Happy New Year! Hope you had a great break - we definitely ate too many cookies. But we're back, caffeinated, and ready to ship.

Here's what's new: audit logs, semantic layer exports, and a fresh coat of paint on settings.

New Features

Audit Logs
Full visibility into who did what and when across your workspace. Perfect for compliance, debugging, or just satisfying your curiosity.

Export Semantic Layer & Agents
You can now export your entire semantic layer and agents in multiple formats. Back it up, share it, do whatever you need.

Agent Deploy Controls
Agents are now private by default. Only Studio users can see them until you explicitly deploy to Explorer. This gives you proper staging before going live.

Improvements

Settings Revamp
We completely rebuilt the settings screens. They're cleaner, faster, and actually make sense now.

Steward AI Agent
Various fixes and improvements to make Steward more reliable when helping you build your semantic layer.

Deprecations

Legacy Data Sources & Semantic Layer Pages
These are now retired. If you were still using them, it's time to switch to the new setup.

SQL-based Agents
Also retired. The old ways are no longer available - but trust us, the new agents are way better.

Hey everyone! It's been a busy week for us, we are joining HCLSoftware. In short, nothing changes for you, we are not going anywhere. Your data, your workflows, and your experience with our platform will continue uninterrupted.

You can read the full press release here.

Major changes under the hood

• Querying syntax refactor
  We have rebuilt the SemQL engine under the hood to increase agent accuracy. Now the agent will make less mistakes when writing SemQL.
  
  There is one main user-facing change to keep in mind — SemQL no longer uses to refer to Semantic Layer entites.
  
  Previously: SELECT from tasks;
  Now: SELECT tasks.task_count from tasks;

• Teams integration stability
  When working with large Teams instances, Wobby would sometimes fail to fetch channel lists. Now it works properly

UI Improvements

• Same chat input for Steward and Analysts
  We have unified the chat input for both Steward and Analysts, which really helps with muscle memory :)

• More space for testing agents
  We hid the name and description editor in the toolbar, so now you have more vertical space to work on agent settings

  

• Better tool use UI for Steward
  It's now easier to see what tools Steward used, what parameters the tool was called with, and how long it took.

  

Bug Fixes

• Fixed Steward hanging.
  Now it works

• Fixed agent interrupts.
  Now agent interrupts when you need it to

• Fixed Steward not showing an input when asking for input.
  Now you can answer Steward's questions

• Metrics now show "error" instead of "null" if something failed.
  Makes more sense that way

• Scroll down button no longer gets in the way.
  That was annoying

So, imagine you're in a crunch, and need to make a quarterly report for your board. Due to nebulous reasons, the only person who is available to do this is an intern with a PhD in statistics, but who started at your company two days ago and doesn't even know how the your office coffee machine turns on.

Due to other nebulous reasons, you have a choice between giving that intern:

• A 500-page manual describing your company's datasets and a computer that only runs calc.exe and a PostgreSQL terminal, or...
• A 20-page intro to your company's PowerBI setup, and a PowerBI account

Realistically, you will give the intern the PowerBI account. Sure, it would still be nice if they had your company's tribal knowledge, but they will more likely succeed with the task and make less errors if they drag and drop measures in PowerBI rather than blindly writing raw SQL.

The problem is, most Text-to-SQL solutions are the 500-page manual case — they give the an extremely smart but nil-experience agent a ton of documentation of dubious quality, tell it to do its best, and then whether it does a good job is anyone's guess.

We wanted to change that, so we'd like to introduce the Wobby Semantic Layer, the operating system for agentic BI.

• Semantic Layer
  A translation layer that transforms your raw data from technical abstractions — tables, columns, joins — into business entities that actually mean something: customers, revenue, conversion rates. Instead of agents guessing what tbl_ord_v2.amt_eur_net means, they work with "net revenue in euros."

• SemQL
  A semantic query language that lets agents query business entities deterministically. No more hallucinated joins. No more invented column names. When an agent asks for "monthly revenue by region," SemQL ensures it gets exactly that — with the exact business logic your team has agreed upon, every single time.

