Built with Astro and Three.js, hosted on AWS. Domain registered in 2026.
runmirrors.com is built with Astro, hosted on AWS. It sends email through HubSpot (Marketing Hub tracking & forms) and Amazon SES.
| Technology | Version | First seen |
|---|---|---|
| JavaScript Frameworks & Libraries2 | ||
| – | 8 Nov 2026 | |
| – | 8 Nov 2026 | |
| Frontend Build Tools & CSS1 | ||
| 3.49.0 | 8 Nov 2026 | |
| CDN & Hosting2 | ||
| – | 8 Nov 2026 | |
| Email Marketing & Lead Capture1 | ||
| – | 8 Nov 2026 | |
| Transactional Email2 | ||
| – | 8 Nov 2026 | |
| Error Tracking & Performance Monitoring1 | ||
| – | 8 Nov 2026 | |
| Fonts & Icon Fonts1 | ||
| – | 8 Nov 2026 | |
Registration from the registry's RDAP record, the certificate the site serves, and its rank in public traffic lists.
The crew hasn’t read this site’s colors yet. We read a palette when we capture a site’s screenshot, busiest sites first. Meanwhile, browse palettes from other sites.
Counted from every stack change we've recorded: of the sites we watched running one of this site's tools, how many went on to add another. A pattern across sites, not a forecast for this one.
smtp.google.comns-704.awsdns-24.netns-182.awsdns-22.comns-1091.awsdns-08.orgns-1932.awsdns-49.co.ukgoogle-site-verification=IVP2GjqdTH2pyfTGmBG9UxdmEg1jO44tE4EdX5RPtKQgoogle-site-verification=w6BBJGW-OStBvOT-J0xzFLOwxE0M8pAVQqXHkYYoTVUv=MCPv1; k=ed25519; p=MVQBe7ikWvM3gL5xXRzROeUl7KqsAQ4wXsFLpLiV2Jw=v=spf1 include:_spf.google.com include:_spf.porkbun.com ~allv=DMARC1; p=none; rua=mailto:aryan@runmirrors.com; fo=1; adkim=r; aspf=rUser-agent: * Allow: / Disallow: /setup Disallow: /builds Disallow: /tools Disallow: /simulation Disallow: /replay Disallow: /improve Disallow: /connect Disallow: /settings Disallow: /billing Disallow: /admin Disallow: /oauth Disallow: /connected Disallow: /reset-password Sitemap: https://mirrors.dev/sitemap-index.xml Sitemap: https://mirrors.dev/docs/sitemap.xml
# Mirrors > Mirrors is a developer tool for production AI agents: it surfaces recurring mistakes across your agent’s runs and turns them into targeted corrections you can preview, apply only in the situations where they belong, and measure. ## Earlier product Mirrors does not rebuild the systems your agent calls or run your agent against a replica of them. Older pages, listings and posts may describe an earlier Mirrors product: a staging environment, digital twin or replay-testing tool for AI agents. That product is no longer offered, and runmirrors.com now redirects to this site. For anything current, use this site and its documentation. ## Product - [Homepage](https://mirrors.dev/): Product overview and illustrative examples. - [How it works](https://mirrors.dev/#how-it-works): Surface recurring mistakes, write a correction, choose where it applies, and measure the outcome. - [Request access](https://mirrors.dev/request-access): Book a call or email the founders. ## Documentation - [Documentation](https://mirrors.dev/docs): Product concepts and integration guides. - [SDK quickstart](https://mirrors.dev/docs/quickstart): Install and connect the SDK. - [SDK reference](https://mirrors.dev/docs/sdk/reference): Runtime APIs and configuration. - [Trace capture](https://mirrors.dev/docs/guides/trace-capture): Send agent conversations and tool activity. - [Corrections](https://mirrors.dev/docs/guides/corrections): Review, preview, and activate scoped corrections. - [Runtime modes](https://mirrors.dev/docs/guides/runtime-modes): Control delivery and validate behavior. - [Troubleshooting](https://mirrors.dev/docs/guides/troubleshooting): Diagnose integration problems. - [Documentation Markdown index](https://mirrors.dev/docs/llms.txt): Links to individual Markdown pages. - [Full documentation text](https://mirrors.dev/docs/llms-full.txt): Combined documentation for text readers. ## Guides - [What is an agent correction? Scoped fixes for AI agents](https://mirrors.dev/resources/glossary/agent-correction): An agent correction is a short instruction an AI agent gets only when its trigger matches. How it works, and how it differs from prompt lines, skills and guardrails. - [Why your AI agent keeps making the same mistake in production](https://mirrors.dev/resources/ai-agent-keeps-making-same-mistake): AI agents repeat mistakes when a fix lands in the wrong place, nobody groups the failures, or nobody measures the change. How to find the pattern and make a fix stick. - [AI agent observability vs evals vs corrections](https://mirrors.dev/resources/vs/observability-vs-evals-vs-corrections): Observability shows what an agent did, evals test a change, and corrections change what it gets in one situation. How they fit with Langfuse, LangSmith and Braintrust. - [Self-improving AI agents: what works in production](https://mirrors.dev/resources/self-improving-agents): What self-improving agents do, where automatic prompt rewriting falls short, and why a review step between a lesson and live behavior is worth keeping. - [System prompt too long? What to do instead of adding more rules](https://mirrors.dev/resources/system-prompt-too-long): How to tell when a system prompt has grown too far, what to move out of it, and how to add an instruction only in the situations where it applies. ## Frequently asked questions ### What does Mirrors do? Mirrors finds the mistakes your AI agent keeps making in production and lets you fix each one with a correction: a short instruction your agent gets only in the situations where it applies. You preview a correction before it goes live, then compare outcomes with and without it. ### Why not add the fix to my system prompt or a skill? A line in the system prompt reaches every conversation, so fixes pile up and your agent carries all of them, even when it’s doing something simple. A skill is read only when the model decides it’s relevant, so the fix can be missed. Mirrors adds each correction when its situation comes up, keeps every correction in one place, scoped to the right accounts and workflows, and shows whether it helped. ### How is Mirrors different from evals and observability tools? Observability shows what your agent did. Evals check it against test cases before you ship. Mirrors acts on what keeps going wrong in production: it surfaces recurring mistakes, applies your corrections where they happen, and measures each one on real runs. It works alongside both. ### How do I connect my agent? Install the Mirrors SDK, send your agent’s conversations, and request corrections once per user turn. It works with any agent framework, and your app keeps control of its model calls and tools. ### Does Mirrors add latency? The SDK waits at most 1,000 ms per user turn, and you can set a shorter limit. If Mirrors doesn’t answer in time, your agent continues without corrections. ### Can I check a correction before it goes live? Yes. Mirrors previews each correction against your stored conversations, so you see every one it would have reached, including any you didn’t expect, before you turn it on. ## Company and contact - Email: devs@runmirrors.com - [Y Combinator profile](https://www.ycombinator.com/companies/mirrors) - [LinkedIn](https://www.linkedin.com/company/runmirrors) - [X](https://x.com/mirrorsdotdev) - [YouTube](https://www.youtube.com/@mirrorsdotdev) ## Optional - [Privacy](https://mirrors.dev/privacy) - [Terms](https://mirrors.dev/terms)
| – |
| 8 Nov 2026 |
| – |
| 8 Nov 2026 |