Use DocsGPT for document-grounded enterprise assistants
Deploy DocsGPT to build private assistants that ingest documents, web sources, and enterprise connectors with cited answers.
npx skills add agentskillexchange/skills --skill use-docsgpt-for-document-grounded-enterprise-assistants
Use DocsGPT when a team needs a private document-grounded assistant with citations, connectors, and agent actions instead of asking a general chatbot to reason over loose files. The operator workflow is to deploy DocsGPT, connect approved document or web sources, configure the model and tools, build the assistant, then verify answers against citations before exposing it through chat widgets, bots, or APIs. The scope boundary is grounded assistant setup and review for a defined knowledge base; it is not a generic platform card because the invocation is tied to ingestion, assistant configuration, answer checking, and controlled rollout.
What this skill actually does
Inputs and prerequisites: DocsGPT deployment; document connectors; supported LLM provider or local model.
Setup notes: Follow the DocsGPT quickstart at https://docs.docsgpt.cloud/quickstart or deploy from https://github.com/arc53/DocsGPT using the repository setup instructions.
Source and verification boundary: use https://docs.docsgpt.cloud/ as the canonical reference before running the workflow; keep commands, API calls, CLI usage, and generated outputs reviewable against that upstream source.
Framework fit: publish this as a Multi-Framework workflow only when the operator can invoke the documented toolchain directly, rather than treating the upstream project as a generic product listing.