One of the things we hear most from teams running Proactive Analytics is simple: "The scheduled write-ups are great, but I do not want one more thing to check. I want to hear from Zoë only when something actually needs me." Starting today, you can. Proactive Analytics is now Proactive Agents, and here is what changed:

• Conditional alerts with intelligent thresholds. Tell an agent what "worth my attention" means, and Zoë only reaches out when the line is crossed. Below the threshold, she stays quiet, so you get signal, not noise.
• The root cause, already found. Every delivery is a deep-dive analysis with the driver identified, not just a number that moved.
• Context that stays current. Agents sync context across your org through your MCP connectors, so the data model behind every run keeps up with your business.

Building one takes a minute. Give a person or agent what it needs across three steps:

• Instructions: Write what you want in plain English, for example "Check if daily revenue dropped more than 5% versus the last completed business day, and if so find the root cause."
• Triggers and tools: Put it on a schedule and choose what it can use, from Web Search to Edit Data Model to your MCP connectors.
• Delivery: Decide who gets results and how, and include a shared chat link so the team can pick up right where Zoë left off.

What happens to your existing Proactive Analytics:

• Every Proactive Analytics schedule you already set up has been converted to a Proactive Agent automatically.
• Your agents keep running on the same cadence, at the same times, delivered to the same people.
• There is nothing to rebuild or reconfigure. Open any converted agent whenever you want to add a threshold, tools, or connectors.
• You will now find everything under the ⚡ Proactive Agents section in the left sidebar.

Full details are in our Proactive Agents docs

Zoë's had the ability to edit your context since we launched Self-Learning.

But for a while after that launch, how you viewed the context felt disconnected from Zoë, who was doing the editing of it.

So now we've moved our Context Manager directly into chat (available for develop and above roles).

Whenever you're working with your context in any fashion, Zoë is right there to make changes for you or help you structure your context in the most ideal way.

This is small, but great workflow improvement for data people building context on their business logic.

And this is what it looks like →

The new Folders release gives your workspace a shared, governed home for the Artifacts teams rely on. What is specific to admins:

• Workspace folders are shared spaces that sit alongside personal Artifacts. They are best for collections owned by a team, department, project, or recurring business review, rather than one person's personal work.
• The folder controls access, not the individual Artifact. Once an Artifact is in a folder, the folder's permissions decide who can reach it, and direct shares on that Artifact no longer apply.
• Three access levels. Viewer is read-only. Editor can edit the name and description and create new versions. Owner has full control, including edit, delete, share, and configuring refresh and delivery. A folder Owner can manage access for their group without being a workspace admin, so teams govern their own content.
• Admins always have access. Workspace admins can reach foldered Artifacts regardless of how they are shared, so nothing sits outside governance.
• Flat structure for now. This release supports workspace-level folders, with no nested folders. Each Artifact lives in one folder or none.

Worth coaching your users on: moving a personal Artifact into a folder removes its direct shares, and moving it back out makes it personal again without restoring those shares. Plan moves around the folder's audience. The full model is in Artifact Folder Permissions.

One of the things we hear most from teams living in Artifacts is simple: "I love what Zoë builds, but I need the trusted work in one place, with control over who can change it." Starting June 30, you can. Here is how it works:

• Everything lives on one Artifacts page. You see the Artifacts and folders you have access to, and nothing you don't.
• Group related Artifacts into folders for a team, project, or recurring review. The folder controls who can access what is inside it.
• Search, sort, and filter to jump straight to the Artifact you need.

When you put an Artifact in a folder, the folder decides access. Give a person or group one of three levels:

• Viewer: read-only access.
• Editor: edit the name and description and create new versions.
• Owner: full control, including edit, delete, share, and configuring refresh and delivery.

A few things worth knowing:

• Moving a personal Artifact into a folder hands access control to the folder. Its direct shares are removed, so the folder becomes the single source of truth for who can see it.
• An Artifact sits in one folder at a time. Move it to another folder and the new folder's permissions apply right away.
• Move it back out and it becomes personal again, owned by whoever moved it. Direct shares are not restored, so re-share it if others still need access.
• Folders are flat in this release: workspace-level folders that hold Artifacts, with no folders inside folders.

Full details are in the Artifact Folders docs and here it is in action ↓

Having rich deep dives in your data that automatically refresh is amazing, but you shouldn't have to remember to come back to the platform to check on the latest results.

We've added scheduling for artifacts to make sure that you don't have to!

Artifacts have always been live and running on your latest data, and now they can also be delivered right to where you already work.

You can stay in your flow in Slack or email and see the most important data for your day show up right when you need it.

As someone who spends way too much time in email, this feature makes it easy for me to stay on top of our latest user activity data.

