driven services agency can apply AI to the repetitive work surrounding client judgment — without letting software touch the relationship itself.

Keith Pattison

Founder, Black Flag Design

Three distinct data streams flowing into a single balanced scale that outputs one numbered score, with a human hand resting on the scale's beam

applied ai June 24, 2026 4 min read

Scoring people fairly: the explainability burden of rating humans with AI

Composite scores that rank people — blending grades, social signals, and demonstrated skill — are some of the highest-stakes models you can ship. The hard part isn't the math; it's earning the right to be trusted with a number that changes someone's life.

When AI assigns a single score to a person, explainability and bias aren't features — they're the whole product. Here's how to build composite rating systems that hold up.

Keith Pattison

Founder, Black Flag Design

A control room split down the middle: automated gauges and data streams on the left, a person with a hand on a single decision lever on the right, a seam of light between them

applied ai June 24, 2026 4 min read

Inside the RIA: Where Data Science Changes Wealth Management and Where It Can't

A wealth platform with a real data-science team has an advantage — and a trap. The advantage is leverage on operations. The trap is mistaking that leverage for a license to automate judgment.

Where applied AI and data science actually change RIA operations — and where human judgment has to stay no matter how good the model gets.

Keith Pattison

Founder, Black Flag Design

A person at the base of a mountain trail holding a map that unfurls into an annotated path with markers toward a blank summit flag

applied ai June 24, 2026 4 min read

Capital Without the Reps: Applied AI for the Operator Transition

Plenty of people end up with capital before they have operating experience. The gap isn't money or ambition — it's reps. Applied AI can close most of that gap, as long as the human still makes the call.

Helping someone with capital but not yet operating experience make business decisions — with AI compressing research and diligence while a human owns the judgment.

Keith Pattison

Founder, Black Flag Design

A single craftsman's workbench in front, repeated into an orderly row connected by a conveyor stretching to the horizon

applied ai June 24, 2026 4 min read

From Advisor to Platform: Applied AI and the Client Experience Layer

High-touch advisory firms hit a wall when they try to grow: the very intimacy that wins clients is the thing that won't scale. The way through isn't more advisors — it's a client experience layer.

What happens to the client experience when a high-touch advisory firm tries to become a platform — and where applied AI fits without diluting the relationship.

Keith Pattison

Founder, Black Flag Design

A tree whose roots branch into smaller trees, with a human hand tending one tangled branch

applied ai June 24, 2026 4 min read

Applied AI and the Hundred-Year Advisory Relationship

Multi-generational wealth advice is the most personal, judgment-heavy work in finance. The question isn't whether to automate it, but where AI carries the weight and where a human still has to.

How to scale a deeply personal advisory relationship across a family and decades without turning it into a robo-advisor.

Keith Pattison

Founder, Black Flag Design

A cluttered marketplace handshake on one side transforms into a clean operations dashboard with a pipeline of deal cards moving through labeled stages, one flagged for review

ai June 24, 2026 4 min read

From Marketplace to Operating System: Applied AI and the NIL Back Office

The first wave of NIL software solved discovery — match an athlete to a brand. The revenue-sharing era turned NIL into an ongoing operation someone has to run. Marketplaces don't run operations. Operating systems do, and that's where applied AI earns its keep.

Discovery in the NIL economy is solved. The unsolved, expensive part is the back office — deals, disclosures, compliance, payments — at scale. Here's where applied AI fits, and where judgment still has to win.

Keith Pattison

Founder, Black Flag Design

An athlete at center radiating into dozens of video clips and feeds; a chaotic scatter on one side resolves into an organized, labeled publishing queue on the other

ai June 24, 2026 4 min read

Applied AI in Sports Media: When Every Athlete Is a Distribution Channel

Teams and leagues are expected to produce thousands of personalized clips a week for athletes who each out-reach the old broadcast networks. The supply of moments hasn't changed; the demand for content cut from them has exploded. That gap is where applied AI earns its keep — or gets built badly.

