Skip to content
Agentic Control Plane

Create your first AI agent in 5 minutes

Sign up, connect your tools, and create an agent that monitors, reports, or answers questions across your apps.

1. Sign up and see your dashboard

Go to cloud.agenticcontrolplane.com and sign in with Google or email. You’ll land on your home dashboard — a quick-launch pad with suggested prompts, your agents, and recent conversations.

Home dashboard showing quick prompts, your agents, and recent conversations
Your home dashboard — chat, run agents, and pick up conversations.
What can I do from the dashboard?
The dashboard is your home base. You can type a question into the chat box to query any connected tool, click a suggested prompt to get started quickly, run any of your agents on demand, or jump into a recent conversation. Everything starts here.

2. Connect your data and tools

Click Data in the top nav. This is where you give your agents the context they need — files, websites, and cloud services.

  • Upload files — drag in CSV, Excel, PDF, TXT, or JSON files (up to 10MB each)
  • Add web sources — paste any public URL and we’ll extract the content for your agents
  • Connect services — link GitHub, Jira, Linear, Salesforce, and more with one click via OAuth
Data Sources page showing uploaded files, web sources, and connected services
Upload files, add URLs, and connect cloud services — your agents can reference all of it.
How does connecting a service work?
Click Connect next to a service (like GitHub or Jira) and sign in with your account. ACP uses OAuth — we never see your password. Once connected, your agents can search issues, pull records, check calendars, and more. You can disconnect any service at any time.

3. Create an agent

Click Agents in the top nav, then + Create Agent. Give it a name, describe what it should do, pick a model, and choose a schedule.

For example: “Monitor Hacker News for posts about agentic AI and email me a summary every hour.” Your agent runs automatically on the schedule you set — or you can trigger it manually with Run.

Agents page showing agents with Run, Edit, Share, and Delete actions
Your agents — run on demand, schedule them, or share with your team.
What kinds of agents can I create?
Anything that can be described in plain language. Some examples:
  • Monitor a website for changes and send email alerts
  • Summarize your unread emails every morning
  • Pull open Jira issues and post a daily standup summary to Slack
  • Search your uploaded sales data and generate a weekly report
Agents can use any of your connected data sources and services.

4. Chat with everything you’ve connected

Click Chat to talk to your data. Your AI assistant has access to all your connected tools — ask questions across files, services, and agents in one conversation.

Every tool call shows what was accessed, is scoped to your identity, and is logged automatically.

Chat view showing a conversation with Google Calendar tool calls
Ask questions across all your tools — here, pulling meetings from Google Calendar.
Can I see what the AI accessed?
Yes. Every tool call is shown inline in the conversation — you can expand it to see exactly what was called, what data was returned, and whether it was verified. The Activity tab gives you a full audit trail across all conversations and agent runs.

5. Trigger agents from external systems

Your agents aren’t limited to the dashboard. Every agent gets an HTTP trigger endpoint that any external system can call — n8n, Zapier, Make, a cron job, or a plain curl command:

export ACP_KEY="your-api-key-here"

curl -X POST https://api.makeagents.run/<workspace>/agents/<profileId>/run \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $ACP_KEY" \
  -d '{"input": "Summarize open support tickets tagged urgent"}'

Create an API key from Settings > API Keys, then wire the endpoint into your automation. Every trigger goes through the same identity verification, policy enforcement, and audit logging as an interactive session.

Can I pass dynamic data to the agent?
Yes. Add a context object to your request with any key-value pairs — customer ID, ticket number, region, priority. These are injected into the agent's system prompt so the same agent profile can handle different scenarios. See the full API reference for details.

FAQ

Is it free?
Yes. The free tier includes 1,000 calls/month, 2 connectors, and unlimited seats. No credit card required.
What AI models can I use?
ACP supports multiple models including Gemini, GPT, and Claude. You configure which models are available in your workspace settings and bring your own API keys.
Is my data secure?
Yes. All connections use OAuth (we never store your passwords). Every request is tied to your identity and logged. PII detection and redaction is built in. Your data stays in your workspace — it's never shared across tenants or used to train models.
Can I use this with Claude Desktop, ChatGPT, or Cursor?
Yes. ACP exposes a standard MCP endpoint. You can point any MCP-compatible client — Claude Desktop, Claude Code, Cursor, Windsurf, Cline, Zed, or any other — at your workspace URL. Identity and governance are enforced on every request.
Can I invite my team?
Yes. Invite teammates from the workspace settings. Each person gets their own identity, permissions, and audit trail. You can also share individual agents with anyone via email.
Get started free →