A few weeks ago I wrote about our vision for the agent era: Agents should be able to run on HubSpot and run HubSpot. I want to delve into what “running HubSpot” actually means and our latest step in bringing this vision to life.
Companies don’t send employees to HubSpot just to work. They’re sending officers. And these agents must be able to act as effectively as possible on your behalf, wherever they operate.
This last part is important. An agent is not always running in one place, on one infrastructure.
With AI Connectors, HubSpot context and actions are already available in Claude, ChatGPT, and other environments where teams work. Now we are adding another agent infrastructure: Command Line Interface (CLI).
Introducing the HubSpot Agent CLI
The HubSpot Agent CLI brings HubSpot data and intelligence to the environments where GTM and operations teams are composing their workflows – Codex, Claude Cowork, and Claude Code – and enables agents to automate repetitive, bulk, and scheduled work.
The simplest way to think about it: take questions you’ve asked or tasks you’ve completed repeatedly in chat and automate them. Build automations in Codex or schedule them in Cowork, and the work will happen on its own before you even get to your desk.
It’s built on the same foundation as our public APIs and MCP server that already power our AI Connectors, and is designed to complement them, not replace them. AI connectors are great for work where a human is involved and talking to an agent: questions, insights, conversations, campaign analysis. The agent CLI can also help agents perform these tasks, but it is especially useful for repetitive, bulk, and scheduled work that needs to be performed without a human involved.
How the Agent CLI empowers agents working on HubSpot
The HubSpot Agent CLI will help GTM and operations teams automate and schedule routine tasks, reports, and actions so you have more time to spend on work that matters. You will no longer have to ask the same thing multiple times. For example:
- A marketer might request a report every Monday at 8 a.m. that provides high-level leads with no associated deals, no recent sales activity, or missing key enrichment fields, then send RevOps a prioritized cleanup list with suggested next actions.
- Sales and RevOps might run a daily pipeline scan for deals closed this week that have had no activity in the last five days and ask for a summary.
- Customer Success may get an automated account review that summarizes open deals, recent support activity, and the latest NPS score for each account in the book of business.
- Support could set up an automation for each time a new ticket comes in from a higher-level account, the agent pulls the last five tickets from the contact, summarizes each resolution, and flags recurring issue patterns.
The work happens in the background, ready when you need it.
Why agent infrastructure optionality matters
We’re building a platform where agent infrastructure is a choice your agents make based on what’s right for your workflow.
An agent tied to an infrastructure is less effective than it could be. Just as customers should have the freedom to choose the best tools for their business, agents should have the same freedom. Optionality allows agents to choose the best infrastructure for the task at hand so they can operate in the most efficient way, whether they are running a scheduled automation, processing a mass operation, or acting on a real-time signal.
The direction is clear: wherever agents work and whatever infrastructure they operate on, HubSpot supports it. Here’s what building for the Agent Age looks like.
The HubSpot Agent CLI is now available in private beta, and anyone interested can sign up Here.
