Lab note

How AI agents will interact with business software

There are four routes into a business system, and they are strictly ordered by preference. Most disappointment comes from taking the wrong one.

NEOB Research Published 5 min read
RouteReliabilityWhen it applies
Purpose-built API / toolHighThe system has an API and you can shape the tool around the business rules
Protocol integration (e.g. MCP)HighThe vendor or a community exposes a server
UI automation / browser agentLow to moderateNo API exists and the process is unavoidable
Human in the loopHighestIrreversible, regulated, or rare enough not to be worth automating
In order of preference. Take the highest row that is available.

The ordering is not aesthetic. Each step down loses a guarantee: an API has a contract, a protocol has a schema, a UI has neither and can change overnight without notice.

The tempting mistake

UI automation demos brilliantly. An agent filling in a supplier portal looks like the future. In our own testing, read-only tasks held up and write tasks did not - the failure was not loud errors but occasional plausible-and-wrong entries with no signal that anything had gone wrong.

What the fourth row is for

Human-in-the-loop is not a fallback for weak automation. It is the correct design for actions that are irreversible, legally significant, or so rare that the failure cost dominates the labour saved. An agent that prepares the work and asks for a confirmation is usually the highest-value version of the system, not a compromised one.

The prediction worth making: as more vendors expose protocol servers, row three shrinks. It will not vanish - authorities and legacy portals move slowly - but the fraction of business software reachable through a contract rather than through pixels is growing.