Conversation Intelligence
Ask natural-language questions about your calls, meetings, and emails and get a synthesized, cited answer. Consumes AI action credits.
What it does
Conversation Intelligence turns your calls, meetings, and emails into answers. Ask what was said, agreed, or pushed back on in plain language, and it reads the relevant conversations and hands back a direct answer with citations, no scrubbing through recordings. Scope it to a single engagement, an account, or a contact.
It is the double-click on the timeline that Browse Engagements builds. Browse tells you a meeting happened. Conversation Intelligence tells you what came out of it, and what to do next.
What you can do
- Walk into a meeting knowing what was discussed and committed last time.
- Pull requirements, pain points, and blockers out of a specific call.
- Get an account-health read across recent conversations without replaying a single recording.
- Draft a follow-up grounded in what the customer actually said, with quotes.
Credits
AI action credits. Each call runs a sub-agent that retrieves and reasons over your conversation content, so pricing reflects the work involved. Most questions cost around 10 credits, scaling with how much context the answer draws on. See Credits & Billing.
How it works
Conversation Intelligence is a context agent, like Account Research and Contact Research. It runs a sub-agent that pulls the most recent transcripts and email threads for your scope, up to five of each. The sub-agent synthesizes an answer and returns only what serves your question. A single transcript can run to tens of thousands of characters; the sub-agent absorbs that volume so your orchestrator's context window doesn't have to.
Provide exactly one scope:
- An engagement ID (from Browse Engagements) to analyze one call, meeting, or email. Request the content option to also receive the raw transcript or email body.
- A company ID to synthesize across recent engagements with an account.
- A contact ID to synthesize across recent engagements with a person.
Connected conversation sources
Conversation Intelligence works from the calls, meetings, and emails your organization already captures. That includes recordings from web-conferencing and revenue-intelligence platforms such as Google Meet, Zoom, Microsoft Teams, Gong, and ZoomInfo Chorus, alongside synced email. The more sources you connect, the fuller the picture. A conversation that just wrapped can take a little while to index. Your ZoomInfo admin can confirm what's connected.
Getting the best results
Conversation Intelligence is sharpest when you point it at a specific engagement, account, or contact and ask a focused question. A few pointers:
- Bring the conversation, it does the rest. Start from an account or contact for a recent-activity read, or pass an engagement ID from Browse Engagements to go deep on a single call. Topic-based discovery, like "every call where SOC 2 came up," is on the roadmap.
- One account or contact at a time. Each question centers on a single scope, which keeps answers focused and grounded. To cover a whole book of business, run it across your accounts in turn.
- Tuned to the latest conversations. It draws on your most recent calls and emails, and account queries also layer in longer-run account intelligence. For an older specific, point it straight at that engagement.
- Great for the narrative. Lean on it for what was said, what was committed, and what to do next. Precise tallies across months of calls aren't what it's for.
When the AI uses it
The AI invokes Conversation Intelligence when you ask what happened in a conversation, or what's going on with an account based on recent talks. To find which meetings exist in the first place, it reaches for Browse Engagements. For a firmographic or CRM-based account briefing, it uses Account Research.
The natural chain is Browse Engagements to find the meeting, Conversation Intelligence to analyze it, then a drafting step for the follow-up.
What's returned
- A synthesized answer to your question, written from the actual conversations.
- Inline citations linking back to the source meetings.
- The raw transcript or email body, when you scope to a single engagement and request content.
Example prompts
"What were the main objections on my last call with Acme Corp, and who raised the one about pricing?"
"Summarize where things stand with this account before my renewal call."
"Pull the requirements and any blockers the customer mentioned in this meeting."