Generative AI development
Generation with a human still holding the pen.
Generating text, images or code is cheap; being accountable for what was generated is not. The useful systems put a person in the loop at the point where being wrong would cost something.
Overview
Generative AI, the way we do it
Generative tools are genuinely good at first drafts, summaries, variations and the boring middle of a process. They are poor at being solely responsible for anything a customer or a regulator will read. The design question is always where the human sits, not whether the model is clever enough.
We build the workflow rather than the demo: what gets generated, who checks it, what happens when it is wrong, and how you would know. That is unglamorous and it is the part that determines whether the thing survives contact with your business.
What's included
What you actually get
- Drafting, summarising and variation, where a person still approves the output
- A defined review step wherever being wrong would cost something
- Built into the systems your team already uses, not a separate tool to remember
- Your content and prompts kept out of anyone else's training data
- Measured on whether it saved time, not on whether the demo impressed
How we work
Five steps, no surprises
- 01
We talk
A call or a WhatsApp thread. You tell us what is not working; we tell you honestly whether we are the right people.
- 02
We scope it
A written plan with what you get, what it costs and how long it takes. Fixed, so there are no surprises later.
- 03
We build it
You see it as it goes, not at the end. Changes are cheap while it is still being built.
- 04
We put it live
On infrastructure we set up and secure, tested before the launch date.
- 05
We keep it running
Updates, monitoring and someone who answers. Most clients stay on a monthly agreement.
Questions
About generative ai
Is this safe for customer-facing content?
Only with a review step, and we will design one in rather than leave it to discipline. Fully autonomous generation in front of customers is a risk most businesses should not take yet.
Will our content be used to train a model?
Not under the arrangements we set up. Either the model runs on infrastructure we manage, or the provider is contractually barred from training on your content.
Has BitBee shipped generative AI?
Not among the work on this site. We would rather say that than let a page imply a case study we do not have.
Also
Related work
- Quality AssuranceFind it before your customers do.
- UX DesignWork out what it should do before anyone builds it.
- UI DesignScreens people can use without being trained.
- Design SystemsOne set of rules, so the tenth screen looks like the first.
- Mobile ApplicationsApps people keep on the first screen.
- iOSiPhone apps built the way Apple expects.
- AndroidAndroid apps that work on the phones people actually own.
- FlutterFlutter, when one team has to cover both stores.
- AIAI that does one job, properly.
- Machine LearningModels that earn their place in the business.
- Data ScienceAnswers from the data you already have.
- LLMsLanguage models, kept on a short leash.
- PythonPython, for the work that has to be read as well as run.
- Back-EndWhere an order becomes an order.
- DatabaseThe part of your system that is hardest to fix later.
- Node.jsNode.js, for the systems that have to answer quickly.
- GoGo, where it has to be fast and stay simple.
- .NET.NET, for the systems a business runs on.
- JavaJava, for systems measured in decades.
- Front-EndThe half of your product people actually see.
- Web DevelopmentCompany sites, customer portals, and web systems that hold up.
- ReactReact, built so the next team can still work on it.
- AngularAngular, for systems that have to last.
Tell us what you have in mind.
An engineer reads your message and replies to you directly.
Talk to us