Topic archive

Human In The Loop

20 published stories filed under Human In The Loop.

A careful human hand on a railway switch lever at a forking track, with a magnifying lens inspecting the junction before the choice

applied ai June 24, 2026 5 min read

When Being Wrong Costs Someone Their Freedom

In public systems where an error changes the course of a person's life, the goal of applied AI is not to decide faster. It is to make expensive human judgment go further — with every step visible, contestable, and owned by a person.

In high-stakes public systems, a confident wrong answer is worse than no answer. Where applied AI belongs, where a human must stay in the loop, and why explainability is the whole product.

Eli Wood

CEO, Black Flag Design

A small lever on a fulcrum shifting a large interlocking structure of gears and girders

applied ai June 24, 2026 4 min read

After the Roadmap, Someone Has to Build the Road

System-change organizations are brilliant at convening the field and writing the roadmap. The next frontier is harder and more valuable: building the tools the roadmap calls for, with humans kept firmly at the center.

Intermediary organizations that facilitate adoption can do more than convene — they can build the applied-AI tools their own roadmaps point to, without losing the human-centered values that earned them trust.

Eli Wood

CEO, Black Flag Design

A glowing speech bubble crystallizing into a reusable toolkit object that many hands reach for

applied ai June 24, 2026 4 min read

From Teaching People the Tool to Building the Tool

An organization that has taught thousands of educators how to use AI knows something rare: where the judgment actually is. The next move is to stop shipping guidance about the tool and start shipping a tool that exercises that judgment with them.

The leap from AI-literacy content to an applied-AI product is shorter than it looks — and the curriculum already encodes the judgment the product needs to embody.

Eli Wood

CEO, Black Flag Design

A single lantern's light relayed through mirrors to illuminate many distant desks

applied ai June 24, 2026 4 min read

Don't Replace the Expert. Clone Their Attention.

When the expensive thing is a great teacher and there aren't enough of them, the temptation is to replace the teacher with a model. The better move is to take the one thing that doesn't scale — their attention — and stretch it.

Applied AI's role in a teacher shortage isn't to substitute for scarce expertise. It's to extend it — handling the repetitive so the expert is present where the stakes are highest.

Eli Wood

CEO, Black Flag Design

A glowing software dashboard on one side and a classroom of students on the other, with an educator bridging the gap between them by placing an action card

applied ai June 24, 2026 4 min read

The Dashboard Isn't the Intervention

Most intervention software is bought, deployed, and then quietly not used. The gap isn't features. It's the distance between a dashboard that reports a problem and a person who acts on it.

Districts buy multi-tiered intervention systems and under-implement them. Applied AI's real job isn't a better dashboard — it's closing the gap between insight and action.

Eli Wood

CEO, Black Flag Design

A hand bringing two puzzle pieces together to join, with a circle of figures forming a cohort in the background

applied ai June 24, 2026 4 min read

Cohort-Based Programs at Scale: Where AI Helps and Where Mentorship Can't Be Automated

Cohort programs work because of intensity and intimacy. Scaling them with AI is tempting and easy to get wrong — the answer is to automate the machinery of delivery and leave the mentorship, the matching commit, and the community to people.

How to use applied AI across the lifecycle of a cohort-based program — delivery, mentorship matching, and alumni community — while keeping a human in the loop where it counts.

Eli Wood

CEO, Black Flag Design

A scene split between turning mechanical gears on one side and two people in close conversation on the other, joined by a single beam of light

applied ai June 24, 2026 4 min read

From Programs to Platform: Scaling Delivery Without Losing the Human Touch

An organization that runs programs and events lives on relationships. The fear about scaling with AI is that the relationships die. The opposite is true — if you automate the logistics and protect the human moments.

How a programs-and-events organization can use applied AI to scale delivery into a platform — automating logistics while keeping humans where the relationship actually lives.

Eli Wood

CEO, Black Flag Design

Two groups of people separated by a gap, connected by a single sturdy plank in the foreground while a large empty scaffold looms unbuilt behind

applied ai June 24, 2026 4 min read

Before You Build the Platform: The First Useful Thing AI Should Do

Early-stage teams building a matching network reach for the platform first — the dashboards, the accounts, the directory. The leverage is somewhere smaller and sooner: the one repetitive judgment call you're already making by hand.

What an early-stage matching network should automate with AI before building any platform — find the one expensive, repetitive judgment and ship that first.

Eli Wood

CEO, 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 person at the edge of a dense web of interconnected nodes, with one illuminated path threading through the tangle and a hand selecting a single node

applied ai June 24, 2026 4 min read

Matching People to Help: Applied AI for a Messy Resource Graph

When someone needs help and the right help is buried in three hundred programs with different rules, the problem isn't a search box. It's matching across a graph nobody fully understands — and knowing which matches a human has to bless.

How applied AI navigates a sprawl of programs and eligibility rules to put people in front of the right help — and where a human still has to make the call.

Eli Wood

CEO, Black Flag Design

The Draft Isn't the Close: Applied AI in B2B Sales Enablement

sales enablement June 24, 2026 4 min read

The Draft Isn't the Close: Applied AI in B2B Sales Enablement

AI can write a first-class proposal in minutes. Your rep still has to win the deal. Here's why that distinction matters — and how to build the tooling around it.

AI drafts well. Humans close. The teams that figure out which work belongs to which are pulling ahead.

Eli Wood

CEO, Black Flag Design

Black Flag Journal

applied ai June 24, 2026 3 min read

The Navigation Problem: Why AI Alone Won't Get Patients to the Right Resources

Social-determinants navigation is one of the most tractable applied-AI problems in healthcare — and one of the most commonly botched. Here's how to do it right.

Matching patients to community resources sounds like a routing problem. It isn't. Here's the architecture that actually works.

Eli Wood

CEO, Black Flag Design

When AI Meets Money: The Case for Human-in-the-Loop Financial Coaching

applied ai June 24, 2026 3 min read

When AI Meets Money: The Case for Human-in-the-Loop Financial Coaching

AI can make financial coaching accessible to millions — but only if you build it so a human is still in the room when it counts.

The real unlock isn't automation. It's knowing exactly where to keep a human in the loop.

Eli Wood

CEO, Black Flag Design

The Judgment Engine: Building AI That Knows When to Stop and Ask

health ai June 24, 2026 4 min read

The Judgment Engine: Building AI That Knows When to Stop and Ask

Most AI failures in health settings aren't technical failures. They're failures of knowing when the machine should hand it back to the human.

When being wrong has clinical consequences, the architecture question isn't how to make AI more confident—it's how to make it know its own limits.

Eli Wood

CEO, Black Flag Design

A teacher's hand resting lightly on the back of a chair where a young student works through a problem with a glowing guided thread of reasoning on the desk

applied ai June 24, 2026 4 min read

When AI Tutors Think Out Loud With a Student

A model that guides a child's reasoning in the moment is doing the most consequential thing software can do in a classroom. The bar for that is not engagement. It's the bar you'd hold a student teacher to.

Real-time AI instruction raises the stakes the instant a model starts shaping how a student thinks. Here's where the safety bar belongs and why the teacher stays in the loop.

Eli Wood

CEO, 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