All approved
Integrations/Gemini/Setup
Ge

Gemini · Function Calling

Gemini Setup

Connect Gemini via function calling, MCP, or REST fallback.

Connection endpoints

AiM Continuity API base URL

/api

OpenAPI schema URL

/api/openapi.json

MCP server URL

/mcp

Copy these into your Gemini configuration. The actual API key is never shown here.

Supported connection methods

Function CallingRemote MCPREST / OpenAPI Action

Setup steps

  1. 1.Import the AiM OpenAPI schema to generate Gemini function declarations.
  2. 2.Alternatively, add the AiM MCP server URL where remote MCP is supported.
  3. 3.Set the Bearer credential in the function-calling auth configuration.
  4. 4.Verify Gemini can call the read and recommend tools.
  5. 5.Run a test request to confirm the connection.

Authentication

  • ·Authentication: Bearer token on every AiM call.
  • ·Provide the key through Gemini's tool auth configuration, not in the prompt.
  • ·REST is available as a fallback where MCP/function calling is unavailable.

Example request

http
POST /api/continuity/intake
Authorization: Bearer YOUR_AIM_CREDENTIAL
Content-Type: application/json

{
  "provider": "gemini",
  "conversation": { "title": "Strategy sync" },
  "organization": { "primary_project": "Website Redesign" },
  "tasks": [{ "title": "Follow up with design", "status": "OPEN" }],
  "recommendations": [{ "action": "ASSIGN_TO_PROJECT", "confidence": 0.8 }]
}

Gemini setup prompt

Paste this into Gemini's system / instructions so it knows how to push conversations, decisions, tasks, and ideas into AiM Continuity as PENDING REVIEW.

prompt
You are connected to AiM Continuity, my work-intelligence layer, via Gemini
function calling.

When I describe or reference work — a conversation, decision, task, idea, or
asset — ALWAYS submit it to AiM using POST /api/continuity/intake with:

{
  "provider": "gemini",
  "source": "gemini_function_calling",
  "external_conversation_id": "<current conversation id or slug>",
  "conversation": { "title": "<title>", "summary": "<summary>", "date": "<ISO date>" },
  "organization": {
    "primary_project": "<project>",
    "workstream": "<workstream>",
    "related_projects": ["<related>"],
    "brands": ["<brands>"],
    "websites": ["<urls>"]
  },
  "decisions": [{ "title": "<decision>", "status": "PROPOSED" }],
  "tasks": [{ "title": "<task>", "priority": "HIGH|MED|LOW", "status": "OPEN" }],
  "ideas": [{ "title": "<idea>" }],
  "assets": [{ "name": "<name>", "type": "url", "url": "<url>" }],
  "recommendations": [{ "action": "ASSIGN_TO_PROJECT", "reason": "<why>", "confidence": 0.8 }]
}

Before submitting, call GET /api/search?q=<topic> and GET /api/projects to
check for existing records. If a record exists, recommend UPDATE EXISTING.
All submissions land as PENDING REVIEW for a human to approve.

First connection test

After connecting, have Gemini run these two prompts. The second must land as PENDING REVIEW — never auto-approved.

1. “Show me my active AiM Continuity projects.”
2. “Recommend adding a task called Test AiM Connection to my selected project.”

Guided setup

Prefer a guided flow? Use the connection wizard to choose a method, create a credential, test, choose permissions, and finish — in six steps.

Open the wizard

Principle

AI Recommends. Humans Decide. Gemini may read organizational records and submit recommendations, but may never delete, approve its own work, or change configuration.