Incorporating AI in engineering on-call workflows
Hello HN! My name is Max, and I’m a co-founder at Lynx (https://uselynx.ai). We’re building an AI-powered incident resolution platform to help engineers debug and resolve on-call issues faster. If you’ve ever been paged in the middle of the night and had to spend hours piecing together logs, metrics, and code, we’d love your feedback. * The Problem * On-call hasn’t kept pace with modern engineering. Even with great observability tools, diagnosing incidents is slow because: - Systems are increasingly complex. - Logs, dashboards, and documentation are scattered. - Context often…
What it does
In the maker’s words, at launch
Hello HN! My name is Max, and I’m a co-founder at Lynx (https://uselynx.ai). We’re building an AI-powered incident resolution platform to help engineers debug and resolve on-call issues faster. If you’ve ever been paged in the middle of the night and had to spend hours piecing together logs, metrics, and code, we’d love your feedback. * The Problem * On-call hasn’t kept pace with modern engineering. Even with great observability tools, diagnosing incidents is slow because: - Systems are increasingly complex. - Logs, dashboards, and documentation are scattered. - Context often depends on tribal knowledge. Lynx is designed to reduce the time and manual effort involved in incident resolution. * How It Works * Lynx runs on your servers and integrates seamlessly with your existing stack—including your codebase, infrastructure, logs, metrics, tracing, CI/CD, and cloud services. - Direct Integration: Lynx connects via a local agent installed on your servers. This agent interfaces directly with your systems, enabling real-time command execution, log retrieval, status checks, and overall infrastructure interaction. - Automatic Context Aggregation: Using our proprietary chain-of-thought execution process, Lynx automatically gathers and synthesizes context from across your stack—from logs and metrics to code insights and infrastructure status. - Command Generation and Execution: With the aggregated context, Lynx generates targeted commands and executes them to resolve issues, streamlining debugging and remediation. Our method delivers direct, actionable insights and interventions that accelerate incident resolution and overcomes many limitations of traditional diagnostic tools. Check out our demo: https://youtu.be/atzdMyd7PG0?si=Ntvh6uhE3bwE5z7F * Safety and Security * We built Lynx with security in mind to ensure it only takes safe, controlled actions: - Manual Command Approvals: You can require manual approval before any command is executed. - Role-Based Access Control (RBAC): Lynx supports RBAC for many integrations. You can grant specific permissions for investigative tasks while restricting access to sensitive operations or data. - Optional On-Prem Hosting: Lynx can be deployed on-prem or in your private cloud, keeping all data and operations within your network. * Looking for Feedback * If your team deals with heavy on-call loads, we’d like to hear how you’re managing debugging today and any feedback on our approach. - Try it out: https://www.uselynx.ai/getstarted - Discuss: Reach out to [email protected] Your insights will help shape Lynx into a tool that truly addresses on-call pain points.
Does the same job
all alternatives →
Progress AI Observability30d ago · telerik.com · ▲168Trace, evaluate, and improve AI agents in production
- LALogcat.ai:AI-powered observability for Operating Systems(Android+Linux)2025 · logcat.ai · ▲9
Hello HN! I'm an Android OS engineer. I've worked with AOSP and Linux kernels all my career and always wondered about lack of sophisticated tools to debug and analyze system-level logs. Always had to resort to manually skimming through large log files to find something I needed to. With the rise of LLMs and the AI-age, I felt it was a great opportunity to build something for OS engineers, which is what led to logcat.ai! We are building the industry-first observability platform for system level intelligence. Think "Datadog for operating systems" instead of applications. Currently, we support…
- ABAutomated bug fixing powered by LLMs2023 · resolvd.ai · ▲9
Hey everyone, My friend and I built a simple bug fixing app that listens for alerts/issues from Sentry, contextualizes it against your codebase, and any other data sources you wish to connect (right now we support Notion, Google Docs, and Slack), and deploys an ai agent to write a PR for review in Github or Gitlab to solve the bug. Our current demo shows the end-to-end process for a trivial bug fix, but we have been testing it with open source python repos like http-pie, comparing how our agent solves a bug compared to a human engineer and it gets fairly close. We are working on adding…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, February 2025
the whole month →
Screen Studio 3.0▲1,833Beautiful screen recordings with instant shareable links
Growth · 2025 · screen.studio
- IG
I was at FB/Meta from late 2013 to early 2023, mostly working in the compiler/runtime spaces. I got hit in the spring 2023 layoff wave. I immediately started making games in my newfound free time (a lifelong interest, and I even worked in AA(A?) back ca. ~2000), and in October 2023 I stumbled upon the idea of a roguelike pachinko/plinko game inspired by Luck Be A Landlord. Things snowballed quickly, I started talking to publishers, then worked like crazy through all of 2024, almost the hardest I've ever worked in my career, and launched the game in December 2024. It's sold…
Work · 2025
- IB
i wanted to change the habit of reaching for my phone in the morning and doomscrolling away an hour so i built an app to help me. now i have to literally touch grass before accessing my most distracting apps the app is built in swiftui, uses the screen time apis provided by apple and google vision to recognise grass or not i'd love to get your thoughts on the concept.
Life & fun · 2025 · touchgrass.now