Wake up to product work already done.
Session replay and product analytics. Sequential judges your sessions and ranks the ones worth watching.
Every morning your agent asks Sequential what went wrong for your users. It files the work, opens the fix and checks last week's results. You review and approve.
- Mon 08:00 Read 2,140 sessions judged since Friday Sequential
- 08:01 New finding: people stuck at the shipping address, 38 people Sequential
- 08:02 Filed WEB-231 with three sessions as evidence in Jira
- 08:06 Opened a fix: “Accept spaces in postcodes” in GitHub
- 08:07 Asked #web-team to review it in Slack
- 10:40 You reviewed and merged it you
- Wed 14:20 Release 2026.10.09 recorded by your deploy Sequential
- — a week later —
- Mon 08:00 Measured last week's fix: 41 % → 12 % of sessions on the shipping page Sequential
- 08:01 Closed WEB-231 and posted the result in Jira · Slack
Works with the agent you already use
- Claude Code
- Cursor
- Codex
- Claude Desktop
Works with the SDK you already ship
sequential.js, or the analytics SDK already in your app. No re-install.
- Web
- iOS
- Android
- React Native (unverified)
- Flutter (unverified)
Four mornings
It handles the list. You handle the decisions.
error after release A release breaks search
- Wed 08:00 New finding since release 2026.10.11: search throws an error Sequential
- 08:00 21 people, all after the release, none before Sequential
- 08:03 Opened a revert of the search change, linked to the finding in GitHub
- 08:04 Posted the three sessions in #search in Slack
- 09:15 You approved the revert you
- 11:20 Revert released, recorded by your deploy Sequential
- — next morning —
- Thu 08:00 Measured: 0 sessions hit the error since the revert Sequential
Examples from a fictional shop. Your agent, your tools, your numbers.
Before and after
Before and after Sequential.
One connection instead of a dozen tabs.
| Task | Without Sequential | With Sequential |
|---|---|---|
| Find what hurt your users | Watch replays one by one, or wait for a support ticket. | Sequential judges each session against a set of questions you can edit. The ones to look at come first. |
| Answer a product question | Build a chart, then guess why. | Ask in one sentence. You get the sessions that match. |
| Turn a problem into work | Write the ticket by hand and add screenshots. | Your agent files it with the evidence: the sessions, the count, the moments. |
| See how the numbers moved after a fix | Ship it, then compare dashboards by hand. | Sequential records the release and measures the same problem after it. |
| Give your agent product context | Paste screenshots and exports into a chat. | Connect once. Your agent reads sessions, findings and events itself. |
| Add session replay | A second vendor and a second SDK. | One more line under the SDK you have. Your events show on the timeline. |
Every tool you already connected
One connection reaches all your tools.
Your agent already works in your team's tools. Connect Sequential to your agent once. Then your agent can take what happened to your users into each of those tools. Sequential itself connects to none of them.
- Sequential
What happened to your users: findings, counts, releases and measurements.
- Your agent
Reads it on a schedule and does only the work you allow.
- Your tools
- Jira
- Linear
- GitHub
- Slack
- Notion
And any other tool you connected to your agent.
You stay the pilot
Autopilot, not autonomy.
You decide what your agent may touch. A person still reviews, approves and designs. Sequential keeps the record: every finding, every release, every measurement after it.
Set it up once
Three steps, then it runs every morning.
-
Send your sessions
Add sequential.js to your app, or point the analytics SDK you already ship at Sequential. No re-install.
-
Connect your agent
Claude Code, Cursor, Codex or Claude Desktop. One token, scoped to what it may see.
-
Give it a morning
In your agent’s scheduler: “Every weekday at 08:00, work through what’s new in Sequential.”
What preview means
Sequential is free while it is in preview. You need no card. Each organisation has a monthly session allowance, and we email you at 80 % and at 100 %.
We keep your events and replays for 7 days.
We change features often while we build. Tell us what you need.
Put your product on autopilot.
Sequential is in preview. Get in early.
Can't be bothered? Tell your agent to do it.
Paste this into your coding agent, for example Claude Code or Cursor.
ChatGPT: web chat; it cannot edit your app.
Show the prompt
Set up Sequential (session analytics and replay) in this app with a free trial. Ask me for my email address. Then send POST https://api.usesequential.com/api/agent/provision with the JSON body {"owner_email": "<my email>", "platform": "web"} (or "ios", "android" or "react-native", to match this app). Add the answer's install.snippet to the app, run the app on localhost, and keep mcp.url and mcp.token to read the sessions. Do not put the token in source control. Everything you need is in the answer. Then tell me to claim the trial from the email Sequential sends me.- Your agent creates a trial project and installs Sequential in your app.
- You get an email from Sequential.
- Open the link in the email and claim the project. A trial that nobody claims is erased after 72 hours.