Lina

Topics & mood

Every conversation tells you something. Here's what you can do with it.

Lina doesn't just answer questions — it pays attention. Every website chat message is read for what the person wants and how they feel, the moment it happens. Those signals build up into a fuller picture of each person and feed one list of everything that needs your attention — without storing a single message, and without slowing down a single reply.

The sensing layer

What people want and how they feel, read turn by turn — no message text saved.

A simple checker runs on every public website chat message, in the same step that produces the bot's reply. It looks for keywords — no AI model, no extra delay — and tags each turn with a category for what the person wants and a direction for how they feel. The tags are saved; the actual message text is not. This is the base layer everything else reads from: profiles and the Waiting on you list use these tags, never the raw conversation.

Privacy by design: the tag store keeps only the tags themselves (for example, volunteer, positive) plus a random session ID. No message text, no name, no phone number, no email ever enters this layer. Personal info stays in your CRM; tags stay in their own store — always kept apart.

Intent categoriesinterested — said something showing general interest in the organization or its work. volunteer — said they want to help out. donor — said they want to give. urgent — said something time-sensitive or urgent. hostile — an aggressive or abusive message (this brings in a human right away).
Sentiment directionpositive, negative, or neutral — tracked separately from what they want. A person can be both positive and urgent, or hostile and negative, or interested with no particular feeling attached.
PrecedenceWhen more than one tag could apply to the same turn, this is the order that wins: hostile > urgent > donor > volunteer > interested. The most important tag is the one that gets saved — so one confusing message can't create a misleading profile.
Fail-openIf the tagging step fails or can't save, it never breaks the chat itself. This layer only watches — it never changes a bot's reply and never sends an alert on its own.
More on profiles, follow-ups and the advanced switch

Each person’s record

One full profile per person, built from what they do across chat and phone.

The People list holds one record per person, matched first by email, then phone, then session ID. As a person chats and calls, their record fills in over time: how many sessions, how many calls, which channels they've used, when they were last seen, whether they've given, and the history of tags from the sensing layer. The profile combines who they are (from your CRM) with what they actually do — a fuller picture than either gives you alone, and your team never has to tag anything by hand.

  • No duplicate contacts. A person who chats on Tuesday and calls on Thursday is treated as the same record — matched by email, then phone, then session — not as two separate people.
  • What they do, not just who they are. The profile tracks how many times they've engaged, which channels they used, and what they've said they want — real behavior, not just name and contact fields.
  • Automatic, not manual. Profiles fill in on their own as conversations happen — your team never has to tag or sort anything; the system just watches and records.
  • Lifecycle tracking. When they were first seen, when they were last seen, how engaged they are, and which channels they use — so you can tell a first-time visitor from a frequent repeat contact at a glance.

Waiting on you

One list of everyone who needs a person — right on Today.

The Command Center’s Today screen has a “Waiting on you” list. It puts everything that needs a human in one place, with one count, so your team knows what to work on the moment they log in. Each row says why it is there and has a button to act on it or mark it handled. If one source can’t be read, the list says so instead of showing a zero.

  • Everything in one place. Callbacks to return, emails that need a reply, forms nobody has answered, answers flagged for review and people who asked for a person are listed together — not spread across separate screens.
  • People who left frustrated. When someone leaves a website chat frustrated (the signal Topics & mood reads), they appear here — “left their chat frustrated” — until someone marks them handled.
  • Clears itself. A row goes away when your team marks it handled, so the count is a queue, not a tally that only grows.
  • Linked to alerts. The same things can also send you an alert by email, so your team finds out even when they’re not logged in.

Editions & availability

An advanced capability you switch on yourself.

Topics & mood is an advanced capability of both the Business and Campaign editions, and it is off until you turn it on in your Command Center. Once it is on, the sensing layer tags every website chat message right away — there is nothing else to set up. Here is what it does for each edition:

Campaign edition

People & voter insight

Track what voters and the people who reach you want, in your website chat. See on each person’s record what they have said they want (to help, to give, something urgent), and follow up with anyone who left a chat frustrated from the Waiting on you list.

Business edition

Customer insight

Track what customers want, in your website chat. Follow up from the Waiting on you list with the customers who left a chat frustrated.

Talk to Eljae

Try it, then start when you’re ready.

This site’s chat and phone line are Eljae, on our own Lina account: the same system you get. Use the chat button at the bottom right, or hear the phone agent: call (619) 853-2687.

Get started See the Campaign edition preview →