• Steward
  The agent that builds your semantic layer for you. Traditional semantic layers are 6-month PoC projects that become outdated documentation the moment they're finished. Steward monitors your team's conversations, detects knowledge gaps, and proposes updates — turning semantic layer maintenance from a burden into an incremental workflow with immediate results.

If you'd like to try it out, you can check out more information in the docs, or reach out to us, and we will help you get set up. Semantic Layer is currently in beta, and we are still ironing over some rough edges, so we'd love to hear what you think about it.

Thanks for reading, and have a great week!

Hey! We've been heads-down building something we're really excited about: a brand-new Semantic Layer. Think models, dimensions, measures, filters, relationships — all tied together with our own query language, SemQL. And to help you actually build and maintain all of that? We made a Steward Agent that works with you through natural conversation.

We're in beta with a few customers right now and going public in 1-2 weeks. Can't wait to show you.

Here's what else shipped:

New Features

Agent Monitoring

Remember the old Agent History page? We threw it out and rebuilt it as a proper Agent Monitoring experience.

Traces Tab

• See all your agent execution traces in one place

Analytics Tab

• Dashboards showing how your agents are actually performing
• Pick your time range (7d, 30d, 90d) to spot trends
• Get a visual breakdown of what's happening

Export Traces

Want to dig into conversations outside Wobby? Now you can export traces to CSV.

• Exports include user email, query, full conversation, feedback, channel, and date
• Whatever filters you have active get applied to the export too

Docs in the Sidebar (Wobby Studio)

• We added a docs viewer right in the sidebar — no more hunting for documentation in another tab.

Improvements

Better Sidebar

• The left sidebar is now resizable. Drag it however you like.
• Hit Ctrl+B to collapse/expand it quickly.

Stability

We did a bunch of work under the hood:

• Things should feel faster overall — we cut latency in a lot of places
• Fixed edge cases in the agent loop & improved agent's websocket communication
• Better error handling and recovery

Thanks for reading! :)

New Features

Explorer

• Agent Access Control
  Now you can define who can access which agent in Explorer, so Bob from accounting will only see finance-related agents, and Jane from engineering — only the ones relating to product.

Data Sources

• Snowflake Multi-Schema Support
  Using multiple schemas in Snowflake? We've got you covered. You can now use our agents with your deployment.

Enhancements

Chat

• Better Input Experience
  The input box in Explorer no longer has weird behaviour when you send long messages. Write longer, more detailed questions without fighting the UI.

• Title Sanity
  Long analysis titles used to take over your screen. Now they're truncated with an expand button.

• Table Titles
  Tables in Explorer now have proper titles. Small detail, but when an agent produces a lot of tables, it really helps.

Charts

• Multi-Dimension Column Charts
  Need to show multiple dimensions in a column chart? Done. Your visualizations just got more powerful.

• Stacked Charts
  Added stacked column and bar charts for showing how parts contribute to the whole. Perfect for composition analyses.

• Better Metadata
  Chart axes are now properly labeled with clear X and Y specifications. No more guessing what you're looking at.

Bug Fixes

• Messages That Send
  Fixed that annoying issue where messages would fail to send in a certain organization.

• Charts Will Render
  Squashed multiple bugs where the agent would create a chart but it wouldn't display. If the agent says there's a chart, you'll see the chart.

• Reports Complete
  Deep analysis reports no longer mysteriously stop halfway through. Your comprehensive analyses will finish as expected.

• Explorer Properly Loads
  Fixed several loading bugs that would leave you staring at spinners forever.

• Follow-ups Are No Longer Dead-ends
  Follow-up questions in various contexts now work reliably.

• Suggestions Update
  Switching agents in Explorer now properly updates the suggested questions. No more stale suggestions.

• Empty Messages Gone
  Fixed bug causing empty assistant messages to appear.

• Long Datetime Rules
  Date/time column rules now display properly instead of being hidden.