· AI Engineering · Auroviq

System Prompts, Temperature, and Model Settings: Controlling LLM Behavior

Control LLM behavior with system prompts, temperature, top-p, max tokens, and stop sequences. Practical defaults for chat, extraction, and coding features.

System Prompts, Temperature, and Model Settings: Controlling LLM Behavior

Prompt text is only half of control. Message roles and decoding parameters decide whether your feature feels precise or creative—and whether it stays on policy. Product teams should treat these settings as part of the prompt version.

System vs developer vs user messages

Put invariants in the system prompt. Putting critical safety only in the user message is fragile when users override instructions.

Temperature

Higher temperature increases randomness among likely tokens.

If outputs must match a schema, low temperature plus constrained decoding beats “please be consistent” alone.

Top-p (nucleus sampling)

Top-p limits sampling to a probability mass. Many teams either tune temperature or top-p—not both aggressively. Start with defaults; change one knob at a time while evaluating.

Max tokens and stop sequences

System prompt design tips

  1. Short, prioritized rules (models overweight early and late content—still keep noise low)
  2. Explicit tool and refusal policies
  3. Output contract first if the feature is machine-consumed
  4. Version the system prompt in git next to the feature flag

Multi-turn memory hygiene

Long chats accumulate contradictions. Summarize state into a structured “working memory” object and resend it instead of infinite raw history when building agents.

Recommended starting defaults

Use case Temp Notes
Data extraction 0 JSON schema + validation
Support draft replies 0.3 Style examples in few-shot
Marketing variants 0.7 Human picks winner
Code generation 0–0.2 Tests required

Frequently asked questions

Why did the model ignore my system prompt?

Long user content can dominate; conflicting instructions exist; or the model is weaker at instruction hierarchy. Shorten, reorder, and reinforce critical rules near the task.

Work with Auroviq

Auroviq (AuroviQ) builds production AI features, agent workflows, and LLM integrations for product companies in the UK, Netherlands, Singapore, and India. We combine prompt design with architecture, evals, and secure delivery—not demos that break in production.

Work with Auroviq — custom software & AI for product teams.

Contact us · More articles · Services