Here's how it works →

New MCP connectors let Zoë read the context your stack already holds, and act in the systems your team already uses.
​

If you're the one who owns your data stack, you know the fear about adopting a new agent: "Great, now I have to maintain yet another context layer."

It's a fair concern. Your business logic isn't in one place (impossible in any large company), it's scattered across platforms, each holding definitions someone fought hard to get right.

Drop in an agent that starts from zero and its definitions will drift away from your other tools. You're stuck with either wrong answers or a massive amount of manual synchronization, and both of those land on your desk. What if the agent played nicely with your existing data context?

Today, we're launching MCP connectors for Zoë.

Zoë connects directly to your existing tools as an MCP client, reads the context that's already there, and sets herself up. No rebuild. The years of logic locked in your other tools becomes the starting point.

Then the loop closes:

• Context flows in over MCP, on a schedule.
• Zoë gets smarter as people ask real questions, and standardizes her own context.
• Updates flow back to your source of record, written directly or proposed as a PR on a schedule.

Zoë uses the same definitions across analytics and operations. And every question makes the next one smarter.
​

The loop doesn't stop at analysis

Data → Analysis → Insight → Action → Behavior ↺ back to Data
​

Use cases: data to action

Each one starts with analysis Zoë already does well, and ends with an action she writes back through MCP. The final row is the general pattern: if you've automated it, Zoë can trigger it from an insight.

You stay in control

As an admin, you control all of it: which connections exist, which tools Zoë can call on each one, and when credentials get rotated. Set it up in Workspace Settings → Extensions → MCP.
​

Read the docs →

In short: Zoë moves from a place you go to read numbers, to a teammate who reads the numbers, acts on them across your stack, and closes the loop.

A few updates shipping this week and next.
​

Live now!

Artifact Run History
Track every scheduled Artifact delivery from the Run History tab in the Schedule Artifact Delivery modal. Confirm sends, troubleshoot misses, and jump to the Zoë chat behind any run.
​Docs →

Coming next week!

Chat side by side with the Context Manager
The Context Manager and chat are going to be built directly next to each other for easier development instead of the current pop-up modal. Plus a full-size view option for the Context Manager.

​MCP: Token-based authentication
Connect to Zenlytic via MCP using token-based auth. Docs →

Working with agents to create rich outputs like interactive dashboards is a blast, but every time you want to make one small edit, it takes forever to iterate and rebuild the whole asset just to change the small thing you asked for.

“It takes so long to make small changes” was one of the top pieces of feedback on artifacts right after we launched them.

Today, we're launching a visual editing experience for artifacts, which is WAY faster than just asking the agent to change something.

It lets you be more specific about what you want changed in an easier-to-use form factor and applies your changes in seconds instead of minutes for large artifacts.

There's still lots of work left for us to do to make the artifact experience feel snappy with such rich outputs, but this is a great step forward in making editing fast and easy for artifacts.

Here's how it works →

Managing context for a data agent is hard.

There are so many special cases, so many scenarios where a simple question actually kicks off a whole day’s worth of nuanced work.

You want it to know how your team defines a qualified lead, the weird returns logic from your old ERP, which orders count as fulfilled. But dump all of that into every question, and quality falls off a cliff.

Agents get worse, not better, when you drown them in context they don't need.

Zoë has had Skills to solve this problem for a while, but now she can create and manage those skills for you. She can craft her own reusable bits of know-how, which she pulls in only when a question actually needs them.

This makes it dramatically easier to create skills, which in turn reduces context bloat and helps Zoë perform better. Catch her getting something wrong, and she updates it so it doesn't happen again.

The logic compounds without the context bloating.

Check out how it works →

Every analytics tool I've used asks you to define your KPIs up front. Revenue, active users, churn, retention, etc. You pick your definitions, write the SQL, and maintain it forever.

The problem is nobody actually knows all their KPIs on day one. Humans are really bad databases.

Stop for a second and list all the cheeses you know. It’s hard to even get to 10 cheeses in 60 seconds!

In data, new questions surface new metrics. Definitions drift. The list is never easy to recall or even completely done.

So when you're setting up a new tool, you're stuck. Either you spend weeks (sometimes months) defining metrics before you get any value, or you skip it and the numbers come out wrong.

Now (with self-learning) Zoë can build them out herself. Docs > Here

Ask her a question that needs a metric she doesn't have. She'll work out the definition from your data, propose it back to you in plain English, and save it for you once you confirm. Net revenue retention, weekly active accounts, qualified pipeline, whatever you need. She writes the SQL, names it, and adds it to your model.

The metrics library grows as you actually use the tool, not as a prerequisite to using it.

Here’s how it works.

PS: Lmk in the comments if you actually got above 10 cheeses