Tommi Somersuo
@tommis.fi
Director of Technology @ Solita.fi | Tech management & leadership, Dev, AI, agents, SWE, low-code, innovation and emerging tech.
Offline: Runner, angler, RES/SRA, Tibetan Terrier owner.
Offline: Runner, angler, RES/SRA, Tibetan Terrier owner.
Framework to automate regulatory compliance checks for AI/ML systems in supporting adherence to the EU AI Act and GDPR.
EUROCOMPLY: Enabling zero-touch AI compliance auditing via LLM-based agentic AI | EURECOM
www.eurecom.fr
January 10, 2026 at 5:34 AM
Framework to automate regulatory compliance checks for AI/ML systems in supporting adherence to the EU AI Act and GDPR.
Reposted by Tommi Somersuo
Opus and I were crafting a local MCP Server acting as a wrapper around a 3rd party API but I wanted the best of both MCP and Skills: here is our progressive disclosure architecture, with a single exposed tool "gateway" and point-in-time instructions to the LLM how to handle tool outputs.
Progressive Disclosure in MCP Servers: Keeping LLM Context Lean | Oskar 🕊️ | WhiteWind blog
Progressive Disclosure in MCP Servers: Keeping LLM Context Lean
MCP (Model Context Protocol) servers give LLMs access to external systems, but naive implementations waste thousands of tokens on tool schemas and verbose responses. This post covers patterns for context-efficient MCP design.
The Prob...
whtwnd.com
January 6, 2026 at 3:46 AM
Opus and I were crafting a local MCP Server acting as a wrapper around a 3rd party API but I wanted the best of both MCP and Skills: here is our progressive disclosure architecture, with a single exposed tool "gateway" and point-in-time instructions to the LLM how to handle tool outputs.
Miri: Practical Undefined Behavior Detection for Rust
github.com/rust-lang/mi...
github.com/rust-lang/mi...
Miri: Practical Undefined Behavior Detection for Rust
plf.inf.ethz.ch
January 2, 2026 at 7:21 PM
Miri: Practical Undefined Behavior Detection for Rust
github.com/rust-lang/mi...
github.com/rust-lang/mi...
Reposted by Tommi Somersuo
A Guide to Claude Code 2.0 and getting better at using coding agents by sankalp
sankalp.bearblog.dev/my-experienc...
sankalp.bearblog.dev/my-experienc...
December 29, 2025 at 12:19 AM
A Guide to Claude Code 2.0 and getting better at using coding agents by sankalp
sankalp.bearblog.dev/my-experienc...
sankalp.bearblog.dev/my-experienc...
Reposted by Tommi Somersuo
Good grief this might be the most beautiful video I’ve ever watched. You’ll need to have some idea of how LLMs work internally to follow along, but the findings of the papers presented in this video are incredible.
youtu.be/D8GOeCFFby4?...
youtu.be/D8GOeCFFby4?...
The most complex model we actually understand
YouTube video by Welch Labs
youtu.be
December 20, 2025 at 6:00 PM
Good grief this might be the most beautiful video I’ve ever watched. You’ll need to have some idea of how LLMs work internally to follow along, but the findings of the papers presented in this video are incredible.
youtu.be/D8GOeCFFby4?...
youtu.be/D8GOeCFFby4?...
Multi-part series with lot of predictions for coming year(s)
2026 DevOps Predictions - Part 1 | DEVOPSdigest
The Holiday Season means it is time for DEVOPSdigest's annual list of predictions, covering DevOps and software development. Industry experts — from analysts and consultants to the top vendors — offer...
www.devopsdigest.com
December 17, 2025 at 5:12 AM
Multi-part series with lot of predictions for coming year(s)
AWS guide about the shift from static automation to autonomous agents. Showcases Bedrock Agents, the Model Context Protocol (MCP) and the Strands Agents framework.
Timelines converge: the emergence of agentic AI - AWS Prescriptive Guidance
How agents evolved in the current decade through enterprise-grade platforms, MCP servers, and agentic AI.
docs.aws.amazon.com
December 15, 2025 at 5:08 AM
AWS guide about the shift from static automation to autonomous agents. Showcases Bedrock Agents, the Model Context Protocol (MCP) and the Strands Agents framework.
