Preparing an AI agent project: the checklist to stay on schedule

Most delays in an AI agent project do not come from technology. They come from an access right that does not arrive, examples that are too clean, a decision that does not get made. Here is the list of what to gather before starting.

1. Access to the tools concerned

For each tool the agent has to read or change (email, CRM, accounting software, ERP, shared folders):

• who can grant access;
• what level: read only, or write.

For testing, you have nothing to provide: we organise it, in your software’s test space when the provider offers one, otherwise in observation mode.

Granting access sometimes takes days: a publisher, an IT department or a provider has to be asked. Start it first.

2. Real and representative examples

Not three perfect files: a sample that looks like everyday work.

• routine cases, in numbers;
• difficult cases: a badly scanned document, an unknown customer, an amount that does not match;
• rare but costly exceptions.

A process is won or lost on its exceptions, not on its routine case.

3. The rules, even unwritten ones

What the person applies without thinking: deadlines, thresholds, tolerances, the tone used with a given type of customer. Scoping is there to write them down. If they only exist in one person’s head, plan time with them.

4. An available contact

About two hours a week, during the project: the person who knows the work and its exceptions. They answer questions, approve behaviours, test on their cases.

5. A decision-maker who can settle questions

Trade-offs come quickly: does the agent handle this case or pass it on? Does this reply go out on its own or after approval? With a decision-maker who can settle a question when one comes up, nothing is left hanging and the project keeps to its deadlines. A decision committee, on the other hand, lengthens every one of them.

6. The indicator and its starting point

Before starting: what will be measured (time spent, processing time, number of corrections) and today’s figure. See How to calculate the return on investment of an AI agent.

What is not needed

• Fifty pages of specifications: a description of the real work is enough.
• An overhaul of your tools: the agent works in the ones you have. See Connecting an AI agent to your existing tools.
• Technical skills on your side: they are on ours.

The list, in short

To gather	Why
Access rights, before the start	first cause of delay
Real examples, exceptions included	the agent is checked on them
The rules applied	otherwise the agent gives answers that are right for everyone, and wrong for you
A contact, two hours a week	they know the exceptions
A decision-maker who can settle questions	nothing is left hanging
The indicator and its starting figure	without it, no gain can be demonstrated

These are exactly the conditions written into each of our proposals: How we work with you.