# Agents inside your HighLevel sub-accounts > We build agents scoped to one HighLevel sub-account: lead qualification, conversation triage and appointment setting, with every outbound send cleared first. Canonical page: https://aispeedforce.com/platforms/highlevel/ Last updated: 2026-08-23 HighLevel is multi-tenant by design, so the first thing we build is not a capability. It is the location scoping that keeps an agent inside one sub-account. The second is the send gate, because conversations here run over SMS and email. ## Three jobs an agent does well here Each one is scoped to a single location, reads far more than it writes, and stops at a decision you named before we built it. ### Lead qualification The agent scores an inbound lead against your criteria, enriches the record, sets the custom fields you use for routing and moves it to the right pipeline stage. - **Touches**: contacts, opportunities, pipelines, custom fields - **Human gate**: Any pipeline move past the stage you name. ### Conversation triage The agent reads a thread across SMS, email and messaging, summarizes where it has got to, and drafts the reply for a person to send. - **Touches**: conversations, contacts - **Human gate**: Every outbound send, without exception. The agent drafts, a person sends. ### Appointment setting The agent checks calendar availability, proposes slots that fit your rules on notice, duration and who is qualified to take the call, and prepares the booking. - **Touches**: calendars, contacts, opportunities - **Human gate**: Booking confirmation. ## What the agent is wired into One agent, one location, one set of granted permissions. Nothing reaches across a client boundary because nothing is given the credentials to. - **HighLevel API v2**: Contacts, opportunities, pipelines, conversations and calendars, with every call made against a single location the agent is bound to. - **Webhooks**: ContactCreate, OpportunityStatusUpdate and InboundMessage are the triggers, so the agent wakes on a real event rather than polling for one. - **Marketplace app**: How the agent is installed and how permissions are granted per sub-account, so an agency can add it to one client without touching the rest. - **Location scoping**: Enforced in the tool layer, not left to the prompt. A tool call for another sub-account's records is rejected before it reaches the API. - **Workflows**: HighLevel's own automation keeps the deterministic steps, so the agent only handles the parts that genuinely need judgement. ## Two gates, not one Most platforms need a gate on write actions. HighLevel needs that and a hard boundary between the sub-accounts an agency runs. **Location gate**: An agent is issued credentials for one sub-account and its tools carry that location on every call. It cannot read another client's contacts or write to their pipeline, because the request never gets built. This is the first thing we put in place, before any capability is added on top of it. **Send gate**: Nothing goes out over SMS or email until a person clears it. Outbound messaging is regulated, so we do not make this gate optional and we do not ship a mode that turns it off. The agent produces a draft on the conversation, a named person sends it, and the run is traced either way. We build the approval step, the trace and the record of who cleared what. We do not advise you on the rules that apply to your messaging, and we do not certify anything on your behalf. Bring your own counsel for that part and we will build to what they tell you. ## Questions agencies ask first ### Can one agent serve all our sub-accounts? Not as one shared instance. An agent is bound to a single location, and that binding sits in the tool layer, so a call for another sub-account's records fails rather than returning them. The same agent is rolled out across sub-accounts as separate scoped installs through the marketplace app, each with its own permissions. That way widening what an agent can do in one sub-account is a decision you make for that sub-account, not a change that quietly lands everywhere. ### Does this replace HighLevel workflows? No, and we would rather it did not. Workflows keep the deterministic steps: a tag fires, a delay runs, a field is set. The agent takes only the parts that need judgement, like reading a messy inbound thread and working out what it is actually about. The two run side by side, with webhooks such as ContactCreate, OpportunityStatusUpdate and InboundMessage handing work to the agent and the workflow carrying on afterwards. ### Who is responsible for message compliance? You are, as the sender, and we build so that a person is always in that loop. Outbound SMS and email are regulated, so we do not make the send gate optional: the agent drafts, a named person clears it, and the run is traced so you can see what was drafted and who approved it. We are not your legal advisers on this and we will not build a version of the agent that sends on its own. Related work: [agent engineering](https://aispeedforce.com/services/agent-engineering/) for the agent itself, and [automation and workflows](https://aispeedforce.com/services/automation-workflows/) for the deterministic steps around it. - [All platforms](https://aispeedforce.com/platforms/) - [Wix agents](https://aispeedforce.com/platforms/wix/) - [Agent engineering](https://aispeedforce.com/services/agent-engineering/) - [Automation and workflows](https://aispeedforce.com/services/automation-workflows/) - [Contact](https://aispeedforce.com/contact/) ## Start with one sub-account Pick a single location and one job inside it. We will scope the agent to that location, agree the gate on every send, and show you the trace before you roll it out to the rest.