While interviewing for different companies and find Leetcode-like platforms to practice system design, there really isn't any good tools to practice that grill me like an interviewer. I built Scrimm.ai to solve a personal pain point: practicing System Design interviews alone is impossible and expensive (if you want to find a real person). You can read books, but you can’t simulate the pressure of an engineer poking holes in your architecture.

It’s in private beta. I’d love for you to try any of the questions and let me know if the AI is too harsh or too lenient.

While many are focusing on AI chatbots / {x} AI for B2B, I am particularly excited about useful technology that can now be built in small teams thanks to AI (hardware telemetry platforms , new encrypted messaging apps, etc)

Hi HN, I'm Cristian, an indie developer from Italy working on tools to make multi-agent AI safer and more debuggable. When agents talk to each other (CrewAI, LangGraph, AutoGen, custom setups), they quickly develop shorthand, lose context, invent jargon, and propagate hallucinations — all invisible to us. InsAIts is a lightweight Python SDK that adds observability in ~3 lines of code. V2 just shipped with:

Anchor-aware detection (set the user's original query as context to reduce false positives) Forensic root-cause tracing + ASCII chain visualization Built-in domain dictionaries (finance, healthcare, kubernetes, ML, devops, quantum) Local (Ollama) decipher mode — translates agent jargon to human-readable (Cloud soon) Integrations: Slack alerts, Notion/Airtable export, LangGraph/CrewAI wrappers

Privacy-first: local embeddings by default, nothing leaves your machine unless you opt into cloud decipher. Free tier works without an API key (local only). Also running limited lifetime deals for early supporters. Quick install: Bashpip install insa-its[full] Demos included:

Live terminal dashboard Marketing team agent simulation (watch shorthand emerge in real time)

GitHub: https://github.com/Nomadu27/InsAIts PyPI: https://pypi.org/project/insa-its/ Docs: https://insaitsapi-production.up.railway.app/docs Would love feedback — especially from anyone building agent crews or running multi-LLM systems in production. What’s your biggest pain point with agent observability? Thanks for checking it out!

Cristian