Think Build Implement Repeat
London, UK +44 7367 067226
WhatsApp FOLLOW f in X
Python & Django

Adding AI to a System Already in Use

Last updated:

Three things that fit

  1. Classification — routing, categorising, prioritising
  2. Extraction — documents and free text into structured fields
  3. Drafting — replies and summaries for a person to review
All three produce output a person can check in seconds, which is what makes them safe to add to a system people already depend on.

Call from a task, not a view

Model calls are slow and occasionally fail. Making one during a request means a user waiting and a request that sometimes times out.

  • Queue the work, process it, store the result
  • The interface shows pending, then the result
  • Retries handled by the queue
  • A provider outage delays rather than breaks

Store it as data on the model

The output should land as structured fields with a confidence value, not be regenerated each time it is displayed. That makes it queryable, auditable, correctable and cheap.

Add fields for the model version and prompt version too, so an output can be explained months later.

Keep the human path

RequirementWhy
Review queue for uncertain outputErrors reach a person
In-place correctionFixing must be easy
Corrections captured as dataThey improve the system
A switch to disable the AI stepWhen something goes wrong
Original input preservedReprocessing and disputes

Controls

A hard daily cost cap, a per-user cap, cost per item tracked, and prompts in configuration rather than in code so they can be changed and rolled back.

None of that is difficult, and all of it is what makes an AI feature safe to run in a system the business depends on.

Frequently asked questions

Does this need a rewrite?

No. It is usually a background task, a few model fields and a review screen alongside what you already have.

How long to add?

Four to eight weeks for a first capability including the evaluation set and review interface.

What about our data leaving?

A decision to make deliberately: which provider, which region, what retention, and whether to redact first.

What if it gets things wrong?

It will sometimes. That is what confidence routing and the review queue are for.

Keep reading

Have a Django system that could classify or extract automatically?

Tell us what people currently do by hand and we will tell you whether it fits.

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

Related services

What we build for problems like this one

Custom Software DevelopmentWeb DevelopmentMachine Learning