AI Personalizations for Lawyers: Teach Your AI How You Work
Nov 13, 2026 · 8 min · 8 segments
This episode of Attorney at Work Today is brought to you by Answering Legal. Adapted from an article by…
Nov 13, 2026 · 8 min · 8 segments
This episode of Attorney at Work Today is brought to you by Answering Legal. Adapted from an article by…
That repetition is optional.
The leading productivity AI tools now include personalization features that let you provide standing guidance about who you are, how you work, and how you want the tool to respond.
Teach the AI the durable context you should not have to retype in every prompt.
Personalization will not make an AI tool infallible, and it does not replace a well-written prompt.
It can, however, make everyday results more consistent and reduce the amount of corrective editing you do afterward.
But when we talk about personalization, it helps to separate it into two buckets.
First, there's standing instructions.
Directions you deliberately provide about tone, format, process, and guardrails.
Think, use headings and bullets when they improve readability, or if important information is missing, ask before making assumptions.
Second is memory or persistent context.
Information the tool can carry from one conversation to another, such as your role, practice area, jurisdiction, recurring audience, or long-running projects.
A useful shorthand is, instructions describe how you want the AI to work.
Memory describes what you want it to know.
The line is not perfectly sharp, and the products implement it differently, but the distinction is practical.
That repetition is optional.
The leading productivity AI tools now include personalization features that let you provide standing guidance about who you are, how you work, and how you want the tool to respond.
Teach the AI the durable context you should not have to retype in every prompt.
Personalization will not make an AI tool infallible, and it does not replace a well-written prompt.
It can, however, make everyday results more consistent and reduce the amount of corrective editing you do afterward.
But when we talk about personalization, it helps to separate it into two buckets.
First, there's standing instructions.
Directions you deliberately provide about tone, format, process, and guardrails.
Think, use headings and bullets when they improve readability, or if important information is missing, ask before making assumptions.
Second is memory or persistent context.
Information the tool can carry from one conversation to another, such as your role, practice area, jurisdiction, recurring audience, or long-running projects.
A useful shorthand is, instructions describe how you want the AI to work.
Memory describes what you want it to know.
The line is not perfectly sharp, and the products implement it differently, but the distinction is practical.
The rest of this transcript — segmented and speaker-labeled, so you land on the exact moment something was said
Search every transcript — by keyword, by phrase, or by meaning, across every show Radar indexes
Trends — what is surging across podcasts, measured against its own baseline
Alerts — when a name you follow appears in a newly indexed episode
No account is needed to search Radar.
