Intercom-style 고객 지원 앱은 한계를 알고 있습니다.

비즈니스는 웹 사이트에 스니펫을 붙여 채팅 위젯을 가져옵니다. 방문자는 비즈니스의 자신의 지식 기지에서 ** 만 ** 응답하는 AI 에이전트에 대해 이야기합니다. 에이전트가 확실하지 않을 때, 또는 방문자는 사람을 요청, 대화는 실시간 대시보드에 소유자에 간다.

MarshalDesk는 YouTube 비디오를 위해 제작되었습니다. 그것은 가짜 자료로 데모가 아니라 완전히 작동 제품이지만, 빌링, 팀 기능 또는 기업 경화가 없습니다.

네온에 의해 후원

이 비디오를 후원하기 위해 네온에게 감사드립니다. MarshalDesk는 끝에서 네온에서 실행합니다. 지식 베이스의 pgvector와 Postgres, 등록을위한 네온 Auth, 업로드 된 파일을위한 Object Storage, 배경 작업을위한 기능 및 채팅 모델과 embeddings 모두를위한 AI 게이트웨이.

Try Neon 무료로 →

뷰어

비디오와 함께 건물? 현재 위치:

• 아이디어 : 우리가 건물과 우리가하지 않는 것
• 프롬프트: 각 프롬프트는, 단계별 그룹화
• 건축 도표: 체계와 그것의 3개의 핵심 교류
• Skills: 먼저 설치하는 에이전트 기술

무엇 그것

MarshalDesk

An Intercom-style customer support app with an AI agent that knows its limits.

A business pastes one snippet into its website and gets a chat widget. Visitors talk to an AI agent that answers only from the business’s own knowledge base. When the agent isn’t sure, or the visitor asks for a person, the conversation goes to the owner in a real-time dashboard.

MarshalDesk is built for a YouTube video. It’s a fully working product, not a demo with fake data, but it doesn’t have billing, team features, or enterprise hardening.

Sponsored by Neon

Thank you to Neon for sponsoring this video. MarshalDesk runs on Neon from end to end: Postgres with pgvector for the knowledge base, Neon Auth for sign-in, Object Storage for uploaded files, Functions for background jobs, and the AI Gateway for both the chat models and the embeddings.

Try Neon for free →

For viewers

Building along with the video? Start here:

• The idea: what we’re building and what we’re not
• The prompts: every prompt used to build it, grouped by phase
• Architecture diagrams: the system and its three core flows
• Skills: the agent skills to install first

What it does

An agent that knows its limits. Every visitor message is classified before anything else happens:

• Support questions are answered from the knowledge base, streamed into the widget word by word, in the visitor’s own language.
• Off-topic messages (“What’s 5 × 5?”, “write me a poem”, “ignore your instructions…”) get a polite refusal. They never reach retrieval or the answer model.
• Questions the knowledge base doesn’t cover, or that the agent can’t answer confidently, go to a person instead of getting a guessed answer.

For the business owner:

• Knowledge base. Upload PDF, Markdown, and TXT files, or write text sources in the dashboard. Files are parsed, chunked, and embedded in the background, and suggested questions for the widget are generated from them.
• Live inbox. See every conversation as it happens, take over from the agent, reply, hand the conversation back, or close it. Waiting conversations are counted in the tab title and can trigger browser notifications.
• “How the agent handled this.” Each answer shows how the message was classified, which sources matched and how strongly, which models answered, and how long it took. You can see why the agent answered or handed off.
• Visitor details. Location, local time, language, device, browser, current page, and visit history, without storing the visitor’s IP address.
• Widget settings. Agent name and avatar, greeting, color, position, and the domains allowed to embed the widget, with a live preview.
• Light and dark mode.

For visitors: