ResearchCopy link to this section

Research is where Floe turns raw content and product context into structured product knowledge. After ingestion collects your documentation, the research pipeline analyzes it to support the AI agent's real-time answers.

What research producesCopy link to this section

Research isn't a single pass. It runs multiple analysis layers across your content:

• Feature extraction: Identifies distinct product features from your documentation, grouping them by area (e.g., "Reporting," "User Management," "Integrations")
• Workflow modeling: Connects related product features into logical user flows, such as "create account then configure workspace then invite team"
• Terminology indexing: Builds a vocabulary of your product's specific language so the agent speaks in your terms, not generic ones
• Content linking: Connects related documentation topics so the agent can draw on consistent product context

This produces a structured knowledge base that the AI agent draws from in real time during demos, self-serve onboarding, and support conversations.

How research fits the pipelineCopy link to this section

The typical flow is:

1. Create a site for your product
2. Ingest content from your docs, knowledge base, and videos
3. Research analyzes your content and product context
4. The AI agent draws on the resulting product knowledge

Research can run automatically after a first successful ingestion. Updating source content re-runs ingestion, but any generated demo-context update requires internal processing before it is reflected in a demo.

What you see in the dashboardCopy link to this section

After research completes, the Knowledge tab in your site shows what Floe learned:

• Topics: Grouped areas of your product, each with a summary of what Floe understands about that area
• Features: Individual features identified from your content, with the source material that supports each one
• Content coverage: A breakdown of how much of your documentation informs Floe's product knowledge, highlighting topics that need more detail

This is the place to check whether Floe has an accurate picture of your product before running demos.

Reviewing and improving research outputCopy link to this section

Research quality depends on the quality of your inputs. If you see gaps:

Missing features: You likely need more content. Add documentation or help articles that cover the missing area and re-run ingestion.

Incorrect associations: A feature may not be connected to the right product context. Add more specific documentation about the feature and re-run ingestion.

Vague descriptions: Research mirrors the clarity of your source content. If a feature description is generic, check whether the underlying documentation is specific enough. Detailed docs produce detailed research.

Low coverage scores: If the content coverage section shows topics that need more detail, add documentation that more clearly describes the affected product areas and re-run ingestion.

After changing any source, generated demo context requires internal processing before it is reflected in a demo.

How the agent uses research at runtimeCopy link to this section

During a live demo or onboarding session, the agent draws on research in three ways:

Answering questions: When a prospect asks "How does your reporting work?", the agent retrieves the research-derived knowledge about your reporting features and explains it using your product's terminology.

Navigating to the right place: Research connects features to the relevant workflow guidance, helping the agent choose what to show during a demo or onboarding session.

Contextual explanations: As the agent navigates your product, it pulls in the relevant knowledge for the workflow it is showing.

This is what makes the agent sound like it knows your product rather than reading from a script. The research layer is the bridge between your raw content and the agent's contextual help intelligence.

When research needs updated inputCopy link to this section

Re-run ingestion when:

• You've added or updated content via ingestion
• The agent is giving inaccurate or outdated answers during demos

Re-ingestion updates your source content. Any generated demo-context update requires internal processing before it is reflected in a demo.

FAQCopy link to this section

Is research the same as ingestion? No. Ingestion reads and indexes your raw content. Research analyzes that content and available product context to build structured product understanding. Ingestion is input; research is analysis.

Can I see exactly what research extracted? Yes. The Knowledge tab shows topics, features, and coverage metrics. Everything research produces is visible and reviewable.

How long does research take? It runs in Floe's internal knowledge-building pipeline. Its timing depends on the site's content and processing state.