AWS guide: Prompt engineering fundamentals for Amazon Quick, including the CRISPE framework
AWS ML Blog · rss · 2026-09-30
Part 1 of a two-part AWS ML Blog series on prompt engineering for Amazon Quick's AI capabilities:
- Core principles: specificity (vague requests yield vague results — specify metrics, timeframes, scope, analysis type); business context (who reads the output and what decision it informs); few-shot examples (show the desired output format rather than describing it).
- The CRISPE framework for complex requests: Context/constraints, Role, Intent and inputs, Steps and scope, Perspective and presentation, Evaluation criteria — each illustrated with enterprise examples.
- Component frameworks: RADAR for knowledge retrieval and ARCHITECT for building custom agents, mapping directly to the Quick agent builder fields.
- Part 2 will cover component-specific techniques for Research, Flows, Sight, Chat Agents, and Action Integrations.
More from coding & agent
- GPT-6.1 Sol matches GPT-6 Astra at ~1/5 cost, ultrafast version targets 300 tok/s — haider1 · 2026-09-30
- Dots review: OpenAI's always-on agents read your Slack and flag conflicts first — every · 2026-09-30
- Developer Has Dots Drive Its Own Computer to Run Blender and Model Itself in 3D — Dimillian · 2026-09-30
- GPT-Sol 6.1 Ships Too, as Omarsar Argues Codex-Dots Combo Unlocks New Agent Workflows — omarsar0 · 2026-09-30
- LangSmith adds Trajectories: collapsing agent sessions into readable, ordered execution paths — LangChain · 2026-09-30
- Codex Cloud announced at OpenAI DevDay, available across Plus through Enterprise tiers — testingcatalog · 2026-09-30