Use case
Campus switching questions are distributed across Webex conversations, public documentation, and specialist knowledge, so answers can be slow or inconsistent.
Ask Campus Switching Webex AI Agent
Campus switching questions are distributed across Webex conversations, public documentation, and specialist knowledge, so answers can be slow or inconsistent.
How it solves it
A human-first agent retrieves approved context, drafts an evidence-backed answer, applies response guardrails, and keeps posting separate from reasoning.
Architecture
The design separates inputs, orchestration, AI assistance, and human verification. Secrets and environment-specific identifiers belong in runtime configuration, never in this page or source control.
Software stack
Python, Webex APIs, SQLite/FTS, vector retrieval, MCP adapters, provider routing, regression tests.
Source-controlledTestableObservableLeast privilege
AI and AgenticOps
AI synthesizes only retrieved context and should cite or qualify uncertainty; AgenticOps handles scheduling, health, retry, shadow mode, and human handoff while credentials remain in runtime secrets.
Technical operating model
Ingest
Accept structured inputs and normalize them.
Accept structured inputs and normalize them.
Reason
Retrieve approved context and produce a bounded plan.
Retrieve approved context and produce a bounded plan.
Verify
Apply guardrails, human review, and evidence checks.
Apply guardrails, human review, and evidence checks.
Safe defaults favor shadow or draft mode until retrieval quality, identity, and posting permissions are verified.