Nov 12
Bringing just-in-time data modeling to Blobby
Why the semantic layer needs to grow out of the questions people ask
Omni · Company blog · 4.2 a month · 179 posts since Apr 5, 2022
Nov 12
Why the semantic layer needs to grow out of the questions people ask
Oct 22
Building an end-to-end demo environment for our field team
Oct 21
When is a cheaper LLM good enough for analytics? What testing new models taught us about ambiguity, definitions, and cost.
Sep 28
Dashboards should stop being the default answer to every analytics request. The better question is what action someone is trying to take.
Sep 24
Benchmarking open-weight LLMs in Omni's AI agent exposed prompt-cache bugs in our harness. Once fixed, GLM 5.3 Flash matched Sonnet 5's accuracy at 1/12 the cost.
Sep 23
We tested Jev against Claude Haiku on 1,000 product classifications. It matched Haiku's results about 90x faster and 20x cheaper. Here's where it fits in Omni.
Sep 22
Snowflake’s Semantic Views are treated as their own objects, as Topics (curated datasets) in our semantic model. And we’re proud to have the only two-way integration, which lets you develop in both platforms and sync back in either...
Sep 9
Otrium's two-person analytics team put AI on top of a governed semantic model. Ad hoc "pull me this data" requests went to zero, and everyone using Omni saves about 5 hours a week.
Sep 8
Doubling adoption after a two-month BI migration
Sep 1
A good semantic layer improves through use, absorbing context from the people and agents who rely on it.
Aug 19
One analytics engineer used Claude Code and Omni's API to move Handshake from their previous BI tool to Omni in eight weeks, while cutting the scoped timeline by roughly 40%.
Aug 18
Omni is now ISO/IEC 27001 certified, recognizing our high standards for information security management.
Aug 6
Introducing Omni Apps. Anyone can now build and share governed applications on your company metrics. Describe the tool you need, and Omni's agent creates it on your semantic model.
Jul 28
We took 100 real questions our team had asked in our own production Omni instance, and tested five AI setups using the same questions, data, and warehouse. The results show Omni is better, faster, and less expensive.
Jul 15
We've built tools, services, and processes to make BI migrations faster and more straightforward. In this guide, we’ll cover how to think about your migration, what to do before you start, and which paths you can take to get there
Jul 7
AI Evals are tests for your AI agent. Run prompt sets against your semantic layer and AI context to observe your agent’s behavior and validate changes before you ship to production.
Jun 29
Checkr unified its BI + AI workflows with Omni’s semantic layer, giving both humans and AI the context and guardrails to scale self-service.
Jun 22
Data was never the goal. As performance pressures mount, executives are becoming the new power users of data through AI, and the best data teams are building roads, not driving taxis.
Jun 11
We’ve given Blobby, Omni’s AI Agent, a new tool in its arsenal to make this process a lot less time-consuming: Enter the Omni Dashboard Builder.
Jun 9
I vibe-coded a World Cup bracket app with live player stats, AI analysis, and embedded dashboards using Omni, Snowflake CoCo, and Claude in two evenings. Here's a bit about what you can do with it and how I built it.
Jun 1
Introducing AI Hub, Omni's command center for observing AI usage, improving the semantic model, and validating AI changes before they ship.
Omni's own blog on omni.co, found by the daily check.
Data engineering (9), Product and company (7), AI and agents (6) in the last six months.
Across Glyph:awards·calendar·Roundup·marketplaces·Changefeed·salaries·socials
Listed on Blogs Oct 4, 2026. No changes to its feed, status or cadence since.