
Get experiment designs from a new A/B Experiment Expert, and take tracking plans from design to acceptance
A new preset A/B Experiment Expert drafts experiment designs and interprets results for your review.
Read the updateNew agents, skills, integrations and controls, with what changed and where to find it.

You can now open product pages and files in a panel next to your AE Agent conversation and delegate part of a task to a remote Agent.
Read the update
With the AI Evaluation Platform, you can test Agents and models in batches against your own criteria.
Read the update
Automations can now run on several days each week or several dates each month, including the month's last day, and send results to configured external channels.
Read the update
Shared workspaces keep a team's sessions, files, Agents, Skills, memory and automations in one place, with tasks, a message center and easier knowledge base upkeep.
Read the update
MCP Management lets an Agent reach into the platforms and tools your team already works in, so it does the work inside a conversation instead of only describing it.
Read the update
A new A/B testing module lets you run several versions of your product at once, split users fairly, and get a plain answer on which one wins.
Read the update
You can now put any Agent, or a whole Agent Team pipeline, on a schedule: hourly, daily, weekly, or monthly.
Read the update
Connect specialist Agents into one automated pipeline, in series or in parallel.
Read the update
Agentic SDK gives the agents embedded in your app a runtime trace of every skill, tool call, and cost, tied into the same funnel as your user behavior.
Read the update
Upload your tracking plans, metric definitions, and playbooks into the Agentic Engine.
Read the update
The biggest Agentic Engine update yet: your Agents now answer using your company's own definitions, turn good practices into shared skills, run end-to-end workflows as a team, and give leadership the…
Read the update
A new command-line tool that brings the full Agentic Engine to your terminal.
Read the update
Agents now connect to third-party tools through secure OAuth, starting with Slack, and run recurring work like data inspections and reports on a schedule instead of only on demand.
Read the update
The tools and methods your agents use are now a browsable, shareable library.
Read the update
New admin controls for running Agents at company scale: unified member and permission management, an isolated sandbox for every user, and token-based cost caps at both the company and individual level…
Read the update