Does Brevo Remember Between Runs?
Does Brevo Remember Between Runs? No. A Brevo automation holds no memory of its own between runs. When a contact enters an automation, Brevo reads that contact exactly as the record stands at that moment: the current attribute values, the lists the contact belongs to, and the segment conditions the contact matches right now. Anything an earlier run worked out survives only if that run wrote it back onto the contact first, as an attribute value, a list change, or a tag-like marker a later step c
Does Brevo Remember Between Runs?
No. A Brevo automation holds no memory of its own between runs. When a contact enters an automation, Brevo reads that contact exactly as the record stands at that moment: the current attribute values, the lists the contact belongs to, and the segment conditions the contact matches right now. Anything an earlier run worked out survives only if that run wrote it back onto the contact first, as an attribute value, a list change, or a tag-like marker a later step can check.
That distinction is easy to miss because Brevo feels continuous. Contacts, automations, and logs are all still there tomorrow. The continuity lives in stored contact records and automation definitions, not in a memory that one run hands to the next.
What does a Brevo contact actually hold?
The contact record is where durable state lives. Every contact carries identifiers such as an email address, a phone number, and a WhatsApp number, plus a set of attributes: default fields and custom attributes a team defines for its own needs, such as a plan, a language, a registration date, or a last purchase category. Imports, forms, the API, and automation steps can all write those values, and every later automation reads the values as they stand.
Around the attributes sit lists and segments. A contact can belong to several lists at once, and segments rebuild themselves from attribute and activity conditions, so membership updates as the underlying values change. Engagement lands on the record too: sends, opens, clicks, and transactional events are logged against the contact, and conditions inside an automation can branch on that activity.
All of that works reliably, and all of it is current state. A later automation reads values, memberships, and event counts. It does not recover why a contact was given an exception, which offer was already refused last quarter, or what was promised in a support thread last week, unless someone stored that thread as an attribute value in the first place.
How do Brevo automations actually run?
An automation is a series of steps set in motion by a trigger. The trigger can be a contact added to a list, a contact matching custom filters or a segment, an anniversary date held in an attribute, a website or purchase event, or a manual enrollment. Once a contact meets the entry conditions, that contact moves through the steps one at a time: send an email, SMS, or WhatsApp message, wait for a delay or for an action, split on an if/else condition or an A/B test, update a contact attribute, add or remove a list, or create a task.
When a contact has no further actions, that contact exits the automation. Whether the same contact can enter again is a setting chosen when the automation is built: some automations allow entry more than once, others run a contact through a single time. A contact can also sit inside several automations at the same time, a welcome series, a birthday automation, and a re-engagement automation, and each one runs independently, tracking its own position for that contact and ignoring the others.
That position is real, and it is narrow. An automation knows where one contact stands inside its own steps. It does not know what a different automation decided about the same contact, what an external scenario changed overnight, or why a step was written the way it was. And an attribute only changes when an import, an integration, or an update step writes it. Nothing in an automation automatically turns what the run learned into a note the next run can read.
What about workflow logs and transactional logs?
Brevo keeps thorough records. Workflow logs show the steps a contact took through an automation, visible in real time while the contact is moving and reviewable afterwards. Transactional logs track what happened to transactional emails sent by API, SMTP, or automation: sent, delivered, opened, clicked. Those logs are stored indefinitely by default, with a custom retention period available for teams that want one.
Those records answer what happened. They are not working memory the next run consults before acting. An automation does not open last month's workflow log to learn why a branch underperformed, and an AI step drafting the next message does not recover the earlier draft, the rejected subject line, or the reasoning behind a split from the log. The history is there for a person to review. The next automated run starts from the contact record in front of it.
The gap shows up in routine work. A scheduled agent that reviews automation performance every Monday, drafts the next test, and checks it against what contacts were already promised has to be handed the numbers, the angle already used, and the promise already made, every single week. The automation fires on time. The context arrives by hand, or not at all.
Where this leaves agents working from Brevo
Brevo is often one part of a wider setup. A store or a CRM sends events in, an n8n, Make, or Zapier scenario updates contacts and lists, and planning happens in a chat tool somewhere else. Each part can read the same current attributes and logs. None of them inherits the conversation behind those values.
So the work turns into re-briefing. Background gets pasted into a prompt again, a question answered in another tool gets asked again, and automation instructions grow longer to cover for context the next run cannot see on its own.
One memory that every run can read
The fix is a memory layer that lives outside any single contact 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 Brevo 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 an attribute value on a contact.
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. Brevo stays the system of record for contacts and sends. Vilix AI becomes the system of record for the thread behind them, and the re-briefing cycle ends.
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.