Editing the Brief Manually

While the AI Consultant is excellent at drafting and iterating on your research brief through conversation, sometimes you know exactly what change you want to make and you'd rather just do it yourself. Koji's brief editor lets you directly modify every part of your study design.

When to Edit Manually vs. Chat

Both approaches update the same research brief, so choose whichever feels faster for the change you're making:

The general rule: if you know the exact words you want, edit manually. If you want to think through implications or get suggestions, chat with the Consultant.

Accessing the Brief Editor

The research brief is displayed in the artifact panel alongside your conversation with the AI Consultant. To edit any section:

1. Navigate to your study
2. Look at the research brief panel on the right side of the screen
3. Click on the section you want to edit
4. Make your changes directly in the text
5. Your changes are saved automatically

The brief editor works like a standard text editor — you can type, delete, copy, paste, and rearrange content freely.

Editing the Problem Statement

The problem statement sits at the top of your brief. It's the anchor for your entire study, so changes here can have cascading effects.

Tips for editing the problem statement:

• Keep it to one to three sentences
• Focus on what you want to learn, not what you plan to build
• Avoid language that assumes a particular outcome
• After editing, scan the rest of the brief to make sure everything still aligns

If you significantly change the problem statement, consider asking the AI Consultant to review the rest of the brief for consistency. You can say something like: "I updated the problem statement — does the rest of the brief still make sense?"

Changing the Methodology

You can switch the methodology by editing the methodology section of the brief. Koji supports several approaches, each described in detail in our methodology guide:

• Mom Test — great for idea validation without leading the witness
• Jobs to Be Done — ideal for understanding motivations and decision-making
• Customer Discovery — suited for early-stage problem exploration
• User Interview — versatile general-purpose qualitative interviewing
• Usability Testing — focused on how people interact with a specific product or feature
• Employee Engagement — tailored for internal organizational research
• Market Research — designed for broader market understanding
• Custom — full flexibility to define your own approach

Important: Changing the methodology affects how the AI interviewer conducts conversations. Different methodologies use different questioning styles, follow-up strategies, and conversational tones. If you switch methodologies, review your interview questions to make sure they still fit the new framework.

For significant methodology changes, chatting with the AI Consultant is often more efficient, since it can regenerate appropriate questions for the new approach.

Fine-Tuning Interview Questions

This is where most manual editing happens. Here's what you can do:

Rewording Questions

Small wording changes can make a big difference in how participants respond.

Before: "What challenges do you face with the product?" After: "Walk me through a recent situation where you ran into difficulty while using the product."

The second version is more specific, grounded in real experience, and harder to answer with a vague generalization.

Adding or Removing Questions

To add a question, place your cursor where you want it and type it in. To remove one, simply delete it.

Things to consider when adding questions:

• Will there be enough time to cover this in the interview?
• Does it contribute directly to answering your research question?
• Is it distinct from other questions, or does it overlap?

Things to consider when removing questions:

• Is the question truly unnecessary, or is it just phrased poorly? Sometimes rewording is better than removing.
• Does removing it leave a gap in the conversation flow?

Editing Probes

Probes are the follow-up questions listed under core questions. They tell the AI interviewer what to dig into when a participant gives an interesting answer.

Good probes dig into:

• Specific examples ("Can you tell me about a specific time that happened?")
• Emotions and reactions ("How did that make you feel?")
• Decision-making ("What made you choose that approach over other options?")
• Consequences ("What happened as a result?")

Weak probes to avoid:

• "Can you tell me more?" (too vague)
• "Was that good or bad?" (leading and binary)
• "Anything else?" (signals the interviewer wants to move on)

Reordering Questions

The order of questions matters more than most people think. A well-ordered interview:

1. Starts with easy, broad questions that get the participant talking comfortably
2. Moves into the core topic once rapport is established
3. Goes deeper with specific, potentially sensitive questions in the middle
4. Ends with reflective or forward-looking questions that leave the participant feeling valued

To reorder, cut and paste questions into the position you want. After reordering, read through the whole plan to check that transitions between questions still feel natural.

Adjusting the Target Audience

The target audience section describes who your study is designed for. When editing this section:

• Be as specific as possible — this description helps you recruit the right people and helps the AI interviewer calibrate its conversation style
• Include relevant behavioral criteria, not just demographics (e.g., "has evaluated at least two CRM tools in the past year" is more useful than "works in sales")
• Consider adding exclusion criteria if certain groups would skew your findings

Editing Additional Settings

Depending on your study, you may also be able to edit:

• Interview length target — how long you want each conversation to last
• Tone and formality — how casual or professional the interviewer should sound
• Special instructions — any custom guidance for the AI interviewer

These settings fine-tune the interview experience without changing the research substance.

After Editing: A Quick Review Checklist

After any manual edits, run through this checklist before publishing your study:

• Does the problem statement still match the rest of the brief?
• Are all questions open-ended and non-leading?
• Do questions flow naturally from one to the next?
• Is the total number of questions realistic for your target interview length?
• Do probes add depth rather than just asking for "more"?
• Is the target audience specific enough to recruit?
• Does the methodology match the conversational style of your questions?

Switching Between Manual Editing and Chat

Remember, you can freely switch between editing manually and chatting with the AI Consultant. They operate on the same document. A common workflow is:

1. Use the AI Consultant for the initial draft and major structural decisions
2. Switch to manual editing for precise wording adjustments
3. Return to the Consultant if you're unsure about a change and want a second opinion

For a full walkthrough of what each section contains, see Understanding the Research Brief.