Email campaign performance recap
After each email campaign, an agent pulls results, compares them with recent campaigns, and writes a short recap of what stood out and questions to test next for the marketer to review.
The use case
Small teams send emails every week but rarely look back at what worked. Platform dashboards show numbers, but nobody writes down why one subject line did better or which segment stopped clicking. A few days after each campaign, the agent pulls opens, clicks, conversions, unsubscribes, and revenue where tracked from the email platform. It compares them with the last several campaigns of a similar type, notes which links got clicks, and identifies segments that performed differently. It writes a short recap in plain English with possible explanations clearly labeled as guesses and one or two ideas to test next time. The marketer reviews the recap, corrects any wrong reading, and decides what to try. The agent does not send emails, change lists, or edit automations.
Example workflow
- Three days after each campaign, the agent pulls results from Klaviyo or Mailchimp.
- It compares key numbers with the last several campaigns of the same type stored in Google Sheets.
- It lists top-clicked links and segments that performed noticeably better or worse.
- It drafts a short recap with observations, labeled guesses, and one or two test ideas.
- The recap is posted to Notion, where the marketer edits it and records decisions for the next campaign.
- A monthly roll-up groups recaps so patterns across campaigns are easier to see.
Tools
- Klaviyo
- Mailchimp
- Google Sheets
- Notion
- Claude
- Slack
Risks and guardrails
- Open rates are distorted by privacy features in email apps — guardrail: the recap leads with clicks and conversions and notes that opens are less reliable.
- Guesses are read as facts — guardrail: explanations are labeled as possible reasons, not findings.
- Small segments produce misleading differences — guardrail: the agent shows the size of each segment and skips comparisons below a set size.
- The agent changes lists or automations — guardrail: it uses read-only reporting access.
Related recipe
Weekly KPI Digest from Google Sheets with Source-Cited Numbers: An agent reads your defined metrics from Google Sheets, compares them to last week and targets, and drafts a plain-English digest where every number cites its cell. The owner approves before it goes to Slack or email.
Want it set up for you? Request a quote.
Sources
Written by Agents Lookup. Credits and official pages for the tools this use case names:
- Klaviyo MCP server (official page): developers.klaviyo.com/en/docs/klaviyo_mcp_server (checked 2026-11-09)
- Mailchimp (official page): mailchimp.com (checked 2026-11-09)
- Notion MCP server (official page): developers.notion.com/guides/mcp/overview (checked 2026-11-09)
- Claude (official page): claude.ai (checked 2026-11-09)
- Slack MCP server (official page): docs.slack.dev/ai/slack-mcp-server (checked 2026-11-09)