Releasesby IbisSession Replay: Mobile Wireframes for Mixpanel Agent
BetayesterdayUnverifiedAdded Oct 15, 2026
Web replays record page structure, so Mixpanel Agent can read them, summarize them, and answer questions about them. Mobile replays are a series of image snapshots with no structure underneath, so Agent couldn't do any of that for mobile. To learn what happened in a mobile session, you had to watch it.
Topics: AI agents, SQL, Governance, Developer tools
More Mixpanel releases
Every Mixpanel releaseSession Replay: Flutter Autocapture (Taps and Frustration Signals)
Flutter apps had autocaptured screen views, but nothing about what users tapped. Native Android and iOS autocapture can't see Flutter elements because Flutter draws its own UI, so Flutter teams still had to add a track call to every element by hand. Rage taps and dead taps went unnoticed.
Experiments: Built-in Sample Size Calculator
Working out how many exposures or how much time an experiment needed used to mean leaving Mixpanel. You'd look up your metric's historical baseline and traffic, then type them by hand into the calculator on our website. The sample size calculator is now built into experiment setup.
Feature Flags: Semantic Version Targeting for Runtime Properties
Targeting a rollout by app version was hard to get right, especially for non-engineers. Version strings were compared as text, so 2.10.0 sorted below 2.9.0 . Runtime properties now support semantic versions, so you can target rollouts based on app version and have versions compared correctly. This builds on typed runtime property values released in August.
Session Replay: Mobile Autocapture (Taps and Frustration Signals)
Mobile autocapture only covered screen views, so teams could see which screens people visited but not what they tapped. Answering "did anyone tap this button?" meant adding a track call to every element by hand, then waiting for an app store release.
Agent Intelligence is now in Beta
Agent Intelligence brings your AI agent data into Mixpanel, right next to the product data you already track. You can now see how your agent is used, fix issues faster, and measure whether it's driving the outcomes you care about.
What's included
- Agent overview: Conversations, turns, cost, latency, errors, models and tool calls are rolled up automatically, with no dashboard to build. Conversation view: Open any conversation to see every turn and span in order. Slow, expensive or failing steps stand out right away.
Setup
There's no new SDK. Point your existing OpenTelemetry exporter at Mixpanel and include a user ID, and every span lands in your project as an event. Ingested spans count toward your normal event volume.
Availability
Agent Intelligence is in early access. Request access here .
Also shipped on Oct 14, 2026
Mixpanel in October 2026Workspace-level package repositories for Databricks Apps are generally available
Workspace admins can now configure default Python and npm package repositories for Databricks Apps. Apps inherit the workspace configuration while still allowing app-level overrides. See Configure default package repositories .
The Apache Hive catalog endpoint in the Lakehouse runtime catalog is now generally available (GA)
The Apache Hive catalog endpoint in the Lakehouse runtime catalog is now generally available (GA). This integration lets you use the metastore as a serverless, central metadata layer, enabling seamless data sharing and unified querying across Apache Spark, Apache Hive, and BigQuery.
Metadata migration from Dataproc Metastore to Lakehouse is now generally available (GA)
Metadata migration from Dataproc Metastore to Lakehouse is now generally available (GA). You can perform a one-time backfill migration or dry run to migrate metadata from a Dataproc Metastore service to an Apache Iceberg REST catalog endpoint or a Hive catalog endpoint using the Google Cloud console, the gcloud CLI, or the REST API.
Conversational analytics now lets you create a conversation with all of the data sources in multiple...
Conversational analytics now lets you create a conversation with all of the data sources in multiple projects, or create a conversation with a dataset . These features are generally available (GA).
You can publish a BigQuery Conversational Analytics agent in Gemini Enterprise
You can publish a BigQuery Conversational Analytics agent in Gemini Enterprise . This feature is now generally available (GA).
The AI.AGG function now supports the output_schema argument, which lets you specify the schema of the...
The AI.AGG function now supports the output_schema argument, which lets you specify the schema of the function output as a comma-separated list of fields. This feature is generally available (GA).