Koreshield 为 AI 客服智能体提供安全防护，在客户消息、检索文档和工具调用执行前拦截注入、数据泄露与越权操作，适合部署 AI 客服的企业。
热门评论
PH 用户
Today we are launching Koreshield. It sits between your AI support agent and every LLM.
Your support agent talks to strangers and acts on what they say. In most teams, nothing checks that input before the model acts on it. We do.
The problem: A support agent acts on inputs it cannot trust: the customer message, the documents it retrieves, and the tool calls it proposes. Our job is to check all three before they become trusted model behavior or application execution.
Two things you can try right now:
AI Security Gateway: One call before the model: your server sends the input to https://api.koreshield.com/v1/scan with an X-API-Key header, and the decision comes back before the model sees it. One declarative policy governs every request, and the same policy applies across OpenAI, Anthropic, Gemini and openai-compatible models, even though each provider normalises streaming and tool calls differently.
Tool action governance: Every proposed tool call is checked against your policy before it runs. A support bot steered toward an action it should not take simply does not execute, whether that is an account edit, an order change, or a refund above your limit.
Also part of the platform.: - RAG Security checks the knowledge base the bot reads, so hidden instructions in a help article are caught.
- Every request and every block is recorded. The record matters as much as the block.
Honest about what this is.: - Request-layer enforcement only. Response-layer inspection is on the roadmap. - We are not claiming to have solved AI security. It is a new field and anyone who says otherwise is selling.
Free trial on the hosted plans (one-time 3-day trial, card required). Docs at docs.koreshield.ai, API key in about two minutes.
If you run an AI support agent, try to break it. If you do, we want the report first.
PH 用户
this maps almost exactly onto the problem we deal with on the voice side - a transcribed customer call is just as untrusted an input as a chat message, arguably worse since background noise and misrecognized words create phrasing the screening layer has never seen before. curious how you tuned the false positive rate, since a support agent that gets blocked from doing a legitimate refund because the customer's wording pattern-matched something suspicious is its own kind of support failure
PH 用户
screening retrieved docs + tool calls not just the prompt is the right call 🔒 congrats!
PH 用户
hi teslim, letting a support bot near real customers always made me a little uneasy, mostly the part where it'd refund someone by mistake. Having a gatekeeper check the move first, and log why it said no, calms that nerve. Nice ;)
PH 用户
Excited to see Koreshield live on Product Hunt🚀
The evidence side matters a lot to us. Being able to explain what an agent was allowed to do, what was blocked, and why.
We are building Koreshield to check customer messages, retrieved content and proposed tool calls before they lead to unsafe actions, with a record of each decision.
For anyone building AI support agents, what is your biggest concern about putting them into production? Would love your feedback.
Your support agent talks to strangers and acts on what they say. In most teams, nothing checks that input before the model acts on it. We do.
The problem: A support agent acts on inputs it cannot trust: the customer message, the documents it retrieves, and the tool calls it proposes. Our job is to check all three before they become trusted model behavior or application execution.
Two things you can try right now:
AI Security Gateway: One call before the model: your server sends the input to https://api.koreshield.com/v1/scan with an X-API-Key header, and the decision comes back before the model sees it. One declarative policy governs every request, and the same policy applies across OpenAI, Anthropic, Gemini and openai-compatible models, even though each provider normalises streaming and tool calls differently.
Tool action governance: Every proposed tool call is checked against your policy before it runs. A support bot steered toward an action it should not take simply does not execute, whether that is an account edit, an order change, or a refund above your limit.
Also part of the platform.:
- RAG Security checks the knowledge base the bot reads, so hidden instructions in a help article are caught.
- Every request and every block is recorded. The record matters as much as the block.
Honest about what this is.:
- Request-layer enforcement only. Response-layer inspection is on the roadmap.
- We are not claiming to have solved AI security. It is a new field and anyone who says otherwise is selling.
Free trial on the hosted plans (one-time 3-day trial, card required). Docs at docs.koreshield.ai, API key in about two minutes.
If you run an AI support agent, try to break it. If you do, we want the report first.
The evidence side matters a lot to us. Being able to explain what an agent was allowed to do, what was blocked, and why.
We are building Koreshield to check customer messages, retrieved content and proposed tool calls before they lead to unsafe actions, with a record of each decision.
For anyone building AI support agents, what is your biggest concern about putting them into production? Would love your feedback.