Internal copilot

An internal copilot usually starts as “chat over docs” and quickly becomes more demanding:

• company knowledge and retrieval
• multiple data sources
• user or team-specific permissions
• auditability and production controls

#Typical stack

npm install @agentskit/react @agentskit/adapters @agentskit/runtime @agentskit/memory @agentskit/rag @agentskit/observability @agentskit/tools

#Recommended package mix

#What the architecture usually looks like

1. A user asks a question in a chat UI.
2. The runtime combines short-term context, memory, and retrieved documents.
3. Tools fetch additional data from internal systems when needed.
4. The assistant returns an answer, citation set, or action result.
5. Observability and security layers provide the controls needed for rollout.

#Good defaults

• Start with retrieval-only before enabling mutating actions.
• Keep retrieval quality visible with traces and sampled evaluations.
• Model access and tool access should be treated separately.
• Add prompt injection and PII protections before broader rollout.

#Best follow-up guides

• RAG chat example
• RAG pipeline example
• createRAG
• Doc loaders
• Prompt injection
• PII redaction

#When AgentsKit is especially strong here

Internal copilots are where the ecosystem framing matters most. AgentsKit gives you one set of contracts across UI, retrieval, runtime, tools, and production controls, which helps a lot once the “simple chat over docs” prototype starts growing into a real internal platform.