HN Explorer

systima

↗ HN profile [ 83.4 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. The Subagent Tax (systima.ai)

    Based on feedback from our last post, we measured Claude Code subagent fan-outs vs. Doing the same work sequentially, We found that they used between 2 and (almost) 6 x the input tokens and were never faster on any task…

    1 points 0
  2. Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k (systima.ai)

    This started based off of a hunch. We usually use OpenCode, but were 'forced' to use Claude Code for a while due to issues with Meridian. In that time, we saw the usage meter rise much, much more quickly than when using…

    706 points 99
  3. Show HN: AI skills for program / project / delivery managers

    A Claude Code and OpenCode skill library that covers the full project and engagement lifecycle through 10 stage-aligned agents and 62 workflows: * Shaping: MEDDIC qualification, ROM estimate, SoW draft * Mobilisation:…

    2 points 2
  4. 9 points 0
  5. Show HN: Open-Source EU AI Act Compliance Scanning for CI/CD

    We built a CLI tool that scans your codebase for EU AI Act compliance risks. `npx @systima/comply scan` analyses your repository to detect AI framework usage, traces how AI outputs flow through the program, and flags…

    1 points 2
  6. Show HN: XML, Markdown, or JSON: Which gives LLMs the most reliable boundaries? (systima.ai)
    3 points 2
  7. Show HN: Open-Source Article 12 Logging Infrastructure for the EU AI Act

    EU legislation (which affects UK and US companies in many cases) requires being able to truly reconstruct agentic events. I've worked in a number of regulated industries off & on for years, and recently hit this gap. We…

    42 points 5
  8. 1 points 0