Mental models, prompting, verification, personal systems

Personal Knowledge Systems and Custom Assistants

Custom assistants become useful when they are grounded in the user work context: documents, preferences, recurring tasks, tone, constraints, and examples. This module teaches how to design assistants as focused tools rather than vague all-purpose companions.

Deep dive summary

What this module actually teaches.

Passage 1Custom assistants become useful when they are grounded in the user work context: documents, preferences, recurring tasks, tone, constraints, and examples. This module teaches how to design assistants as focused tools rather than vague all-purpose companions.

Passage 2Learners structure knowledge bases, instruction files, reusable workflows, and review habits. They also learn the limits of uploaded context, the importance of source quality, and how to avoid mixing sensitive personal or organizational information carelessly.

Passage 3The module ends with a personal assistant blueprint. Students define what the assistant should do, what it should never do, what sources it may use, and how its outputs should be checked.

Learning operating system

Module prerequisites, concepts, outcomes, and artifacts

Prerequisites

  • Prompting fundamentals
  • basic file organization

Key concepts

  • custom assistants
  • knowledge bases
  • instruction files
  • source quality
  • assistant boundaries
  • review habits

Target audience

  • Professionals and teams creating custom AI assistants for repeated daily tasks.

Outcomes

  • Design custom assistants with clear scope and source boundaries
  • Organize knowledge so AI tools can use it effectively
  • Create review practices for assistant-generated work

Artifacts

  • custom assistant blueprint
  • knowledge source inventory
  • assistant boundary checklist

Code example

Real patterns, ready to copy into your editor.

A code reference card that frames this module's concepts in real syntax. Copy any example to study it or adapt it directly in your own editor.

Copy-ready snippets
curriculum/fd-personal-knowledge-assistants.tsts
1type ModuleBrief = {2  track: string;3  difficulty: string;4  keyConcepts: string[];5  reviewGate: 'human-review-required';6};7 8export const moduleBrief: ModuleBrief = {9  track: 'Foundations',10  difficulty: 'Intermediate',11  keyConcepts: [12    'custom assistants',13    'knowledge bases',14    'instruction files',15    'source quality',16    'assistant boundaries',17  ],18  reviewGate: 'human-review-required',19};