News
AWS has released Strands Harness, a fully assembled agent, under the Apache 2.0 license. A harness is the runtime that turns a language model into an agent: it manages tools, context and intermediate steps. Strands runs on models via Amazon Bedrock, Anthropic, OpenAI, Google, Ollama and LiteLLM. By AWS’s own measurements it gets by with 28 percent lower token costs than other harnesses on the same models, at equal or better accuracy. The savings are meant to come mainly from its context defaults: long tool results are truncated, and once the context window is 85 percent full the agent summarizes it. In the same comparison AWS names DeepSeek Harness the most token-efficient, but also the least accurate.
Our take: Strands is a solid foundation for agents on AWS – but it is only the runtime. Approvals, governance and the question of which actions a person has to confirm are not part of the harness. That remains work for each project.
With taktoro.de and taktoro.com, our new product for companies in Germany is live: time tracking that checks every entry against the German Working Hours Act (ArbZG) before it is saved. Breaks, rest periods, maximum working hours and the record-keeping duty are built in, not booked as add-ons. Developed and hosted in Hamburg.
From 11 to 14 September we're at IBC 2026 in Amsterdam — no booth of our own, but you'll find us hanging around the German Pavilion at the RAI most of the time. We're there to network: catching up with partners, customers and friends from the broadcast and media industry. If you're around too, get in touch.
MJML turns a simple markup language into responsive HTML email, usually with a Node toolchain doing the work behind it. We ported it to PHP end to end: php-mjml/php-mjml needs no Node.js, no second runtime in the deployment. It has rendered this website's emails since February; as of this week it's open under the MIT licence for anyone to use.
