A custom agent is a role you set up once that then works on campaigns for you: it comes up with ideas, plans them, and helps you take them live and review them through your connected tools. You decide which channel and tools it can touch, how often it runs, and whether it acts on its own or checks with you first.
Before you start
- You’re a manager of your team. Creating and editing agents is a manager-only setting.
- To let an agent use a tool beyond the built-in campaign tools, connect that integration first in Settings, under Integrations.
- Optional: if you want to focus the agent on one channel, set your channels up first.
Create an agent
- Go to Settings and open Agents.
- Select New agent.
- In Name, give it something you’ll recognise, such as “Social campaigns” or “SEO”.
- Optional: in Instructions, describe how it should approach its campaigns. The agent follows these every time it runs.
- Optional: pick a Channel to focus the agent on.
- The built-in Growth Method campaign tools are always on for every agent. Under Connected tools, choose which of your other connected integrations the agent may use. Tools you’ve disabled stay off.
- Set Runs to how often the agent should run: Off, Daily, Weekly, or Monthly.
- Choose its Autonomy (see below).
- Optional: pick a Provider and Model. Leave Model on Default unless you have a reason to change it.
- Select Create agent.
Your agent appears in the list with a Custom badge, alongside the built-in agents that power Growth Method.
How it runs your campaigns
Every campaign moves through the same stages, in the same order, every time:
Backlog → Planning → Live → Analysing → Complete.
These stages are fixed. An agent decides what happens within a stage, the plan, the copy, the results that matter, but it never chooses the order and never invents a step. Growth Method moves a campaign to the next stage in code, not by asking the AI, and only ever forward. It won’t run a campaign through the same stage twice, and an agent can’t skip ahead or loop back. This is the same track your team already uses for campaigns you run by hand.
That’s what makes an agent safe to leave running. However it plans or words a campaign, it can only move it along a track you already trust. The worst it can do is prepare the wrong campaign, not run away with your tools.
How far an agent takes a campaign
On a schedule, an agent prepares a campaign and then hands it to you:
- A Manual agent drafts a campaign idea and stops. It lands in your Backlog for you to review.
- An Autonomous agent goes one step further: it writes the plan and moves the campaign to Planning, then stops.
You decide what happens next. Moving a campaign to Live, and on to Analysing once it has run, is a step you take in the campaign view. Nothing an agent does on a schedule goes live without a person taking it there.
When you work with an agent in chat, you can go further in the same sitting, launching and reviewing a campaign together, step by step. When it reviews a campaign it waits for real results, so it won’t rush to a verdict or invent early numbers. It reviews a thirty-day test after thirty days, not on day one.
Tip: set Runs to Off while you’re trying an agent out, then switch it to Daily, Weekly, or Monthly once you’re happy with how it works.
Choose how much it does on its own
Autonomy controls whether the agent acts by itself or checks with you first:
- Manual: the agent drafts campaigns and waits for you to approve anything that changes a connected tool. It publishes nothing without your say-so. On a schedule, it leaves a draft in your Backlog.
- Autonomous: the agent acts without stopping to ask, including using your connected tools. On a schedule, it goes as far as writing the plan.
Whichever you choose, an agent can’t run away. A single turn is capped at a fixed number of steps, it can only move a campaign one stage forward, and it can’t repeat a stage, so it does the work in front of it and stops. Nothing reaches Live on a schedule without a person taking it there.
Start with Manual while you build trust in an agent, then move to Autonomous once you’re comfortable.
Warning: an autonomous agent uses your connected tools without asking first. Keep it on Manual until you’ve watched a few runs in chat and you’re happy with its work.
See what your agent did
Every run happens in a conversation, and that conversation is the record. For each stage, the agent’s actions and the results it got back are written into the thread, in order. Nothing it does is hidden.
You can reopen that conversation at any time to see exactly what the agent did and why, stage by stage, long after the run has finished. It’s the same thread you watch when you test an agent in chat.
Who is Ada Lovelace?
Ada Lovelace is the automation account that runs your campaigns when no one is at the keyboard. You’ll first meet her in your team’s member list, in Settings under Users, even though no one invited her. She belongs to every team by default.
A few things to know about her:
- She isn’t a person, and she never signs in.
- Once you’ve connected an integration, Ada starts sending you new campaign ideas automatically.
- When an agent runs on a schedule, it runs as Ada, and she’s credited as the author of any campaign it creates.
- She doesn’t direct the other agents. Every role runs either as you, when you work in chat, or as Ada, when it runs on a schedule. The steps and their order are the same both ways.
The name is a nod to Ada Lovelace, the 19th-century mathematician often regarded as the first computer programmer. Working with Charles Babbage on his Analytical Engine, an early mechanical computer, she wrote what many consider the first algorithm meant to run on a machine, and she saw what others missed: that such a machine could do far more than arithmetic. We named our automation account after her as a small tribute to that mix of method and imagination, the same qualities we built Growth Method around.
Try it in chat
You don’t have to wait for a scheduled run to see what an agent does.
- Go to Settings, open Agents, and select Edit on your agent.
- Select Test in chat.
- Watch the agent work through the campaign in the conversation, step by step.
In chat you see each step as it happens. With a Manual agent, you approve each action that touches a connected tool before it runs.
Next steps
- Connect more tools for your agent to use in Settings, under Integrations.