Mastering Knowledge Work with AI

Course code: PT1019

Context Engineering for Business Teams already answer from a policy, an account file, a project folder. What slows the work down is starting from a blank chat and hoping the model remembers the right documents. This course is about the material you put in front of the model before you ask: the files, the rules, and a short note on how your team works. Over two days, participants build a folder pack for a recurring job, get an answer that stays inside those files, and leave a way for the next person to run it. Context, in this course, means that pack. People have heard the term RAG, a system that searches a library for you. Here the team chooses the documents and hands them over. If a folder is no longer enough, the last module is the request you would actually send to engineering. The course is for people who work from documents and are being asked whether the team can do this inside the files it already has. No coding.

Request a Consultant

About This Course

Duration: 2 Days Skills Gained

By the end of this course, participants will be able to:

  • Brief the model with the job, the files it may use, and a picture of a good answer

  • Assemble a small set of documents and keep the answer inside them, with gaps written down

  • Finish a multi-document task from a folder, and say whether that folder is enough

  • Write a short team note with an owner and a date it should be reviewed

  • Package the pack so a teammate can run the same job next week

  • State a clear request when the work has outgrown a folder: volume, freshness, who may see it, and how the answer will be checked

Who Can Benefit

This course is designed for:

  • Analysts, project managers, and operations leads who answer questions from documents

  • Team leads who want one shared way to brief the model on a policy, an account, or a project

  • People being asked about file upload, project folders, and whether the team needs a search system

Prerequisites

Participants should enter this course with:

  • Familiarity using a chat tool on workplace text

  • Comfort uploading or pasting a document in a browser

  • No coding background required

Organizational Objectives

This course assists organizations to:

  • Raise the quality of document answers by sharing one way to brief the model

  • Give a plain answer to whether a job can be done inside a folder of the team’s own files

  • Make a request to engineering specific when a folder is no longer enough

  • Keep a shared pack current, with an owner and a review date, instead of a prompt that lives in one person’s chat

Software

A modern web browser and an internet connection. The lab accepts a file upload or a pasted pack. No database and no administrator setup. Microsoft 365, Google Workspace, or the equivalent already in use is enough for the folder work.

You'll Learn

Module 1 — What You Hand Over Before You Ask

By the end of this module, you will be able to say what the model is allowed to see, and what a good answer looks like.

  • The job, the reader, and the files

  • The rules: what to refuse, what tone to use, and what to do when two documents disagree

  • Why a careful question still fails when the files are missing or out of date

  • A cover sheet: job, files, and the shape of a good answer

Hands-on Lab: Write the cover sheet for one recurring job. Mark which lines change every time the job is run.

Module 2 — Answers That Stay Inside the Files

By the end of this module, you will be able to assemble a small set of files and keep the answer inside them.

  • What to include, what to leave out, and what to redact

  • Order: the rule first, then the case, then the question

  • Every material claim points at a file. Gaps go on a “not in the documents” list

  • What to do when two documents disagree

Hands-on Lab: From policy and case files provided in class, produce a question-and-answer page with the sources named and the gaps listed.

Module 3 — Working Inside a Folder

By the end of this module, you will be able to finish a multi-document job from a folder, and say whether that is enough.

  • Upload, a project space, or a set of links: three ways to hand over a folder

  • Extract, compare, and recommend, on documents and a small table

  • When a folder is enough for the size of the set, how fresh it is, and who will read the answer

  • The five lines you would send engineering if it is not: how many documents, how often they change, who may see them, what good looks like, and who owns the answer

Hands-on Lab: Finish a three-document folder task. Write five lines on whether a folder is enough, and why.

Module 4 — What the Team Keeps

By the end of this module, you will be able to decide what is saved, what expires, and who owns it.

  • What lives for one session, and what the team should keep

  • A short note: owner, review date, and what it replaces

  • A shared word list, a decision log, and a do-not-use list

  • What must stay out of a shared pack

Hands-on Lab: Turn the day’s pack into a one-page team note with an owner and a review date.

Module 5 — A Pack Someone Else Can Run

By the end of this module, you will be able to wrap the pack so a teammate can run the job without you.

  • The goal, the steps, and the point where a person decides

  • Three checks before anyone trusts a repeated answer

  • When the pack should become a saved instruction in the tool the team already uses

  • What to ask for if the folder has been outgrown, stated as volume, freshness, permission, and the check

Hands-on Lab: Package the folder, the cover sheet, and a one-page run note. Another person in the room should be able to run the job from it.

Request a Consultant

Speak with a Learning Consultant