How to analyze your email performance with Active Intelligence
This guide is based on the What Happens When You Feed AI 21,000 Emails and Ask What to Do Next webinar, published on the AI Lab by ActiveCampaign.
Get the quick-start guide
What will I accomplish with this guide? By the end, you’ll have a repeatable way to ask ActiveCampaign’s Active Intelligence what your email data is telling you and turn its answers into concrete improvements for your next send. It’s based on the approach Evan and Mason from Scrappy ABM demonstrated live in this webinar, where they treat AI as a thought partner rather than a one-click report generator.
Before you start, you’ll need:
- An ActiveCampaign account with Active Intelligence available
- A campaign, webinar, or email sequence with enough send history to analyze
- Tags that identify the events or campaigns you want to ask about
- A specific goal in mind before you open the prompt box (a better subject line, higher open rate, content to reuse)
Quick reference
- Total time: 15–30 minutes per analysis
- Tools needed: ActiveCampaign Active Intelligence
- Key output: A prioritized list of feedback on what worked, what didn’t, and what to change for your next campaign
Watch this section
For full context on the following topics, watch these sections of the webinar:
- Why a vague prompt gets vague data, and how to ask better—[19:04]–[20:42]
- The live Active Intelligence analysis of a webinar—[24:10]–[25:19]
- Evan’s three-step recap of the approach—[30:27]–[31:00]
The workflow
Phase 1: Frame the question, not the command
After this phase, you’ll have: a clear, specific request that gives Active Intelligence enough context to respond usefully.
- Ask what the AI needs first: open with a question like “what do you need from me in order to assess my latest webinar?” so it tells you what data to provide.
- Supply the specifics: name the tag, the campaign, and your goal rather than typing a vague command like “analyze my email campaign.”
- State the outcome you want: tell it whether you’re after a better subject line, content to reuse, or a read on engagement.
That vague prompt that you see like ‘analyze my email campaign’, with that, you’re gonna get vague data and results back.
Phase 2: Run the analysis inside your account
After this phase, you’ll have: Active Intelligence’s read on a specific campaign, grounded in your own send data.
- Open Active Intelligence in your account: work from your real data, not an export.
- Point it at a specific campaign or tag: for example, ask how many emails referenced a topic like ICP development and which performed well.
- Read the prioritized output: expect a short list of two to three items to act on, plus a breakdown of what drove performance.
Phase 3: Iterate and apply
After this phase, you’ll have: a refined set of recommendations you can carry into your next send.
- Don’t accept the first answer: give it a couple of iterations, adding context each time to sharpen the response.
- Set guardrails: tell it what to focus on so it doesn’t wander; treat it like a capable intern that needs direction.
- Apply one improvement at a time: pull the strongest recommendation into your next campaign and aim to get a little better with each send.
AI is the best intern that has access to everything, but you have to give it guardrails of what to focus in on.
Related
More data from the AI Lab.