🤖

Agents

Everything about building, deploying, and tuning AI agents.

Settings: system prompt, fallback, behaviour

The core identity of your agent — who it is, what it does, and what it says when it hits a dead end.

Simple vs Advanced agents: picking a context level

Advanced agents pre-load the contact's opportunities and custom fields into every turn. When to flip it on, what it costs, and when not to.

Writing a Business Context glossary

The free-text block that tells your Advanced agent what your custom fields and opportunities mean in your business.

Channels: where your agent runs

SMS, WhatsApp, Instagram, Facebook, Google Business, Live Chat, Email. Pick the channels your agent listens on.

Knowledge base

Give the agent things it needs to know — pricing, FAQs, policies, a full website crawl.

Deploy rules: when the agent runs

Decide which conversations this agent picks up. AND, OR, and NOT across tags, stages, keywords.

Merge fields: the {{…}} placeholders that personalise pre-written messages

Drop contact data into fixed-mode triggers, follow-ups, voice openers, fallback lines, and the Advanced business-context glossary.

Rules vs Listening: what goes where

Rules write a known value to a known field. Listening takes free-text notes. Learn when to use each.

Rules: IF the contact says X, THEN do Y

Passive detection rules that run CRM actions — update fields, add tags, enroll in workflows, change opportunities, mark DND — based on what the contact says.

Listening: categories the agent remembers

Teach the agent to keep private notes about contacts without asking, and reference them in future chats.

Tools: what the agent can do

The verbs available to the agent — send messages, book appointments, tag contacts, enroll in workflows, hand off to humans.

Qualifying questions: what to ask, what to do with the answer

Scripted questions the agent asks to fill contact fields, plus conditional actions when specific answers land.

Persona: how the agent sounds

Voice, tone, response length, emoji use, language, typing behaviour. The personality layer.

Objectives: what a "win" looks like

Define the outcomes that matter so the agent can push toward them — and so you can measure success.

Stop conditions: when the agent should stand down

Auto-pause on bookings, keywords, hostile sentiment, message counts. Tag needs-attention and trigger GHL workflows on the way out.

Triggers: start conversations, not just reply to them

Fire a first message when a contact hits a specific event — new contact, tag added, etc. Edit, test-fire, delay by days/hours/minutes.

Follow-ups: nudging quiet contacts

Multi-step automated nudges when a contact goes silent, says a keyword, or the agent decides it's time.

Voice: phone-call agents

Real-time voice agents that answer inbound calls, speak naturally, and book appointments.

Working hours: when the agent is allowed to reach out

Define the time window when the agent can send proactive messages. Inbound replies always send.

Needs Attention: the review queue for flagged conversations

One page that surfaces every conversation your agent couldn't handle — paused, errored, fallback-answered, stalled. Act on any row inline without leaving the page.

Taking over and resuming: the handoff workflow

When your agent flags a conversation, you can take over under your own name or resume the agent with a context note it reads on its next reply.

Human handover notifications: where the pings go

Configure Slack, Discord, email, and SMS destinations for agent pauses, errors, and transfer_to_human calls.