Does Kayako Remember Between Runs? The Timeline Survives. The Reasoning Does Not.
Does Kayako Remember Between Runs? The Timeline Survives. The Reasoning Does Not. Short answer: Kayako keeps the customer, not the run. A customer is remembered across every channel through a single timeline. A conversation keeps its messages, its internal notes, and its place in that timeline. None of that keeps what a scheduled agent worked out while reviewing those conversations, so the next run opens the same complete history and starts its thinking from zero. Open any ticket in Kayako and
Does Kayako Remember Between Runs? The Timeline Survives. The Reasoning Does Not.
Short answer: Kayako keeps the customer, not the run. A customer is remembered across every channel through a single timeline. A conversation keeps its messages, its internal notes, and its place in that timeline. None of that keeps what a scheduled agent worked out while reviewing those conversations, so the next run opens the same complete history and starts its thinking from zero.
Open any ticket in Kayako and nothing looks forgotten. The customer's earlier tickets, purchases, and activity sit beside the new message in one view. Under that complete surface, each outside run still starts with only the records in front of it, and none of the reasoning from the run before.
What a customer keeps between conversations
Kayako is built around one idea: every ticket should open with the customer's full history beside it. That history lives in SingleView, a unified customer timeline that consolidates every email, chat, and social interaction into one record. When a conversation opens, purchase data, previous tickets, and satisfaction scores surface automatically.
The profile behind that timeline is detailed. It shows tickets, purchases, orders, devices, entitlements, and subscription details at a glance, with health, churn, and satisfaction scores added on top. An organization view groups every contact from the same company. The timeline also pulls from connected systems, including Salesforce, Shopify, Stripe, and any custom source connected through the API or webhooks.
Channels do not split that history. Email, live chat through Messenger, social messages, WhatsApp, web forms, voice, and SMS all flow into one inbox and into the same timeline. A customer can start on email, continue on chat, and finish on the phone, and the agent still sees one continuous story in chronological order. For human support, that is a strong answer.
What a conversation keeps
Inside Kayako, support work is held in cases. A case carries a subject, a department, a status, a priority, and a type, and each reply inside it is stored as a post. Statuses move through new, assigned, waiting, and resolved. Internal notes keep team discussion private inside the same record, so the handling of a case stays attached to the case itself.
Kayako also remembers team decisions in advance through automations. The automation engine uses two structures. Triggers are event-based: they act the minute a conversation is created or updated and matches their conditions, assigning it to a team, changing its priority, adding a tag, or sending a notification. Monitors are time-based: they run every hour and act on conversations that match time conditions, such as a conversation approaching an SLA breach, and they can escalate priority and notify a team leader.
The Kay AI agent adds another layer inside the same boundary. Kay classifies, prioritizes, and routes incoming tickets, drafts replies from customer history and the knowledge base, and learns from how agents resolve the cases handed to it. Every one of these layers serves the record in front of the agent. None of them is a memory for work done outside Kayako.
What a scheduled run does not keep
Now place a scheduled agent next to that record. The agent runs on a timer, perhaps each morning in n8n, Make, or Zapier, to review new Kayako conversations, group them by topic, flag customers who have contacted the team repeatedly, and draft follow-ups for the cases that need them.
Run one reads the timeline. It works out which cases were billing questions, which match a known help center gap, and which customer has raised the same issue three times across three different channels. That judgment is the valuable part of the run. When run one ends, where does that judgment go? Not into Kayako as run memory. SingleView keeps the customer's history. A case keeps its posts and its status. None of them keeps a review layer from an outside run, ready for the next run to load. So run two re-reads, re-groups, and re-decides. If run one spotted a pattern across thirty cases, run two has to spot it again.
That is the gap behind the question in the title. Kayako remembers the customer. A scheduled workflow around Kayako does not remember its own work between runs unless a memory layer outside Kayako carries it.
Why writing notes back is not the same as memory
One workaround is to push everything back into an internal note or a tag on each case. That helps a person who opens that one case later. It helps less when the next run needs the whole picture across every customer. A note sits inside one case, while agent memory needs to be searchable across runs and across tools. A tag can say a case was urgent. It cannot carry why the run grouped ten cases together or what it planned to check next. The fix is to give every run the same place to load context from and save context to, outside any single help desk.
Give the runs one shared memory
Vilix AI is that shared place. It is cloud-hosted, so there is zero infrastructure to run or maintain. The memory sits in the cloud, not on one laptop or inside one automation.
Every connected tool reaches the same memory over MCP. A scheduled agent in n8n, a tool used for drafting, and an assistant used for analysis can all load from and save to the same Vilix AI memory. The same memory follows the work everywhere, across tools and devices.
Vilix AI stores full conversation history, not just facts pulled out of it. That matters for review work. A short fact can say a customer was frustrated. The full conversation shows what was promised, what changed, and why the run decided to escalate.
With that layer in place, the Kayako workflow changes in a simple way. Run one saves its grouping, its flags, and its open questions to Vilix AI when it finishes. Run two loads that saved work first, then reads only the new cases in Kayako. The pattern spotted on Monday is still known on Tuesday.
Start free, keep control of the data
Vilix AI has a free plan forever, with no time limit forcing a decision. Paid plans start with a 7-day Pro trial with no credit card required, so the full workflow can be tested on real cases before any payment.
Data stays under the team's control. Everything can be exported at any time, and everything can be deleted at any time. Nothing is locked in as the price of remembering.
Get Started for Free Free forever, no credit card.
Kayako will keep doing its part well. Customers will be recognized on every channel, timelines will stay complete, and cases will keep their posts and statuses. Add one shared memory for the runs around it, and the thinking survives too. The next run then starts where the last run stopped, instead of reading the same history and calling it a fresh start.