The template changed. The old skill goes, and what used it is checked.
Step 1 of 4: In use
A stale skill removed, its dependants checked.
A stale or wrong skill is removed, and what depended on it is checked again.
Persistent intelligence. It runs On an authorised request.
The next release notes use the new template.
With the stale skill gone, nothing goes out in last year’s style. The notes go to your AI with the new template until a new skill is proven.
Step 1 of 3: Release 4.2
Release 4.2 needs its notes.
From the day it went stale to the day it was replaced.
A skill can go stale without failing outright. Once someone notices, it is removed, and what depended on it is checked straight away.
Step 1 of 5: Proven
In January, the release-notes skill is proven and starts writing every release’s notes.
Each thing that relied on it is checked on its own.
Everything that used the skill is checked again: what still holds carries on, and what relied on the old style waits for a new skill.
Step 1 of 3: The changelog
The monthly changelog never needed the old style, so it carries on unchanged.
Adapts your model without retraining.
Your model answers as if it had been trained on your work, its weights stay as they are, and the fit moves with you to a new model.
- Exactly what your model is givenYour model answers as if it had been trained on this work, without being retrained.
- Which context makes a differenceOnly context that improves your model’s answers is sent, so you stop paying for the rest.
- How your model is adapted, per work areaEach work area shows how your model is being fitted to it, so nothing changes unseen.
- Your team sets the persona, rules and formatYour team decides the persona, rules, sources and answer format your model works with.
- A proven answer becomes a skillA proven answer becomes a skill your model can use, with no retraining.
- A stale skill removed, its dependants checkedA stale or wrong skill is removed, and what depended on it is checked again.
- Every skill adapting your modelEvery skill shaping your model’s answers can be traced to where it came from.
See it on your own work.
From your own assistant to every agent your company runs, a pilot puts Duplex on your own work, with the measures agreed before it begins.