Skip to main content

Prompt Components Checklist

#ComponentOne-liner
1Role and ObjectiveWho the assistant is and the task it’s there to complete.
2Personality and ToneWarmth, professionalism, conversational style.
3LanguageDefault response language and spoken phrasing style.
4GreetingStandard polite opener for new conversations.
5ReasoningControls how deeply the model thinks before responding. Voice AI Model Settings/Model Parameter Controls —> Reasoning Efforts. Takes values from 0 to 4. 0=minimal, 1=low (default), 2=medium, 3=high, 4= very high. Higher values increase latency and cost.
6Message ChannelsSpoken vs. hidden content; no internal jargon spoken aloud.
7PreamblesShort spoken update before noticeable internal work (tool call, multi-step reasoning, lookup).
8VerbosityHow short or long spoken replies should be.
9ToolsWhen to call tools, how to interpret results, how to handle failures.
10Don’t Announce ToolsNever expose tool names, system mechanics, or backend details.
11Input GatheringCollect all required inputs before invoking a tool.
12Capability BoundariesDon’t claim abilities beyond what’s actually available.
13Unclear AudioAsk the user to repeat; don’t guess or preamble on bad audio.
14Entity CaptureRead back and confirm critical entities (IDs, numbers, amounts).
15Long Context BehaviorReuse customer details and prior tool results across the session.
16No Human HandoffNever offer to transfer or escalate to a human agent.
17Escalation / LimitsAcknowledge limits honestly; suggest in-scope alternatives.

Best Practices

  • Structure the Prompt in Labeled Sections: Organize the system prompt under clear named sections (Role, Tools, Preambles, Entity Capture, etc.) rather than a single prose block. The model locates relevant instructions faster, conflicting rules are easier to spot, and iterating on one behavior doesn’t risk breaking another. Only include sections relevant to your use case.
  • Tune Reasoning Effort to the Task: Reasoning effort trades latency for depth of thought. Default to the lowest setting that still gets the job done.
  • Use Preambles Deliberately: Trigger a preamble before a tool call that may take noticeable time, before multi-step reasoning, or before an escalation — anywhere silence would feel unresponsive.
  • Define Verbosity explicitly: Telling the model to “be brief” leaves too much open to interpretation. Instead, specify expected length per task type — for example, one to two sentences for direct answers, one question at a time for clarifications, a summary-then-next-step pattern for tool results, and a tradeoffs-focused structure for comparisons.
  • Capture Exact Entities Carefully: Collect one value at a time, confirm identifiers before tool calls.
Find more details.