An assistant that remembers your returning visitors
Use owned content to answer visitor questions with less friction.
7-day free trial
What this feature covers
Why it matters
The practical reason to use it.
Most website assistants forget everything the moment a tab closes.
How it works
A step-by-step look at the workflow.
Step 1
As a visitor chats, the assistant identifies facts and preferences worth remembering, such as a preference, a past issue, or context that.
Step 2
Each fact is saved as a categorized memory backed by vector embeddings, so it can be recalled accurately later even if it's.
Step 3
On a later visit, the assistant recalls the relevant memories for that same person and picks the conversation up with context instead.
Step 4
Your team can list, add to, or delete stored memories at any time, so what the assistant remembers stays accurate and under.
Core job
The main job this feature handles.
Automatic capture
The assistant identifies and saves key facts and preferences while a conversation happens naturally.
Vector-backed recall
Memories are backed by vector embeddings so relevant facts surface accurately later, even worded differently.
Categorized memories
Facts are grouped by category, so preferences, context, and history stay organized instead of one long note.
Recall on return
When a visitor comes back, the assistant recalls what it already knows instead of starting the conversation cold.
Daily use
How teams use it after launch.
List stored memories
Review every memory saved about a visitor, so nothing the assistant recalls is a surprise.
Delete on request
Remove a memory immediately when a visitor asks or a saved fact is no longer accurate.
Save mid-conversation
Let the assistant save a new preference or fact the moment a visitor shares it.
Per-person scope
Memories stay tied to the individual visitor, not shared across every conversation on the site.
Control points
What to keep controlled.
Returning customers
A shopper who already shared their size, plan, or preference does not have to repeat it next visit.
Support continuity
A visitor who explained their issue last week does not have to start the story over.
More personal answers
Recommendations and answers reflect what the assistant already knows about that specific person.
Works across sessions
Memory persists between separate conversations, not just within a single chat window.
What you get
The changes teams should notice first.
- Fewer repeated questions from returning visitors
- More personal answers based on known preferences
- Faster support when context carries over between visits
- Full visibility and control over what the assistant remembers
The facts do the selling
Plan facts, platform capabilities, and worked examples — every claim here is checkable, not a pitch.
White-label included — never a paid add-on. Copyright removal from $98/mo. Full white-label — custom domain, branded portal, your-domain emails — from $198/mo.
The white-label wedge
Platform fact
Training runs on your sitemap, PDFs, docs, and YouTube transcripts. Answers cite the source pages they came from.
Trained on your content
Platform fact
Five clients at $300/mo on a $198/mo Agency plan is $1,300+ of monthly margin before usage.
A 5-client agency on one flat plan
Worked example
Your questions, answered.
Tap any question about the product, pricing, security, or setup to see a straight answer.
InsertChat
Answers about InsertChat
Hi! Tap any question below and I'll answer it for you.
Memory questions
What does the assistant actually remember?
It stores facts and preferences worth recalling later, saved as categorized memories per person and backed by vector embeddings for accurate retrieval. Casual chit-chat isn't stored, only details that make the next conversation more useful. The operational question is whether memory makes the workflow clearer once real conversations, real ownership, and real edge cases show up. That is the bar teams should use before they expand the rollout across more assistants, more channels, or more teams.
Can I see or delete what's remembered about someone?
Yes. Memories can be listed, saved, recalled, and deleted, so your team always knows what the assistant knows and can remove anything that's outdated or requested to be removed. The operational question is whether memory makes the workflow clearer once real conversations, real ownership, and real edge cases show up. That is the bar teams should use before they expand the rollout across more assistants, more channels, or more teams.
When is memory not a good fit?
If your traffic is almost entirely one-time, anonymous visitors, there isn't much for memory to recall on a return visit. It's most valuable where the same people come back more than once, such as support, repeat purchases, or ongoing accounts. The operational question is whether memory makes the workflow clearer once real conversations, real ownership, and real edge cases show up. That is the bar teams should use before they expand the rollout across more assistants, more channels, or more teams.
Ready to get started?
Start your 7-day free trial. Review current trial terms.
7-day free trial