Skip to main content

Your AI Ambitions Need Better Foundations

· 8 min read
Trevor Grant
Builder in Chief

Clients come to us excited to "do AI." We love doing AI. But sometimes, before we can get to the fun part, we need to talk about the bailing wire and bubble gum holding their cloud environment together.

That conversation belongs in the budget meeting. If you are funding an AI application that people will depend on, you also need to fund the infrastructure required to operate it. Otherwise, the project risks exposing weaknesses your existing software has been quietly living with.

You can experiment while you work on those weaknesses. You should. Just understand that a convincing demo tells you very little about whether the house is ready for the party.

What I Brought Home from the Cavalry

· 6 min read
Trevor Grant
Builder in Chief

It's been a while since I've written here. Today is Veterans Day, and I want to talk about something that connects my time in the cavalry to the work we do at Aboriginal Armadillo: trusting people to make a decision when you can't give them instructions for everything they're about to encounter.

There's a moment from Kandahar that helps explain what I mean.

An AI Pilot Needs an Operating Thesis

· 6 min read
Trevor Grant
Builder in Chief

An AI pilot is not an operating plan.

It is a container. It tells us that a company intends to try some technology for a limited period. It does not tell us which work will change, who will do less of it, where judgment will remain, or how anyone will know the trial helped.

That missing statement is the operating thesis.

A useful operating thesis sounds like this: routine order-status calls can be handled from approved facts and documented automatically, while exceptions arrive in front of an experienced CSR with the context required to act.

That can be tested. It names the work, the boundary, the human role, and the expected change. "We are piloting an AI phone agent" names a technology and leaves the operation blank.

How We Built an AI CSR That Escalates to Humans Instead of Replacing Them

· 11 min read
Trevor Grant
Builder in Chief

The client's customer-service problem did not begin with a model.

It began with a familiar staffing cycle: hire for an entry-level remote CSR role, spend experienced supervisor time on training, discover that the person or the job was a poor fit, and start over. Even when a hire worked out, the team still had to keep routine answers consistent across shifts, people, and systems.

The common failure modes were not mysterious. Attendance and punctuality problems hurt a tightly scheduled call queue. Some new hires underestimated the intensity of back-to-back calls, upset customers, repetitive work, and constant measurement. Others became defensive with frustrated callers, improvised outside policy, missed important details, or left weak documentation for the next person.

The role also required more systems work than "answer the phone" suggests. A representative might need to listen, speak, type, search a knowledge base, inspect a customer record, update a ticket, and follow a policy at the same time. Some hires struggled with that combination. Others repeated mistakes after coaching, worked from unreliable or distracting home environments, wrote unclear follow-up messages, or left a few weeks after training.

Human Review Is Part of the System

· 7 min read
Trevor Grant
Builder in Chief

The agent prepares the recommendation, and a person approves it.

That sentence is often delivered like an apology. The system is useful, the explanation goes, but it still needs human review. The implication is that review is scaffolding: something tolerated until the model improves enough to remove the person from the loop.

That is the wrong design goal.

Surface Is Not Operations

· 5 min read
Trevor Grant
Builder in Chief

There is a particular satisfaction in making a business look real on the internet.

The name is settled. The copy explains the offer. The photographs line up. The site loads, the links work, and the rough idea that had been living in notes and conversations finally has a public address.

That moment matters. It is also easy to mistake it for more progress than it is.

Agent Demos Need Interfaces

· 5 min read
Trevor Grant
Builder in Chief

The agent calls a search tool, reads a few documents, updates a record, and produces a plausible answer. The steps appear one after another in the terminal. The room gets quiet. For a moment, it feels like the hard part is over.

Then someone asks where their team would click.

When Not to Build an Agent

· 6 min read
Trevor Grant
Builder in Chief

Sometimes the right answer is not an agent.

The workflow may be painful. The team may be losing hours to it. A model may even be capable of performing the most visible step. None of that guarantees that an agent is the best first intervention.

The Requested Tool Is Not Always the Bottleneck

· 5 min read
Trevor Grant
Builder in Chief

"Can we automate the recognition step?"

It was a reasonable request. A civic reporting workflow included manual license plate review. If software could read the plate from an image, return the detected text, and spare someone the repetitive inspection, the team should have more capacity.

The recognition service was technically plausible. It was also not the whole job.

Bring Real Examples, Not Abstract Requirements

· 6 min read
Trevor Grant
Builder in Chief

"We need something that handles this."

That sentence can start a useful conversation, but it cannot scope useful work. It points toward pain, not evidence. It says the current process is frustrating, slow, inconsistent, or too dependent on one person. That may all be true. But before anyone can recommend an agent, a software tool, a workflow change, or no build at all, the work has to become visible.