Uploading Context Documents

Context documents give Koji's AI a richer understanding of your research landscape — they're background materials that help the AI Consultant design more informed studies and help the AI interviewer ask more relevant follow-up questions. Think of them as briefing materials you'd hand to a human research assistant before they start working on your project.

Why Context Documents Matter

Without context documents, Koji works with what you tell it in the chat conversation. That's often enough for straightforward studies. But when your research lives within a specific domain — a particular product, a niche market, a complex organizational structure — extra context can make a meaningful difference.

Here's what context documents help with:

Better Question Design

When the AI Consultant has access to your product documentation, previous research, or market analysis, it can craft interview questions that reference real features, actual pain points, and genuine use cases rather than generic placeholders.

Without context: "How do you use the product in your daily work?" With product documentation as context: "How does the workflow automation feature fit into your team's daily operations?"

More Relevant Probes

During interviews, the AI interviewer uses context to ask smarter follow-up questions. If it knows your product has a specific feature or your industry has a particular challenge, it can probe more precisely when a participant mentions something related.

Accurate Terminology

Every domain has its own vocabulary. Context documents help the AI learn and use the right terms — your product's feature names, your industry's jargon, your organization's internal terminology. This makes conversations feel more natural and professional to participants.

Supported File Formats

Koji accepts the following file types as context documents:

You can upload up to 5 files per study. This limit keeps the AI focused — too many documents can dilute the signal. Choose the most relevant materials rather than uploading everything you have.

What to Upload

Not all documents are equally useful. Here are the types that tend to have the biggest impact:

High-Value Context Documents

• Previous research findings — summaries or reports from past studies on related topics. These help the AI build on what you already know rather than retreading old ground.
• Product documentation — feature descriptions, user guides, or product specs. These help the AI understand what participants are using and what language to use when discussing it.
• Customer feedback summaries — compiled feedback from support tickets, NPS surveys, or review platforms. These surface recurring themes that the AI can probe during interviews.
• Competitive analysis — information about alternatives in your market. This helps the AI understand the landscape participants are navigating.
• Internal strategy documents — product roadmaps, quarterly plans, or team goals. These help align interview questions with strategic priorities.

Less Useful Documents

• Raw data dumps — large spreadsheets or databases without context. The AI can't easily extract relevant information from unstructured raw data.
• Entire codebases — technical implementation details rarely help with qualitative research design.
• Legal or compliance documents — unless your study is specifically about legal compliance, these add noise without signal.
• Marketing materials — these tend to describe ideal states rather than reality, which can actually bias the AI's understanding.

How to Upload

Adding context documents to your study is straightforward:

1. Open your study in the design workspace
2. Look for the context documents area in the study interface
3. Click to upload or drag and drop your files
4. Your files are processed and made available to the AI

You can upload documents at any point during the design process — before you start chatting with the AI Consultant, during the conversation, or after the brief is drafted.

Tip: Uploading documents before your first message to the AI Consultant tends to produce the best results, since the Consultant can factor in the context from the very beginning.

How Context Documents Are Used

Once uploaded, context documents influence two stages of your study:

During Study Design

The AI Consultant draws on your context documents when suggesting methodologies, drafting interview questions, and defining your target audience. You'll notice more specific, grounded suggestions compared to studies without context.

During Interviews

The AI interviewer has access to context documents while conducting conversations with participants. This means it can:

• Recognize when a participant mentions something related to your product or domain
• Ask follow-up questions that reference specific features or concepts
• Use appropriate terminology that matches your participants' vocabulary
• Avoid asking questions about things that are already well-documented

Context documents don't change the structure of your interview — the questions in your research brief remain the guide. But they enrich the AI's ability to improvise meaningfully within that structure.

Best Practices

Be Selective

With a limit of five files, prioritize quality over quantity. One well-written research summary is more useful than five loosely related documents.

Keep Documents Focused

If you have a 50-page report but only the executive summary and findings sections are relevant, consider extracting those sections into a separate document before uploading.

Update When Needed

If your context changes — for example, a new product feature launches between study design and interviewing — you can update your documents before publishing. The AI will use whatever is current at the time of publication.

Consider Participant Knowledge

Upload documents that reflect what your participants would know about, not just what you know. If you're interviewing external customers, product documentation they might have seen is relevant. Internal engineering specs they'd never encounter are less so.

Context Documents and Study Quality

Think of context documents as a multiplier. A well-designed study without context produces good results. The same study with relevant context produces great results. The context doesn't replace good research question writing or thoughtful work with the AI Consultant — it enhances both.

If you're new to Koji, it's perfectly fine to start without context documents and add them as you become more comfortable with the platform. Your first study doesn't need to be perfect — it needs to teach you something useful.