Chat Focus Suggestions

A focus suggestion is the chat's recommendation for which data it should work on. That scope affects much more than loading highlights. The same focused scope is also used for tasks such as creating clusters, assessing hypotheses, and collecting evidence.

Why focus suggestions exist

Teamspaces are often set up by one person who knows the taxonomy in detail. Their colleagues usually know what they want to learn from the data, but not which tags, search phrases, or time ranges best represent that request.

Focus suggestions bridge that gap. The chat analyzes your question, compares it with the available data organization, and recommends a suitable scope before doing heavier work.

That scope can include tags, a search phrase, a time range, or a combination of them. Tags are used when the taxonomy has a reliable way to represent part of your request. A search phrase is used for the parts that still need narrowing but are not cleanly represented by the taxonomy.

The goal is simple: give the chat a more relevant and consistent dataset so it can produce better results.

A better focus helps the chat:

• Create more coherent clusters
• Assess hypotheses against the right evidence
• Collect stronger supporting or contradicting examples
• Produce answers that are better grounded in related data

Example

If you ask, What are the user pains during onboarding about passwordless login since our March release?, the chat might suggest a focus like:

• Tags: [User pain], [Onboarding]
• Search phrase: passwordless login
• Time range: March until now

In this example, User pain and Onboarding are good tags because the taxonomy already captures them. Passwordless login stays a search phrase because it narrows the topic further, but may not exist as a reliable tag in the teamspace.

How tag AND and OR behavior works

When a focus includes multiple tags, it matters whether they apply together or as alternatives.

• AND means the chat looks for data that matches all tag conditions
• OR means the chat looks for data that matches any of the tags

For example, a topic tag and a segment tag are often combined with AND because both should be true at the same time. When the suggestion includes multiple tags from the same tag group, the chat treats those tags as alternatives and groups them with OR, since a single highlight usually matches one of them rather than all of them.

That still applies if your wording sounds conjunctive. If you ask about several brands, countries, or issue types that all come from the same group, the chat will treat them as alternative ways to narrow the dataset rather than requiring all of them on the same highlight.

Search phrases are not only a fallback for when there are no tags at all. The chat can also combine tags and a search phrase in the same focus. This happens when part of your request maps well to the taxonomy, while another part needs to be narrowed through the wording of the topic itself.

How confirmation works

The chat can misinterpret your question and suggest a focus that is too narrow or too broad. If it continued immediately, it might run heavy analysis on the wrong dataset. Instead, the chat asks you to confirm.

You can think of it like you being the manager of the chat:

• The chat proposes the dataset it plans to use
• You review that plan
• You approve or adjust it

The suggestion also shows the number of matching highlights so you can quickly judge whether the focus looks reasonable.

The chat does not always ask for confirmation. It may continue without interrupting when:

• A focus is already in place
• The suggested focus is effectively the same
• There is no meaningful focus to add
• The message is configured to auto-apply focus suggestions

Messages can opt into automatic focus application. In that mode, the chat still generates a focus when it finds a useful one, but it applies that focus directly instead of waiting for confirmation. For automated messages, that same setting also controls whether focus generation runs at all.

Automated messages never require a human focus decision. When they generate a usable focus, the result is applied directly.

When an automated message already has a broad focus, automatic focus application can refine that scope using the current message input. User-set filters take priority, while generated filters fill in missing scope and add useful tags. For example, a message configured to use data from the last 90 days can still narrow inside that time range based on the ticket, account note, or other input being processed.

If the chat cannot produce a usable focus suggestion, it continues with the existing scope, or the full dataset if no scope is active, instead of revising its plan around a new suggestion.

How focus carries through the chat

Once applied, the focus becomes the working scope for the chat.

The focus is a retrieval scope, not evidence by itself. When the chat answers from highlights, it should only make specific claims when the retrieved highlight descriptions or quotes support those claims. Highlight-backed claims include inline annotations whenever highlight IDs are available, even if the message asks to omit citations. If the focus finds highlights that are only broadly related to the question, the answer should say that the evidence does not specifically address the requested product, integration, segment, or relationship instead of treating the focus wording as fact.

For lightweight account-level questions with an active focus, the chat can request selected account metadata alongside the retrieved highlight descriptions. For example, when you ask how feedback differs by account, region, segment, industry, employee size, account type, or account status, the chat may include only those account fields in the evidence it reads. This helps it reason about account dimensions without adding every available field to the prompt.

The chat also rewrites the active focus into a readable scope before planning and answering, so internal tag and date filters become understandable context. Calendar date filters are interpreted in the teamspace timezone, and the chat receives the resolved local start and end dates as context. If your message asks for a specific date format, the chat formats those local dates for the answer. When retrieved highlights have grouped tags, the chat can include those tag-group values with each highlight. For example, if the focus compares several countries, the evidence can show Country: France or Country: Germany instead of a generic tag list. Tags that do not belong to a tag group are left out of this extra context.

This metadata is still evidence from the retrieved sample, not a full teamspace breakdown. If you need counts, percentages, or representativeness by account dimension, use a quantified breakdown rather than treating the chat answer as a distribution report.

Follow-up messages continue using that same dataset, so the chat does not need to start from the full dataset each time.

If you start from manually selected highlights or a recording, follow-up messages continue using that exact selection as the working scope.

If you select one or more clusters, those selected clusters become the working scope for the next retrieval steps. The chat searches, collects evidence, creates new clusters, and assesses hypotheses inside the selected clusters instead of returning to the broader focus suggestion from the chat. This lets you drill into a cluster without the chat widening the scope back to the full focused dataset.

When the chat creates clusters, it quantifies them before showing them. Cluster counts in the chat are based on the matched highlights for the active scope, not on a separate manual quantification step.

While that work is running, the processing stream can carry live activity for the current operation. Short steps send status messages only. Longer predictable steps such as cluster quantification, evidence collection, and hypothesis assessment can show a percentage from 0% as soon as measurable work begins, then advance as the work progresses. Those updates are transient signals for the active run; they do not change the saved chat history or the final cluster counts.

When follow-up messages stay within the same scope, the active time range remains part of that scope. If a later message clearly sets a new timeframe, that timeframe becomes part of the focus instead. If a later message clearly broadens back to no time limit, the time range is removed from the focus.

If you want to work from a different scope later, change or clear the active focus before sending the next message.

FAQ

What if the suggested focus keeps excluding useful data?

This usually means a tag isn't applied consistently enough in the teamspace.

For example, a country tag might exist for app feedback but not for survey feedback. If that tag is used for focus, the chat may unintentionally exclude survey data.

In such cases, it is often better to opt that tag out of AI focus.

Should I always approve a focus suggestion?

No. Approve it when it reflects the dataset you want. Edit or reject it if it would lead the chat in the wrong direction.

Does focus only affect highlight loading?

No. Focus defines the dataset used for all downstream tasks, including clustering, evidence collection, and hypothesis assessment.