{"slug": "sia-foundry-getting-started", "title": "SIA Foundry Getting started", "summary": "Hexo AI has released SIA Foundry, a platform that improves existing AI agents by generating evaluations, running them, detecting failures, and proposing fixes. The company provides a sample expense agent that developers can clone and run end to end to see how SIA works, and they can also point SIA at their own agents. The process requires that the agent already runs cleanly on its own before SIA is applied.", "body_md": "We provide a sample agent — the **expense agent** — that you can clone and run end to end to see how SIA works. It gives you something working to try the whole flow against.\n\nYou don't have to stop there. You can build any agent of your own, structured the same way as the sample expense agent, and point SIA at it to start improving it. The steps below are the same either way.\n\nBefore you start:SIA improves agents that already run. Make sure your agent executes cleanly end to end on its own — no SIA involved — before you point SIA at it. See[step 5].\n\nSignup on [sia.hexo.ai](https://sia.hexo.ai).\n\nOnce you've signed up, reach out to us to request approval — we'll get you set up with API keys as well.\n\n```\ngit clone https://github.com/hexo-ai/expense-agent.git\n```\n\nThis is the sample agent. Once you're ready to work on one of your own, point these same steps at your agent's repo instead.\n\n```\nconda create -n expense python=3.12\nconda activate expense\npip install sia-foundry\ncd expense-agent\n```\n\nCreate `.env`\n\nfile for your agent.\n\n**Do this before anything else in SIA.** SIA's whole job is to improve an agent that already works. It generates evals against your agent, runs it, reads the failures, and proposes fixes. If the agent can't complete a run on its own, every failure SIA finds will be a setup problem — missing keys, bad config, a broken dependency — not a real weakness in the agent. You'll spend your time debugging plumbing instead of improving behavior.\n\nSo run your agent by hand first, start to finish, on a normal input. Confirm it:\n\n- starts without errors\n- reads its\n`.env`\n\nand reaches every API and service it depends on - completes a full task and returns the output you expect\n\nOnly once a clean run works every time should you move on. If you're using the sample expense agent, run it as-is and confirm it completes before continuing.\n\n```\nsia login --foundry https://sia.hexo.ai --device\nsia init\nsia status\nsia evals generate\nsia envs generate\nsia evals run\nsia failures detect\nsia fixes propose\nsia fixes show p1\nsia fixes apply p1          # only when you want it landed\nsia evals run\n```\n\n", "url": "https://wpnews.pro/news/sia-foundry-getting-started", "canonical_source": "https://gist.github.com/VigneshHexo/b2c3f28bf0e05906434c8efa3f256730", "published_at": "2026-08-25 20:24:33+00:00", "updated_at": "2026-08-26 01:13:40.082299+00:00", "lang": "en", "topics": ["ai-agents", "developer-tools", "ai-products"], "entities": ["Hexo AI", "SIA Foundry", "expense agent"], "alternates": {"html": "https://wpnews.pro/news/sia-foundry-getting-started", "markdown": "https://wpnews.pro/news/sia-foundry-getting-started.md", "text": "https://wpnews.pro/news/sia-foundry-getting-started.txt", "jsonld": "https://wpnews.pro/news/sia-foundry-getting-started.jsonld"}}