What this covers
A prototype for one writing, summarising or extraction task inside your app, tested on examples you approve.
Tools
Model APIs, TypeScript, Streaming UI, Evaluation sets. The exact stack depends on what you already use.
Where it helps
- Drafting a brief from form inputs
- Summarising a long customer conversation
- Suggesting content for a person to review
We agree what “done” means before work starts.
What you get
- A working prototype for one writing, summary or extraction task
- Test results on examples you approved
- Source code, setup notes and an agreed definition of done
The final list depends on the agreed scope. The estimate and schedule follow from it.
Data and security
We check how long the provider keeps data, what inputs are allowed, what gets redacted, and how output is handled. Keys stay on the server, and model output is never trusted blindly.
How I work on it
Collect examples, build a small prototype, compare it against what “good” looks like, add review and error states, then try it with a few approved users.
What helps me get started
- A short description of the process and who uses it.
- Sample data, any API documents, and what access is available.
- How much it will be used, who reviews the work, and your release priorities.
A short outline is enough for a first call. Please send sample data, not real records or passwords.
Related services
Read the planning guideQuestions
Can generated content be published automatically?
We start with a person reviewing everything. Automatic publishing needs its own scope, testing, permission checks and a way to undo mistakes.
How do you price the work?
I look at the workflow, the systems involved, the access needed and what “done” means, then send an estimate. If there are big unknowns, we start with a short discovery or a prototype.