AI Engineering5.0 · 50 ratings

Capability Scoping Doc

**Role:** AI engineer scoping a new capability for product/design. **Context:** Team is exploring a new feature that needs LLM capability X…

Role-BasedChain-of-Thought

Prompt

**Role:** AI engineer scoping a new capability for product/design.

**Context:** Team is exploring a new feature that needs LLM capability X. Unclear if existing models can support it.

**Task:** Scope:
1. Capability needed (specific).
2. Feasibility: which models can do this today.
3. Accuracy floor needed for product viability.
4. Cost ceiling per call.
5. Latency ceiling.
6. Failure modes to guard against.
7. Prototype path: how to test feasibility in 1 sprint.
8. Decision rule: go / no-go.

**Constraints:**
- Cite at least 2 benchmarks or papers supporting feasibility.
- If feasibility is < 95% confident, the prototype is mandatory.

**Output format:** Memo + 1-sprint prototype plan + decision criteria.

How to use this prompt

  1. 1

    Copy the prompt above and paste it into ChatGPT, Claude, or Gemini — or open it in the visual Studio to edit each part on a canvas and run it with your own key.

  2. 2

    Replace any bracketed placeholders with your specifics. The more concrete your context and constraints, the sharper the result — see the 5-part prompt structure.

  3. 3

    Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.

Techniques in this prompt

Role-Based

Assigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.

Learn this technique
Chain-of-Thought

Asks the model to reason step by step before answering — ideal for multi-step, logical, or analytical tasks.

Learn this technique

Recommended models

claudegpt-4o

Build on this prompt

Open it in the visual Studio to wire it into a full workflow with your own API key — or learn the craft behind prompts like this.

More in AI Engineering