card file · JAI-63
ai solutions / designing solutions
card 63 of 73
Updates & Maintenance
what is needed to keep your ai solution running smoothly
This card covers what it takes to keep your AI tool working after launch. Models change, data ages, and needs shift, so a tool is not finished when it ships. Naming who maintains it and how often prevents a useful tool from quietly breaking down.
Questions to explore
// use these as prompts in a workshop or on your own. There are no right answers.
- Who is responsible for keeping this tool working once the build team moves on?
- How often does the data or model behind it need refreshing?
- What signs would tell you the tool's quality is slipping over time?
- How will you handle a model update that changes the tool's output?
- What is the plan if the person who built it leaves the newsroom?
Things to consider
- A tool with no owner tends to drift until it no longer works.
- Budget time for upkeep, not only for the initial build.
- Write down how it works so others can maintain it later.
using this card
Pull Updates & Maintenance when it is relevant and set it aside when it is not. Pair it with the other AI Solutions cards, lay them out on a table, and use the questions above to get everyone on the same page. Capture what you discuss on sticky notes or in a shared doc.
More AI Solutions cards
~/library/ai-solutions
JAI-56
Interface
how users interact with your ai solution and its visual design
JAI-57
Features
the functionalities and parts you want your ai solution to have
JAI-58
Users
who will be the users of your ai solution
JAI-59
Input
data your ai solution needs to function
JAI-60
Output
what your ai solution delivers
JAI-61
AI Models
what llms and machine learning models work for your ai solution