The assistant now follows 12 imperatives on every analytical question:

• Ranks lists by impact instead of enumerating in random order.
• Cites the specific data point behind each claim, in compact form.
• Recommends a specific next 24-hour action, never just "you might consider".
• Triages long lists into Now / This Week / Watch / Skip.
• Surfaces non-obvious findings as "Worth flagging".
• Connects across data ("this contact's last activity was on Acme's open deal").
• Forward-looks on consequences ("if no contact by Friday, ...").
• And more. See the full list in the analytical voice block.

Simple lookups ("what's the address of Acme?") still get a 1 to 2 sentence prose answer. The structured TL;DR / Details / Recommendation shape kicks in for analytical questions only.

After every substantive assistant message, 3 or 4 chips appear below the response. Each chip is a one-tap follow-up that drills deeper, drafts outreach, schedules a follow-up, or compares alternatives. Chips never appear on simple confirmations or clarifying questions.

When you open the chat panel on a CRM detail page (a company, contact, or deal), the opener chips reflect the entity's actual state (stall time, recent activity, last contact) instead of generic “summarize this”.

Generation is cached per entity for 5 minutes, so revisiting the same page in a short window does not re-run the AI call. Each cache miss is metered against your AI budget alongside other AI features. See Usage Limits for how this counts toward your monthly spend.

Laureo automatically picks how hard to think about each message. A quick lookup (“what's Acme's phone number?”) is answered fast and cheaply, while a harder, multi-step question (“which of my deals are most at risk and what should I do this week?”) gets a bigger thinking budget before it answers. A short follow-up after a complex answer (“and the second one?”) drops back down so you're not billed for heavy reasoning on a trivial turn.

While an answer is still coming back you see a Preparing response line, and once it passes three seconds the line starts counting them, so a harder question simply shows a longer count. That is the same capability working harder, not a different one. Laureo never shows you the model’s own reasoning: the line is a progress signal, and the answer itself is where the thinking shows up.

You don't configure this for chat. It happens behind the scenes on every message and counts toward your AI budget the same as any other AI feature. Background AI Agents work the same way, and you never pick the setting yourself. See AI Agents in automations.

Preferences saved via /remember or the AI Preferences settings page apply on every future chat. See the AI Preferences doc for details.