Current Goal and Constraints, Ruled-Out Options and Why, and Next Single Action.
{{contact.current_goal_and_constraints}}, {{contact.ruled_out_options_and_why}}, and {{contact.next_single_action}} at the top of the prompt and test a fresh session by asking what the assistant should do next and what it should avoid.
Set up a structured project context handoff for multi-session AI chats in sub-account <YOUR_LOCATION_ID>: 1. In Settings > Custom Fields, create fields for Current Goal and Constraints, Ruled-Out Options and Why, and Next Single Action. 2. In AI Agents > Knowledge Base, store permanent project constraints and approved specifications as standalone entries. 3. In AI Agents > Conversation AI, inject the three custom fields at the top of the system prompt so new sessions preserve rejected options and the next step.
# Inspect custom fields and Conversation AI context handoff workflows in the sub-account ghl-crm custom-fields list --context <YOUR_CONTEXT> --location <YOUR_LOCATION_ID> ghl-crm workflows list --context <YOUR_CONTEXT> --location <YOUR_LOCATION_ID>
Official GHL MCP vs. ghl-tools: HighLevel’s official hosted MCP (services.leadconnectorhq.com/mcp) covers public v2 CRM records (contacts, opportunities, appointments, conversations). ghl-tools MCP complements it with workflow graph inspection & recipes, funnel/form builders, DNS/BIMI checks, and ghl-crm doctor audits.
| Step | Menu Path in GHL | Action |
|---|---|---|
| Step 1 | Settings > Custom Fields | Create three text fields for ongoing projects or multi-day client threads: Current Goal and Constraints, Ruled-Out Options and Why, and Next Single Action. |
| Step 2 | AI Agents > Knowledge Base | Store permanent project constraints, approved pricing tables, and technical boundaries as separate topic entries so the assistant can pull reference facts on demand instead of relying on chat history. |
| Step 3 | AI Agents > Conversation AI | Inject {{contact.current_goal_and_constraints}}, {{contact.ruled_out_options_and_why}}, and {{contact.next_single_action}} at the top of the prompt and test a fresh session by asking what the assistant should do next and what it should avoid. |
Connect Claude Code, Cursor, or OpenAI Codex to our ghl-tools MCP Server & Rust CLI to build workflows, forms, and funnels from your editor, or start your GoHighLevel plan through our partner link to unlock $612+ in ready-to-import kits (including GHL AI Agent Context Handoff & MCP Kit) and weekly live clinics.