The athlete became the distribution channel, and almost no one can feed that channel by hand. Here's where AI actually fits in sports media — and where judgment still has to win.

Keith Pattison

Founder, Black Flag Design

HARNESS Canvas LinkedIn cover: AI created a new problem, too many ideas.

ai May 13, 2026 6 min read

HARNESS: Turning AI Fog Into a Buildable Idea

AI made it easier to generate ideas. That is not the hard part anymore. The hard part is turning a fuzzy possibility into something a team can actually evaluate, scope, and build.

After Boulder Startup Week, the thing that kept sticking with me was not that teams need more AI ideas. They have plenty. What they need is a way to turn the fog into a real product shape. That is what the HARNESS Canvas is for.

Keith Pattison

Founder, Black Flag Design

Pen-and-ink sketch of a small clockwork robot working at a tool-covered workbench late at night while a human sleeps peacefully on a couch in the background, a wall clock reading 2:00 above

ai April 24, 2026 13 min read

The Agent Stays Up Late, Not Me

Every senior engineer knows the right way to set up a codebase. None of them do it. Here’s the four-stage framework we use — The Ratchet — to take a vibe-coded project all the way to a thing you’d trust in production, and the punchline about why this only just became worth doing.

Most teams have always known they should be running tests, type-checking, security audits, accessibility checks, dead-code analysis, prose linting, and a coverage floor. Most teams run two of those. Here’s why that math has finally inverted, and the four-stage framework we use to ratchet a vibe-coded project to a hardened one.

Keith Pattison

Founder, Black Flag Design

Pen-and-ink sketch of two keys on a ring with paper labels AI STUDIO and VERTEX, a thin red arrow pointing at the VERTEX key

ai April 24, 2026 4 min read

Two Kinds of Google Keys, Two Endpoints

The Gemini key that rejects your request with 403 API_KEY_SERVICE_BLOCKED is almost certainly a Vertex key being sent to the AI Studio endpoint. Here is how to tell them apart, and which endpoint to use.

We spent an hour chasing what looked like a billing issue and turned out to be a key-format mismatch. The key worked. Google was just telling us we had pointed it at the wrong building. If you are shipping a Gemini integration, this is the one-page reference we wish we had read first.

Keith Pattison

Founder, Black Flag Design

Terminal-output panel showing two red FAIL lines and a green PASS line, with an arrow pointing from red to green

ai April 24, 2026 6 min read

Red/Green TDD When Your Dep Is a Generative API

How to test-drive code that integrates with Gemini, Claude, or any non-deterministic API — without pretending the API is deterministic.

Gemini does not care about your unit tests. But your unit tests can still be green, fast, and trustworthy — if you put the seam between your code and Gemini in the right place. Here is the pattern we used to ship a CMS image-generation feature in under a day, with every layer TDD'd and the Gemini boundary mocked without hand-waving.

Keith Pattison

Founder, Black Flag Design

Black Flag Journal

ai April 20, 2026 5 min read

Six Principles for Shipping Reliable Software with AI

How we stay sane while "vibes" infiltrate codebases — the playbook we run on every engagement.

AI-generated code floods projects with promises of speed and delivers drift instead. Six disciplines turn it back into a reliable tool: small scope, human judgment, repeated purpose, weekly planning, active management, and continuous improvement.

Keith Pattison

Founder, Black Flag Design

Black Flag Journal

playbook April 20, 2026 6 min read

The Black Flag Playbook: Six Principles for Shipping with AI

Battle-tested principles for teams building real software with AI-generated code. Human judgment, tight scope, and weekly evidence — the disciplines that keep AI-built systems reliable.

The six rules we use to ship production software with AI. Small scope, weekly demos, human-led oversight, and continuous improvement — drawn from six months of real client engagements.

Keith Pattison

Founder, Black Flag Design