agentic-engagementDeploy an agent that holds email conversations with leads: a sending domain, a mailbox, a native email trigger on reply and unsubscribe, and a heartbeat that checks thread status when nothing inbound happened. Triggers: "handle email conversations with leads", "agentic engagement", "an agent that replies to inbound email", "stand up a conversation agent on a Cargo mailbox", "native email trigger for lead replies", "keep talking to leads over email". Cargo CDK, defineDomain, defineMailbox, defineAgent, agentNativeTrigger, heartbeat, sendEmail. Skip when: you want to send one email right now, which is a native sendEmail from the CLI and needs nothing deployed; or you want a play that blasts a list rather than holding a thread.
Install via ClawdBot CLI:
clawdbot install cargo-ai/agentic-engagementGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/getcargohq/gtm-skills/tree/main/agentic-engagementAudited Sep 10, 2026 · audit v1.0
Generated Sep 10, 2026
A B2B SaaS team sends cold outreach to trial signups and lets an agent hold the email thread, answering pricing, integration, and security questions from a knowledge base. The native email trigger wakes the same chat on `replied` or `unsubscribed` status, so a hot lead gets a coherent reply in minutes instead of waiting on an SDR.
An agency or in-house recruiter emails passive candidates about a role, then relies on an agent bound to a company mailbox to answer logistics, comp range, and interview-process questions. A heartbeat catches threads stuck at `sent` so no candidate goes cold from silence.
A brokerage receives property inquiries from a listing site and deploys an agent on an owned domain to keep the thread alive, qualifying budget, timeline, and financing status over email. Replies and opt-outs flow back through the native trigger, keeping the conversation in one thread per prospect.
A fintech growth team emails applicants who abandoned a KYC flow and lets an agent answer document, eligibility, and compliance questions on-thread. Because the send-email tool pins the mailbox uuid, replies can't leak from the wrong inbox, which matters for regulated correspondence.
An education company emails prospective students after an info-session signup and uses the agent to handle curriculum, payment-plan, and start-date questions. The heartbeat reintroduces a status check on quiet threads so students who went quiet get a timely nudge.
A product company pays for Cargo workspace credits to run the conversation agent on its own domains, absorbing domain and mailbox costs as infrastructure. The agent replaces or augments SDR headcount for inbound reply handling, justified by a faster time-to-first-response and higher meeting-booking rate.
An agency or fractional GTM shop deploys agentic-engagement per client on client-owned or agency-owned domains, charging a monthly retainer plus setup. Mailbox charges are recurring, so the agency must quote live pricing and get explicit sign-off before every deploy.
Cargo itself monetizes via workspace credits: domain registration is a one-time non-refundable charge, mailboxes are a recurring monthly charge, and LLM connector usage is metered. Customers self-serve CDK deploys and only pay when the loop is actually running.
💬 Integration Tip
Install via `cargo-ai cdk add cookbook/agentic-engagement` and reconcile every domain, mailbox, and connector slug against what already exists before planning, since duplicate slugs collide at deploy. Always run `cargo-ai cdk plan`, quote live mailbox pricing with `cargo-ai mailboxManagement pricing get`, and get explicit approval before `cargo-ai cdk deploy` because domain and mailbox creation are charged.
Scored Sep 10, 2026
Meta-skill for AI agent self-improvement. Analyzes runtime logs to detect error patterns, regressions, and inefficiencies, then generates structured improvem...
Stop waiting for prompts. Keep working.
Turn OpenClaw into a learning-loop agent with seeded workspace rules, skill promotion, reflective memory, and proactive maintenance.
Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub-agents with dynamically generated SKILL.md files, coordinates file-based communication, consolidates results, and dissolves agents upon completion. MANDATORY TRIGGERS: orchestrate, multi-agent, decompose task, spawn agents, sub-agents, parallel agents, agent coordination, task breakdown, meta-agent, agent factory, delegate tasks
Complete toolkit for creating autonomous AI agents and managing Discord channels for OpenClaw. Use when setting up multi-agent systems, creating new agents, or managing Discord channel organization.
Billions decentralized identity for agents. Link agents to human identities using Billions ERC-8004 and Attestation Registries. Verify and generate authentic...