> ## Documentation Index
> Fetch the complete documentation index at: https://nmem.guoxudong.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Bring a source

> Keep a primary source in Library so you can use it now and reread it in a future task.

<div className="course-meta" aria-label="Lesson information">
  <span><Icon icon="book-open" /> AI Now · Lesson 2 / 5</span>
  <span><Icon icon="clock-3" /> \~5 min</span>
  <span><Icon icon="user-round" /> Intermediate</span>
</div>

<div className="learning-stages learning-stages-progress" aria-label="Course progress">
  <div className="learning-stage learning-stage-done">
    <span className="learning-stage-mark" aria-hidden="true" />

    <span className="learning-stage-title">Question</span>
  </div>

  <div className="learning-stage learning-stage-active" aria-current="step">
    <span className="learning-stage-mark" aria-hidden="true" />

    <span className="learning-stage-title">Source</span>
  </div>

  <div className="learning-stage">
    <span className="learning-stage-mark" aria-hidden="true" />

    <span className="learning-stage-title">Evidence</span>
  </div>

  <div className="learning-stage">
    <span className="learning-stage-mark" aria-hidden="true" />

    <span className="learning-stage-title">Investigate</span>
  </div>

  <div className="learning-stage">
    <span className="learning-stage-mark" aria-hidden="true" />

    <span className="learning-stage-title">Save</span>
  </div>
</div>

Add one primary source to the AI Now task in Nowledge Mem. Use its exact wording to check the question you scoped in lesson 1.

## What you'll accomplish

<Check>
  You'll keep one source in Library and verify that AI Now can read it alongside your saved knowledge.
</Check>

## Learn with the simulation

On desktop, the simulation opens automatically when you enter this lesson. Follow the popup hints to send a request, read its reply, and check the result. If you close it, click **Start the simulation** under [Your turn](#your-turn) to reopen it. Each lesson prepares its fictional Atlas materials; no model setup is needed.

<Note>
  The simulation runs locally with preset replies. It does not call AI or search the web, and refreshing resets the practice. On mobile, read the steps first and use a desktop browser for the interactive exercise.
</Note>

## Before practising in the real app

Continue the lesson 1 conversation with its checked context summary. Choose a source you can use with your configured AI provider.

## Your turn

Follow the hints in the automatically opened simulation. After practising, use the steps below to repeat the workflow with your own material in Nowledge Mem.

<script src="/course-playground-guide.js?v=26" defer />

<div className="course-playground-workflow" data-course-playground-guide="" data-course-guide-autostart="true" data-course-guide-scenario="ai-source" data-course-guide-current="1" data-course-playground-open="false" data-course-guide-replay-label="Practise again" data-course-guide-close-label="Close simulation" data-course-guide-mini-label="Playground" data-course-guide-fill-label="Fill the example" data-course-guide-done-message="Lesson complete. Continue to the next lesson, or try it in Nowledge Mem." data-course-guide-open-mem-label="Open Nowledge Mem" data-course-guide-confirm-label="Next lesson" data-course-guide-confirm-href="/ai-now/ask-for-an-evidence-brief#simulation" data-course-guide-mem-url="https://mem.nowledge.co" data-course-guide-hint-1="Open Library. The fictional interview file is ready to import." data-course-guide-hint-2="Import the sample file and wait for indexing." data-course-guide-hint-3="Open the Searchable document." data-course-guide-hint-4="Read Interview B, then return to Library." data-course-guide-hint-5="Return to the same AI Now task. The sample conversation from lesson 1 is already loaded." data-course-guide-hint-6="Ask AI Now to read the interview file." data-course-guide-hint-7="Send the source-reading request." data-course-guide-hint-8="Open the cited source and check Interview B." data-course-guide-hint-9="Lesson complete. Continue to the next lesson, or try it in Nowledge Mem." data-course-guide-fillable-6="Find and read atlas-planning-interviews.md in Library alongside the Atlas planning memories already found. First identify the document and its sections. Then list statements relevant to holding one cross-team planning review of the next twelve months, citing the interview heading for each. Separate what the notes say from your interpretation. Use only these sources; if you cannot read the file, say so.">
  <button type="button" className="course-playground-launch" data-course-guide-open aria-controls="course-playground-ai-2-en" aria-expanded="false">
    <Icon icon="panel-right-open" /> <span data-course-guide-open-label>Start the simulation</span>
  </button>

  <Steps>
    <Step title="Choose one primary source">
      Use interview notes, a retrospective, or another document directly relevant to the question. For the practice task, save the following as `atlas-planning-interviews.md` in a text editor:

      ```markdown theme={null}
      # Atlas planning interviews — fictional practice material

      These notes are invented for this course, not real customer evidence.

