Back to Prompt Library
implementation

GPT-5 for Contextual Understanding and Proactive Suggestions

Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.

Linked challenge: Proactive iOS Digital Assistant

Format
Text-first
Lines
1
Sections
1
Linked challenge
Proactive iOS Digital Assistant

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines
1 sections
No variables
0 checklist items
Using GPT-5, implement the 'Proactive Suggestion Generation' state. Given a simulated user context (e.g., calendar, location, past interactions), the agent should formulate a proactive suggestion or identify a task that would benefit the user. Provide an example where GPT-5 analyzes current traffic data and calendar to suggest leaving early for an appointment, detailing the prompt engineering involved.

Adaptation plan

Keep the source stable, then change the prompt in a predictable order so the next run is easier to evaluate.

Keep stable

Hold the task contract and output shape stable so generated implementations remain comparable.

Tune next

Update libraries, interfaces, and environment assumptions to match the stack you actually run.

Verify after

Test failure handling, edge cases, and any code paths that depend on hidden context or secrets.