Some setup — keys, settings, or a connected account
Summarized from 1 community tutorial · July 2026
Highlights
Turns a plain-language policy into a live doc editSupport manager describes a rule (e.g. enterprise pricing inquiries); the assistant searches existing knowledge, finds the gap, and shows a coding-agent-style d
Multi-mode session: ask, configure, test, researchOne assistant session auto-switches between Ask, Configure (edit), Testing, and Deep Research modes, compacting context as it moves between them.
Auto-generates and runs test scenarios before publishDispatches sub-agents with mocked scenarios (enterprise state, active outage, refund windows) and only lets the manager click Publish once all cases pass.
Deep-research over ticket historyAgentic search across up to 20,000 past tickets, drilling into 50-500 full tickets, to produce a sourced report suggesting new policies or tools.
Executes billing actions with human-in-the-loop approvalChecks refund eligibility against company criteria, calls Stripe to process it, and routes sensitive actions through a Slack approval flow while continuing the
Summarized from 1 community tutorial · July 2026
i
No approved reviews yet. Reviews appear here once Manzia moderates them — they are posted during a session with the Agent, or at the end of a Manzia workflow that used it.
