Live data from Hacker News

Ask HN: What Are You Working On? (March 2026)

news.ycombinator.com

901–910 of 1001 posts

Re: Ask HN: What Are You Working On? (March 2026)

#901
post #59

I changed gears and moved into the video games industry at the end of 2021. I started developing a city builder called Metropolis 1998 [1], but wanted to take the genre in new directions, building on top of what modern games have to offer: - Watch what's happening inside buildings and design your own (optional) - Change demand to a per-business level - Bring the pixel art 3D render aesthetic back from the dead (e.g R…

Awesome! I’ve had this game on my wishlist for a while now. Just saw there is a demo, will have to check it out!!

Re: Ask HN: What Are You Working On? (March 2026)

#902
I'm building SnowSignals - the personal ski guide. We help skiers make the most of their day on the mountain no matter the conditions, combining weather, snow conditions, and resort information to create tailored plans.

To accomplish this, I built a snow metamorphosis model that forecasts what the snow surface skis like, a dataset of resort "topography", and an optimizer that gives skiers an idea of how to best structure their day.

You can check it out at snowsignals.com

Re: Ask HN: What Are You Working On? (March 2026)

#903
I built agent-triage - CLI that automates diagnosing AI agent failures in production.

I was spending way too much time staring at logs and web dashboards trying to figure out why my multi-agent setups kept failing.

You just point it at your traces (LangSmith, Langfuse, OpenTelemetry, or a JSON file). It pulls the system prompts directly from the logs, extracts the behavioral rules, and uses an LLM-as-a-judge to replay each conversation step-by-step.

It flags exactly which turn broke things, which agent caused it, and traces cascading failures across routing, handoffs, and retrieval.

It aggregates root causes across all of them: "24 out of 51 failures are missing escalations." You know exactly what to fix first.

Runs locally. Only LLM API calls leave your machine. You can try it without installing anything.

https://github.com/converra/agent-triage

Re: Ask HN: What Are You Working On? (March 2026)

#907
I'm Building MVAR: It's a deterministic execution firewall for LLM agents. The core idea: prompt injection becomes dangerous only when model output can trigger privileged execution.. Instead of detecting malicious prompts, MVAR enforces policy at the sink level.

Invariant: UNTRUSTED input + CRITICAL sink → BLOCK

Just hit PyPI this week. https://github.com/mvar-security/mvar

Re: Ask HN: What Are You Working On? (March 2026)

#908
I'm a product manager with no coding background, building a video editing tool from scratch — solo. The core idea is to rethink the editing workflow entirely around agents rather than manual timelines. Most existing tools still treat AI as a feature bolted on top; I'm trying to make the agent the primary interface. Also been running myself as a one-person ops team using AI for data analysis, writing, and research. Honestly, it's changed my intuition about where human judgment actually matters. Fewer places than I expected

Re: Ask HN: What Are You Working On? (March 2026)

#909
I’ve been building a custom ERP/CRM system for the medical device manufacturing company I work at. We went through two commercial ERPs over the years and both were slow and painful to customize, so I started building a simpler replacement.

It handles inventory, work orders (MRP), purchasing, sales orders, accounting, everything we need. After a couple failed attempts earlier on, I rebuilt it with a much simpler stack and it’s now running the company day to day.

Still learning a lot about manufacturing workflows and how much unnecessary complexity most ERP systems accumulate. Now I'm trying to focus on ways that the software can help other companies in a similar ERP boat that we were some years ago.

Post reply on HN