      ## Interview A — dependency visibility
      A team noticed a shared dependency only after committing to its quarterly plan.
      The interviewee wants teams to compare plans for the next twelve months before committing.

      ## Interview B — preparation burden
      Teams already write quarterly review notes.
      The interviewee would try a joint review if those notes could be reused,
      but does not want a second reporting process.

      ## Interview C — unanswered question
      This team has not tested a cross-team review of dependencies over the next twelve months.
      These interviews contain no measurement of time saved or dependencies avoided.
      ```
    </Step>

    <Step title="Keep the source in Library">
      <span className="course-playground-step-anchor" data-course-guide-source="1" aria-hidden="true" />

      <span className="course-playground-step-anchor" data-course-guide-source="2" aria-hidden="true" />

      <span className="course-playground-step-anchor" data-course-guide-source="3" aria-hidden="true" />

      <span className="course-playground-step-anchor" data-course-guide-source="4" aria-hidden="true" />

      Import the file into **Library** in the same Space as your task memories. Wait until it is **Searchable**, then return to the lesson 1 conversation and refer to its exact name. If it is already there, use the existing document. You do not need to extract memories to read it.
    </Step>

    <Step title="Tell AI Now how to use it">
      <span className="course-playground-step-anchor" data-course-guide-source="5" aria-hidden="true" />

      <span className="course-playground-step-anchor" data-course-guide-source="6" aria-hidden="true" />

      <span className="course-playground-step-anchor" data-course-guide-source="7" aria-hidden="true" />

      Continue the Atlas task with a specific instruction:

      ```text theme={null}
      Find and read atlas-planning-interviews.md in Library alongside the Atlas planning memories already found. First identify the document and its sections. Then list statements relevant to holding one cross-team planning review of the next twelve months, citing the interview heading for each. Separate what the notes say from your interpretation. Use only these sources; if you cannot read the file, say so.
      ```
    </Step>

    <Step title="Check one passage against the original">
      <span className="course-playground-step-anchor" data-course-guide-source="8" aria-hidden="true" />

      Open the file and compare a cited passage with the answer. In the practice material, Interview B allows a trial only if existing notes can be reused. It does not support adding more reporting.
    </Step>
  </Steps>

  <p className="course-playground-workflow-status" data-course-guide-ready>Follow the popup hints; reopen the simulation if you closed it.</p>
  <p className="course-playground-workflow-status course-playground-workflow-status-complete" data-course-guide-done role="status" hidden>Lesson complete. Continue to the next lesson, or try it in Nowledge Mem.</p>

  <div id="course-playground-ai-2-en" className="course-playground-window" data-course-playground-window role="region" aria-label="AI Now practice" aria-hidden="true">
    <link rel="stylesheet" href="/playground.css?v=3" />

    <div data-mem-playground />

    <script src="/playground-ai-now.js?v=4" defer />

    <script src="/playground.js?v=3" defer />
  </div>
</div>

## What you should see

<Check>
  The source is Searchable in Library, and AI Now identifies the correct document and sections. You can trace one finding to its passage, including the condition attached to it.
</Check>

<Note>
  You can also attach a file directly to an AI Now conversation for analysis. This course uses **Library** so a fresh task can find the original later. A file name in a saved memory does not prove that the original can be reopened. If AI Now cannot read it, check the document's Space and indexing status before continuing.
</Note>

## Why this matters

A primary source gives the task evidence. It lets you distinguish what the material says from what you or the AI infer from it.

## Go deeper

Read [Library](https://mem.nowledge.co/docs/library) for how source material is imported and searched alongside memories.
