02 Oct Drinking from the AI firehose
Up to 13 AI coding sessions open at once, and nearly all of them waiting for me....
10 Aug Private Agentic Data Analytics with OpenCode, Qwen and Omniscope
Posted at 18:48h
in AI, Automation, Data Analytics, Data Processing, Data Visualisation, Uncategorized 1 Comment
In my previous article, "Proving a full European AI and data analytics stack with Omniscope", I described a stack using European AI models, private model serving, European hosting options and Omniscope as the data, analytics and verification layer. That test...
03 Aug Omniscope as a tool for AI agents
External agents can author inspectable Omniscope projects. Inside Omniscope, frontier or local models can use the analytical skills we have built into the product. An AI agent using MCP and APIs, and a human using the interface, author the same Omniscope...
19 Jun We let AI write our software. The discipline is in how we keep control.
Four AI superpowers, all sprinting for the lead. We would rather keep the freedom to switch between them than bet the company on one. Most companies talking about AI in their codebase mean autocomplete. We mean something nearer the whole job:...
28 May From Unstructured Text to Structured Q&A: LangExtract, Omniscope and Insight Explorer
Posted at 18:50h
in AI, Data Analytics, Data Processing, Data Visualisation, Uncategorized 0 Comments
A common pattern in AI document workflows is to connect a large language model directly to a PDF, web page, report or long text document, then ask questions against the raw content. That works in some cases, but it is not...
08 Apr The Verification Layer: Why Trust Matters More Than Plausibility in AI Analytics
For 20 years, we have built Omniscope around one core idea: Trust. When you use analytics software, you aren’t just looking at charts; you are making decisions, telling stories, and relying on that software to see the world clearly. Trust takes...
26 Jan Engineering for determinism: a tale of two local LLM inference engines
Local large language models are often presented as creative tools. They generate fluent prose, infer intent, and fill in gaps with impressive confidence. That framing works well for chatbots and copilots. It breaks down in a different class of application:...
19 Sep Lessons from the trenches: why llama.cpp works best (today)
Why llama.cpp beats vLLM for running gpt-oss models locally We’ve spent the past few months knee-deep in the messy reality of adapting our application to run on local LLMs. On paper it should have been simple: swap the API endpoint, keep...
15 Sep 🚀 Not for the Faint-Hearted: Diving Deep into GPT-OSS
OpenAI recently dropped something unusual: open-weight models - GPT-OSS-20B and GPT-OSS-120B. Open weights matter because you can download the raw model files and run them yourself, whether that’s on your laptop or a GPU cluster in the cloud. No API calls,...
08 Jul Harmonising Data Governance and AI: a Unified approach to smarter Data Quality with Omniscope
In today’s data-driven world, data quality isn’t just a checkbox -- it’s a competitive advantage. Businesses are increasingly realising that poor data quality undermines analytics, corrupts insights, and leads to costly decisions. At Visokio, we believe that automated processes and...
- 1
- 2
