AI is a normal part of how we build software now. It generates boilerplate quickly, helps write tests, suggests implementations and takes a lot of mechanical work off the table. A good developer using AI tools moves noticeably faster than one who isn’t, and that means clients get more done for the same budget.
We use those tools throughout our work at Logicc. What we don’t do is treat their output as finished. Anything AI produces is a first draft, and it gets reviewed by an engineer who can tell the difference between code that looks right and code that will actually hold up in a live supply chain environment.
That review matters more in supply chain than almost anywhere else.
Why supply chain makes this harder
Supply chain is an industry built on exceptions. Carrier APIs that behave differently from their own documentation. Customs rules with carve-outs that apply only to specific commodity codes, certain routes, or shipments above a particular value. Warehouse systems that handle 99% of cases correctly and fail in a very specific way on a Monday morning when a particular combination of order types hits the pick queue.
These aren’t hypothetical. They’re the kind of thing that turns up in production, usually at the worst possible time, because no specification captured them. They exist because real operations have been accumulating exceptions and workarounds for decades, and the rules often live in experienced people’s heads rather than in any formal record.
AI tools work from patterns. They don’t know about the carrier that sends malformed tracking responses on bank holidays, the customs authority that wants a field formatted differently from the standard, or the client whose warehouse system has its own interpretation of a palletisation code. An engineer who has spent years in this space does know these things, or knows enough to ask the right questions and spot when something doesn’t look right.
What experience adds
When people talk about industry experience, they usually mean time served. The more useful definition is exposure to failure.
An experienced supply chain developer has seen systems go down before a critical shipment. They’ve debugged carrier integrations at 2am. They’ve watched a well-intentioned change to an order routing rule cause a week of delivery exceptions because of a combination of conditions nobody anticipated. They’ve sat with operations teams explaining why the software is doing something technically correct that causes a real problem on the warehouse floor.
That experience shapes how they work: what questions to ask, where to look for risk, and how to tell a client that something will work in theory but cause problems in practice. AI tools make that person faster. They don’t replace what they know.
How it works day to day
We use AI for generating code, writing documentation, and building and running tests. It speeds up the routine parts of a job, so more of the team’s time goes on the parts that need thought.
Decisions about architecture, where the risk sits in a system, and how software should behave when things don’t go to plan are made by engineers who know this domain. Code generated with AI is reviewed by a developer before it goes anywhere near your systems. Tests are checked against the edge cases the system actually needs to handle, not just the obvious ones. The tools do a lot of the mechanical work, and a person with relevant experience is responsible for what ships.
It all sits inside the same managed process as the rest of our work, and your code and data are handled under the same ISO 27001 controls.
What to ask a development partner
Most development partners use AI now, and they should. The useful question is how. Ask what gets reviewed by a person, who does the reviewing, and how much experience they have with systems like yours. If the answer is that AI means they don’t need experienced developers any more, that’s worth questioning.
The value of years in supply chain software isn’t in typing code. It’s in knowing what the code needs to do, what it will run into in the real world, and what to do when it meets something it wasn’t designed for. AI makes experienced engineers more productive, and that’s how we use it.