{"id":73260,"title":"Talc: Debugger for your LLMs","tagline":"Replay sessions, tweak inputs, and take the guesswork out of AI debugging.","body":"TL;DR:\n\n_We make it easy to debug and test LLM systems. Understand your AI by replaying sessions line by line and setting rules for it to follow moving forward._\n\nHey Everyone! We’re Matt \u0026 Max, the team behind [Talc.AI](https://talc.ai?utm_source=yc\u0026utm_medium=referral\u0026utm_campaign=launch-yc)\n\n![uploaded image](/media/?type=post\u0026id=73260\u0026key=user_uploads/1274021/e0fc1906-3bf6-4a91-9c68-c91f1a5b5b46)\n\n**Matt**: I’ve spent the last 6 years engineering at Facebook and Airbnb. At FB I worked on Election Integrity, developing new ways to detect foreign interference campaigns. Hit me up if you want to hear some war stories!\n\n**Max**: I found my passion for tech early, teaching myself to code when I was 13. This journey most recently brought me to being the technical lead for a 30 person org at Facebook that reviewed every major product launch. I love the challenge of trying to understand complex systems and want to help people do the same with Talc.\n\nWe’ve been friends for almost a decade and couldn’t be more excited to be doing this together.\n\n### The Problem\n\nDeveloping real LLM systems is still hard. Prompt engineering is full of trial and error, and debugging your chain and regression testing is a painful manual process.\n\n### The Solution\n\nReplay any session your AI has had and tweak it until it's perfect. No more copy and pasting into a playground – re-run your sessions exactly as they happened and deeply understand their possible outputs. Have a bug on message 20? Hop into that context immediately and start fixing it.\n\n![](https://lh6.googleusercontent.com/A8PxlLmIyUlxmpADBV6WOisxmZAZFraHnniUGf52CmR3IEPKY-mNdz_q3gTNMuD_EsJWu9Rhn25kfDR4Li5z_7mipCkugQOFCWjC_c9rG8q_jkEd0PGw19cf1kt1OyFLZeMAegwK0aNNo-qK2XzEVRI)\n\n\u003e _Left: Walk through your AI message logs_\n\n\u003e \u003e _Right: Edit the inputs and prompts that went into each message, all auto-populated for you_\n\n![](https://lh4.googleusercontent.com/sv7qlXTg598CcU5TY_v3uN2tNqiQgEW9PwW6n5YrQgozYubSYIiEdlbhXZGKfdAxI4aL8AZ48KhMDxbT8xWyNNDeQcxZKHFlAQkq95-Wa93jVlmoTrr5Wmh0x1awwrl0elHkZa8CcPXvJpvaGhysw6k)\n\n_Test changes against your saved use cases for regression testing_\n\n**What we’re asking**\n\n* Is LLM debugging \u0026 testing holding you back? **Reach out to us** at [talc.ai](https://talc.ai?utm_source=yc\u0026utm_medium=referral\u0026utm_campaign=launch-yc) or [book time directly on our calendars](https://calendly.com/_mattlee/intro-to-talc-ai)!\n* Do you know anyone working on LLMs in production? We’d love to learn from them! [Help us get connected](mailto:founders@talc.ai?subject=Introducing%20you%20to%20the%20Talc%20AI%20team).\n* Share us with anyone who spends a lot of time debugging LLMs\n  * _Blurb_: [Talc.ai](https://talc.ai?utm_source=yc\u0026utm_medium=referral\u0026utm_campaign=launch-yc) launched an LLM debugger so you don’t have to copy context into openai playground or jupyter notebooks any more. Reach out via [founders@talc.ai](mailto:founders@talc.ai).","slug":"J3c-talc-debugger-for-your-llms","created_at":"2023-07-20T16:36:00.133Z","updated_at":"2026-05-25T03:10:11.761Z","total_vote_count":27,"url":"https://www.ycombinator.com/launches/J3c-talc-debugger-for-your-llms","share_image_url":"//bookface-static.ycombinator.com/assets/ycdc/yc-og-image-c440a0ad1dacfb86eeeb343717479cc54d256614449b4ef719977a0a451f8bc8.png","company":{"id":28826,"name":"Talc","slug":"talc","url":"https://talc.ai","logo":"https://bookface-images.s3.amazonaws.com/small_logos/c40e7adcc07e4afaf4ca793746aeb4e609ac24b0.png","batch":"Summer 2023","industry":"B2B","tags":["Artificial Intelligence"],"search_path":"https://bookface.ycombinator.com/company/28826"}}