Yadulink / Documentation / AI agent

Configure the Yadulink AI agent before delegating LinkedIn prospecting.

A useful prospecting agent does not start by sending more messages. It starts with a clear operating frame: target, offer, exclusions, authorized signals, human review, and success metrics.

AI agent

The brief should frame autonomy

The Yadulink AI agent should know who to contact, why now, what it must never promise, and when to hand control back to a human. This prevents a signal-based workflow from becoming opaque automation.

AI agent

Preview before execution

Before importing a list or activating a sequence, the preview should expose criteria, representative profiles, exclusions, proposed messages, and risks around volume or wrong targeting.

AI agent

Measure the right outcome

The operating review should track qualified conversations, booked meetings, handled objections, avoided duplicates, stopped sequences, and the signals behind each action.

Verified facts

What this documentation should make explicit.

Purpose

A useful prospecting agent does not start by sending more messages. It starts with a clear operating frame: target, offer, exclusions, authorized signals, human review, and success metrics.

Workflow proof

The Yadulink AI agent should know who to contact, why now, what it must never promise, and when to hand control back to a human. This prevents a signal-based workflow from becoming opaque automation.

Assistant prompt

Help me configure the Yadulink AI agent for controlled B2B LinkedIn prospecting. Check ICP, exclusions, signals, preview, messages, MCP/CRM permissions, and metrics to monitor.

Verification method

How to turn the guide into an operational test.

  1. 01 Agent setup Define the ICP, excluded accounts, priority roles, and acceptable LinkedIn signals.
  2. 02 Agent setup Provide the offer, tone, approved proof points, and objections the agent should handle carefully.
  3. 03 Agent setup Run a preview of the search and messages before activating any sequence.