Think Build Implement Repeat
London, UK +44 7367 067226
WhatsApp FOLLOW f in X
AI Integration

Your First 30 Days on an AI Project

Last updated:

Why the first month of an AI project is different

We have described the first month of an ordinary software engagement in what happens when you hire SpiderHunts. An AI project follows the same principles of fixed scope and visible progress, but the first month has a different priority.

In a normal build, the main uncertainty is effort. In an AI build, the main uncertainty is whether the approach works well enough on your data at all. So the first 30 days are arranged to answer that question as cheaply as possible, before anyone spends serious money on screens, integrations and polish.

Days 1 to 5: real examples and real access

The most valuable thing you can give us in the first week is a pile of real, messy examples of the task. Not the tidy ones chosen for a presentation. The scanned invoice at an angle, the customer email written in three languages, the order with handwritten amendments.

  • Several hundred real examples of the input, anonymised where necessary
  • The correct output for as many as you have, such as the order as it was eventually keyed
  • Read access to the systems the AI will eventually read from or write to
  • An hour with the person who does the task, sharing their screen
  • Your data protection lead's requirements, so the design fits them from the start

Access is the item most likely to slip. Start arranging it the day the project is agreed.

Days 6 to 12: the evaluation set and the baseline

Before we build anything clever, we build the test. With the person who knows the task, we assemble an evaluation set: a few hundred real cases with agreed correct answers, deliberately including the difficult ones. Every version of the system from now on is scored against it.

At the same time we measure the current process. How long does a case take? How many errors reach the next step? That baseline is what the AI has to beat, and it is written down now so nobody can move the goalposts later, including us.

The evaluation set is the most important thing built in the first month. The prototype is replaceable. The test is not.

Days 13 to 25: a working slice on real data

Now we build. The goal is a thin, working version of the core task running against your real examples. For a document extraction project, that means documents in, structured fields out, with a confidence score per field. For a support triage feature, tickets in, categories and draft replies out. Our AI integration service describes this as a proof of concept on real data, typically within two to three weeks.

It is deliberately unpolished. There may be no proper interface, just results in a spreadsheet or a simple review screen. What matters is the score on the evaluation set, the cost per case at realistic volume, and the list of cases it gets wrong. We share those results as they improve, not only at the end.

Days 26 to 30: the go or no-go review

The month ends with a review meeting and a short written report. It sets out what the system achieved on the evaluation set, how that compares with the baseline, the estimated running cost, which kinds of cases it struggles with, and our recommendation.

What the evidence showsWhat it usually meansRecommended next step
Strong results on most cases, clear failure patternsThe approach worksProceed to the production build with review routing for hard cases
Good results on some case types onlyWorks for part of the taskNarrow the scope to the cases that work
Results depend on data you do not captureThe data is the constraintFix data capture first, revisit later
Results close to or below the baselineAI is not the right tool hereStop, or solve with conventional software

We would much rather recommend stopping at day 30 than at month four. So would you.

What we need from you each week

  1. Week one: examples, access and an hour with the person who does the task
  2. Week two: a few hours from that person to agree correct answers for difficult cases
  3. Week three: quick answers when we find cases where even your team disagree on the right output
  4. Week four: the decision-maker at the review meeting

The third item surprises people. Building an evaluation set often reveals that two experienced staff handle the same case differently. Settling that is valuable in its own right, and the AI cannot be more consistent than the rule it is given.

Common surprises in month one

The data is messier than anyone described, usually in ways that matter. A small number of case types account for most of the difficulty. The running cost is either much lower than feared or needs a routing design to keep it sensible. And the person who does the task often has ideas for improvement that are worth more than the original brief. If you want a view of the whole engagement beyond this first month, what SpiderHunts brings to machine learning projects covers what you own at the end.

Frequently asked questions

How long before we see a working AI prototype?

Typically within two to three weeks of access and examples being available. It will be a working slice on real data rather than a finished product, which is exactly what you need to decide whether to continue.

How many examples do we need to start an AI project?

A few hundred real examples is a good starting point for most extraction, classification and drafting tasks, ideally with the correct outputs. Fewer can work for a first look, but the evaluation becomes less reliable.

What happens if the first month shows AI will not work?

We tell you in the written review and recommend the alternative, which might be conventional software, better data capture or simply not proceeding. The cost of finding out is limited to the first phase.

Do we need to prepare a detailed specification before the first month?

No. A clear description of the task, real examples and access to the right people are far more useful. The specification for the production build is written using what the first month reveals.

Is our data safe during the first month?

Yes. An NDA is in place before examples are shared, data is handled under the terms agreed for your project, and personal details are redacted or anonymised where the task allows.

Keep reading

Ready to find out if your AI idea survives real data?

Tell us the task and send a handful of real examples. We will tell you what the first month would test and what you would need to have ready.

Book a free 30-minute call Get a project estimate WhatsApp us

Related services

What we build for problems like this one

AI IntegrationEnterprise AIAI Agents