AI digest insights

What AI adds to a digest

The AI layer analyzes conversations already included in the member’s digest scope. It looks for recurring evidence and turns it into reviewable findings rather than merely restating message counts.

AI analysis is augmentative: failure or insufficient evidence does not prevent the basic digest from being sent.

Insight types

• Themes that recur across useful conversations in the period.
• Product Discovery findings captured through that Stand-in skill.
• Matches for configured custom conversation signals.
• References to the conversations that support a claim so a member can inspect the underlying evidence.
• An explicit insufficient-data result when the available conversations do not justify analysis.

Enable AI analysis

• Open Digest on a Pro or Business workspace.
• Turn on AI analysis and save the setting.
• Configure Product Discovery or custom signals on the relevant Stand-ins when those specialized findings are required.
• Wait for the next scheduled digest or use the on-demand seven-day send to request a current recap.

Evidence and scope

• Only conversations in the digest recipient’s permitted scope are analyzed.
• Referenced session identifiers are restricted to conversations inside that digest population.
• Labels chosen for ordinary notification preferences do not silently become AI analysis categories.
• Conversation retention determines which source material remains available.

Interpretation limits

• A theme is a synthesis of the sampled period, not a statistical claim about every customer.
• Sparse, repetitive, or low-information chats can produce an insufficient-data result.
• AI findings should be verified against linked conversations before a product or customer decision.
• Disabling AI analysis removes the generated section from future digests but leaves the ordinary digest enabled.

Example

The screen below shows the feature in its normal Stand context. Labels and surrounding controls may vary with account state and plan.

Related features

• Email digests — Email digests send a scheduled or on-demand recap of completed chat activity to each member at the scope allowed by their role.
• Product Discovery — Product Discovery lets an AI Stand-in recognize a relevant research opportunity, ask the visitor for explicit consent, and conduct an adaptive interview without replacing the visitor’s original request. Grounded findings are saved with transcript evidence and a built-in Product Discovery label.
• Custom conversation signals — Custom conversation signals let an organization define the kinds of customer evidence a Stand-in should recognize. A matched signal adds a searchable label with supporting context and can alert the Stand-in owner on the first match.