AI voice calls

Nudge places real phone calls through AI voice agents (powered by Retell). The agent has an actual conversation in the lead’s language, asks your qualification questions, and the outcome routes the next step.

​

Agents and numbers

An agent is a configured voice, script and language. Each agent can be pinned to an outbound number and has its own calling hours. Manage both under Settings → Voice agent. Each contact owner gets a default calling agent, so “call this lead” always knows which voice and which number to use.

​

Editing an agent

Click an agent’s name to open its page. Everything the agent is lives there:

• Prompt and opening line — what the agent says and how it behaves. Anything in {{double braces}} is a placeholder that gets filled per call; it shows as a blue chip so you can see at a glance what the agent will know.
• Voice — swap it any time, with a preview button to hear it first.
• Variables — the answers this agent collects, grouped by when they’re captured.

One Save to Retell publishes all of it, and it takes effect on the agent’s very next call. Nothing saves as you type: a half-finished edit would otherwise go live mid-sentence. While you have unsaved work the page says so and offers Discard changes, and it asks before you navigate away. Use the search box at the top to find your way around a long prompt — it highlights matches in the text and filters the variable list.

​

What the agent collects

Each variable has a name, a description telling the agent what to capture, a type (text, number, yes/no, or a list of choices), and a capture phase:

• During the call — captured the moment the caller says it, so it survives even if the call drops. Pick During, caller confirms first for anything expensive to mishear, like a callback time or a budget.
• After the call — read out of the call analysis once the call ends. This is the default and it’s right for most answers.
• Before the call — not captured at all. These are the fallback values the agent starts with when a call carries nothing better, so the script still reads naturally. If your opening line says “Hello ” and a contact has no first name on file, a default of there keeps the agent from opening with an awkward pause.

Per-contact values always beat the defaults. Nudge sends the contact’s real name and number with every call, so the default only fills a genuine gap. In a standalone workspace, your fields can be the questions. Go to Workspace setup, set a field’s Filled by to Voice agent, then use Seed from contact fields on the agent page to fill the variable rows from those fields. Review them, then save. Answers land on the contact’s own fields, ready to use in trigger conditions and message variables like any other field. Two things worth knowing:

• Fields left as Staff are off-limits to the agent even if it heard an answer. A voicemail still returns a full set of guesses, and those must not overwrite what a person typed.
• An answer with no matching field still lands, namespaced, so you can use it in trigger conditions.

In HubSpot mode it works the other way round: you declare the variables on the agent, and Nudge mirrors them into a read-only list under Workspace setup so you can label them and use them in conditions.

​

Placing calls

Calls happen two ways:

• Automated: a trigger’s call action, for example “new lead in state Contacted: call within business hours”. Call timing clamps to the agent’s calling hours.
• Manual: the Place call button on a contact page or inbox thread. The dialog pre-selects the owner’s default agent and number.

To hear an agent yourself, use Test call on the agent page or in the agents list. It rings a number you type, from that agent’s own number. Real minutes are billed, and it always runs the last saved version — save first if you want to hear an edit.

​

Outcomes drive the workflow

Every call ends with an outcome: reached, no answer, voicemail, not interested, and so on. A trigger can map outcomes to states, for example call succeeded sets possibility to Qualified, call failed sets No answer, which arms the WhatsApp follow-up trigger. That call, no answer, message, close chain is the canonical Nudge workflow. After each call, the summary, outcome and sentiment land on the contact’s timeline. Repeated no-answers are counted per contact, so a rule like “3 failed attempts: close the file” is one condition, not custom logic.

​

Listening back

Open any call — from the contact’s Calls tab or from Activity — and you get the recording, the summary, the answers the agent collected, and the full transcript laid out as a conversation. That last one is what you want when a summary reads oddly or a variable came back empty: you can see exactly what was asked and what the person said.