Ask HN: What's your current AI agentic setup?
I'm curious how people on HN are using AI day to day, and came up with a list of questions I thought could be interesting to know. No need to answer every question of course, just wanted to get a gut feel how people are using AI. 1) What AI subscriptions are you personally paying for? (Claude, ChatGPT/Codex, Cursor, etc) - Which tiers? - Have you purchased multiple subscriptions from the same…
User inquiries about their current AI agentic setups on Hacker News have sparked curiosity about the diverse tools and approaches being utilized. The questions posed aim to provide insights into the popular AI subscriptions, alternative models, coding harnesses, agent orchestration tools, and broader agent platforms in use today.
In the first question, individuals are asked about the AI subscriptions they personally pay for, including details such as the specific subscription they choose (e.g., Claude, ChatGPT/Codex, Cursor), the corresponding tier, and whether multiple subscriptions have been purchased from the same provider (e.g., two accounts with Claude).
Question two delves into the usage of models beyond the mentioned subscriptions. Participants are encouraged to share any models accessed through pay-as-you-go APIs, OpenRouter, or locally hosted alternatives, along with the specific models and providers they utilize.
Moving on to question three, the focus shifts to the coding harnesses and interfaces employed. It invites users to disclose whether they stick with the default CLIs or IDE integrations or opt for alternatives such as OpenCode, Pi, Aider, Muse Code, or custom-built harnesses. Furthermore, it prompts individuals to explain the reasons behind any switches in harnesses, if applicable.
Question four addresses the adoption of agent orchestration or swarm tools. Users are invited to share any tools they employ in this regard, such as Munder Difflin, Gas Town, Ruflo, or custom-built solutions.
The fifth question explores the utilization of broader agent platforms, including names like OpenClaw, Hermes Agent, Grok bot, Dots, or Muse. Participants are asked to articulate the main use cases for these platforms, if they are indeed using them.
The engagement on Hacker News regarding these AI agentic setups has garnered significant interest, with over 333 points and 357 comments as of the time of the report. The comments section offers a platform for users to share their experiences, insights, and rationale behind their chosen tools and approaches in the rapidly evolving landscape of AI-powered automation.
Written by urgent.news from Hacker News Best's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
