Does Kit Remember Between Runs?

No. A Kit automation holds no memory of its own between runs. When a subscriber enters an automation, Kit reads that subscriber exactly as the record stands at that moment: the tags currently attached, the custom field values currently stored, and the segments the subscriber currently matches. Anything an earlier run worked out survives only if that run wrote it back onto the subscriber first, as a tag, a field value, or a sequence position a later step can check.

That distinction is easy to miss because Kit feels continuous. Subscribers, sequences, and automations are all still there tomorrow. The continuity lives in stored subscriber records and automation definitions, not in a memory that one run hands to the next. Kit, formerly ConvertKit, keeps one list for the whole account.

What does a Kit subscriber actually hold?

The subscriber record is where durable state lives. Every subscriber carries an email address and a first name, plus two organising layers a team builds for itself. Tags are fixed labels attached to a subscriber: purchased a product, downloaded a lead magnet, joined a launch, asked not to hear about a topic. A tag is binary, either it is on the subscriber or it is not, and it stays until something removes it. Custom fields hold values instead: a plan, a renewal date, a preferred topic, a score. Kit stores those values as plain text, and forms, landing pages, imports, and automation steps can all write them.

Segments sit above both layers. A segment is a saved filter over tags, fields, forms, and activity, and its membership rebuilds itself automatically as the underlying records change.

All of that is current state. A later automation reads tags, values, and memberships. It does not recover why a subscriber was given an exception, which launch angle was already tried last quarter, or what was promised in a reply thread last week, unless someone stored that thread as a tag or a field value.

How do Kit automations actually run?

Kit offers two automation shapes. A Visual Automation is a flow built from entry points, actions, events, and conditions. Entry points include joining a form or landing page, a tag being added, a custom field changing, and a product being purchased, with up to five entry points on one automation. Actions add a sequence, wait on a delay, add or remove a tag, set a custom field, or move a subscriber into another automation. Events pull a subscriber forward when a tag changes, a date arrives, or a field changes, and conditions split the flow into paths based on tags, fields, and filters. Visual Automations and sequences sit on the paid Creator and Pro plans.

Rules are the simpler shape: one trigger paired with one action, such as subscribing to a form adding a tag, or completing a sequence removing one. The difference matters for sequences. Added through a Rule, a subscriber stays subscribed to the sequence, so emails added to that sequence later still reach that subscriber. Added through a Visual Automation, the subscriber is held at the sequence step inside the flow, marked completed when the last email is received, and then moves on, so later additions pass that subscriber by.

Position inside a flow is real, and it is narrow. An automation knows where one subscriber stands inside its own steps. A subscriber can sit inside a welcome flow, a launch flow, and a re-engagement flow at the same time, and each one tracks its own position and ignores the others. None of them knows what a different automation decided about the same subscriber, or why a step was written the way it was. And a tag or field only changes when something writes it. Nothing automatically turns what a run learned into a note the next run can read.

What about sequence history and subscriber activity?

Kit keeps a visible record. A subscriber profile shows the tags attached, the field values stored, the sequences and automations that subscriber has entered, and the activity around sends, opens, and clicks. That profile answers what the account currently believes about a person and what was sent to that person.

That record is not working memory the next run consults before acting. An automation does not open last month's launch notes to learn why a branch underperformed, and an AI step drafting the next broadcast does not recover the earlier draft, the rejected subject line, or the reasoning behind a split from the profile. The history is there for a person to review. The next automated run starts from the subscriber record in front of it.

The gap shows up in routine work. A scheduled agent that reviews launch performance weekly, drafts the next test, and checks it against what subscribers were already promised has to be handed the numbers, the angle already used, and the promise already made, every week. The context arrives by hand, or not at all.

Where this leaves agents working from Kit

Kit is often one part of a wider setup. A checkout sends purchase events in, an n8n, Make, or Zapier scenario updates tags and fields, and planning happens in a chat tool somewhere else. Each part can read the same current tags, fields, and segments. None of them inherits the conversation behind those values. So the work turns into re-briefing: background gets pasted into a prompt again, and a question answered in another tool gets asked again.

One memory that every run can read

The fix is a memory layer that lives outside any single subscriber or automation, so every run and every tool works from the same past. Vilix AI is built for exactly that job, for scheduled agents and automations that start blank.

Vilix AI is cloud-hosted, with zero infrastructure to run or maintain. Connect it once over MCP and the same memory is available everywhere the work happens: alongside Kit automations, in n8n, Make, and Zapier scenarios, and in the AI chat tools used to plan and review the work. What gets stored is full conversation history, not just facts extracted from it, so a later run can recover the exact agreement, the reason a decision was made, and the wording that was already used, not only a tag or a field value on a subscriber.

The loop is simple. Before acting, a run retrieves the relevant history for the work it will touch. It acts with that history in hand. Then it saves what it did and what it learned back to the same memory. Kit stays the system of record for subscribers and sends. Vilix AI becomes the system of record for the thread behind them, and the re-briefing cycle ends.

Get Started for Free

Free forever, no credit card. The free plan is free forever, the 7-day Pro trial needs no credit card, and your memory stays under your control: export everything or delete it anytime.