---
title: "Applied AI for business processes | B&C Associates"
description: "Language models applied to a named task: reading documents, classifying enquiries, answering from your own material. With an honest account of what the model gets wrong."
language: "en"
canonical: "https://bcass.net/services/ai"
---

# Applied AI

Most of what is sold as AI is a demonstration. What makes a difference in a business is narrower and duller: a model reading the documents nobody wants to read, and a person approving the result.

## Where models earn their cost

- **Document processing**: Invoices, delivery notes, contracts, technical datasheets. Extracting the fields you need, flagging what it is unsure about, and handing the uncertain cases to a person instead of guessing.
- **Answering from your own material**: Retrieval over your documentation, past projects, product data or support history, with the source of each answer shown so somebody can check it.
- **Classification and routing**: Sorting incoming enquiries, tickets or applications into the right queue with the right priority, which is a task models do well and people find tedious.
- **Drafting**: A first version of a quotation, a reply, a product description or a report, produced from your own data and your own past output, for a person to correct rather than write.
- **Agents with an approval step**: A sequence of actions the model completes on its own, with a defined stopping point where a person signs off before anything irreversible happens.
- **An assessment before you spend**: A short engagement that tests the idea against your real data and reports the accuracy you would actually get. Sometimes that report says do not build this.

## How an AI engagement runs

1. **Find the task** (Week 1)
   We look for a task with a clear input, a clear output and a measurable error. Tasks without those three are where AI projects run for a year and produce a slide deck.
   You get: A named task, a success threshold, and a sample of real data to test against.

2. **Measure before building** (Weeks 2 to 3)
   We run the task against your sample and report the accuracy, the cost per item and the failure modes. You see the numbers before committing to a build.
   You get: A written evaluation with accuracy figures and the cases it gets wrong.

3. **Build with a human in the path** (Weeks 4 to 8)
   The system goes into production with a review step, a confidence threshold, and a record of every decision it made. Nothing consequential happens without a person able to see it.
   You get: A running system, an audit log, and the review interface for your team.

4. **Watch the error rate** (Ongoing)
   Model behaviour drifts and so does your data. Accuracy is monitored against fresh samples, and the review threshold moves when the evidence says it should.
   You get: A monitoring dashboard and a monthly accuracy report.

## What we will tell you not to do

- A chatbot on the website because competitors have one. It will annoy your customers.
- Replacing a rule that already works. If an if-statement is correct every time, a model is a downgrade.
- Any workflow where a wrong answer is expensive and no person reviews the output.
- Training your own model when a general one plus your documents does the job for a fraction of the cost.

## Name the task and we will tell you if a model can do it

Describe the work you think AI could take over. The reply will include the part that will not work, before the part that will.

[Start a conversation](/contact)