Prompt

Anteprima

# Role
You are an agent architect who designs tool-using systems with evals, memory, and guardrails. You know current AI product patterns: tool calling, structured outputs, long-context reasoning, multimodal generation, MCP connectors, evals, trace review, and human approval gates.

# Mission
Turn analytics questions into a decision-grade data product for production agent workflows, tool calling, MCP connectors, and evaluation loops.

# Inputs
- Project context: a research assistant agent that searches, cites, and drafts market briefs
- Target audience: AI engineers, platform teams, automation builders
- Success metric: activation, quality, revenue, risk reduction, or cycle time
- Available tools and data: MCP servers, workflow engine, trace viewer, eval runner
- Constraints: least-privilege tool access; observable decision points; human review for high-risk actions
- Desired depth: Fast triage
- Output tone: Clear operator memo

# Domain signals to inspect
- tool schemas
- user tasks
- failure logs
- eval traces

# Known risks to control
- tool overuse
- unbounded loops
- stale memory
- silent failure

# Method
1. Define grain and denominator
2. List confounders and caveats
3. Prioritize actionability over chart volume
4. Write one recommendation with confidence level

# Required output sections
1. Decision to support
2. Metric contract
3. Data sources
4. Analysis method
5. Dashboard layout
6. Decision memo

# Output contract
Return Markdown only.
Use concise headings, decision tables, and checklists.
Every recommendation must tie back to evidence, assumptions, or a missing-input note.

# Quality bar
- Make the output reusable by another practitioner without extra explanation.
- Separate facts, assumptions, and recommendations.
- Use variables and placeholders only where the user must fill in project-specific information.
- Ask at most 3 clarifying questions only if missing information would materially change the result.
- Do not invent private facts, metrics, laws, integrations, or user quotes.
- Prefer specific operational language over generic AI enthusiasm.
- Include a "Verification" subsection when the output could affect users, money, security, compliance, health, or public trust.
- If the task involves tools or automation, state which actions are read-only, which actions write data, and which actions require human approval.

Artefatti

1 artefatti

Example Output: AI Agents Data Product Brief

Inputs used

Project context: a research assistant agent that searches, cites, and drafts market briefs
Target audience: AI engineers, platform teams, automation builders
Success metric: activation, quality, and risk reduction
Available tools and data: MCP servers, workflow engine, trace viewer, eval runner
Desired depth: Production-ready
Output tone: Clear operator memo

Generated Result

metric contract, analysis plan, dashboard outline, and decision narrative

Decision to support

Use tool schemas as evidence, apply the constraint "least-privilege tool access", and explicitly note how the plan reduces tool overuse. The output should be ready for a practitioner to act on without a follow-up explanation.

Metric contract

Define the metric grain before analysis. For a research assistant agent that searches, cites, and drafts market briefs, the first dashboard view should show cohort, denominator, time window, and confidence note, not just top-line movement.

Data sources

Rank sources by authority before retrieval. Chunk around task intent rather than page boundaries, and require every answer to cite the exact source segment used for failure logs.

Analysis method

Define the metric grain before analysis. For a research assistant agent that searches, cites, and drafts market briefs, the first dashboard view should show cohort, denominator, time window, and confidence note, not just top-line movement.

Dashboard layout

Define the metric grain before analysis. For a research assistant agent that searches, cites, and drafts market briefs, the first dashboard view should show cohort, denominator, time window, and confidence note, not just top-line movement.

Decision memo

Use user tasks as evidence, apply the constraint "human review for high-risk actions", and explicitly note how the plan reduces unbounded loops. The output should be ready for a practitioner to act on without a follow-up explanation.

Recommended Decision

Proceed with a narrow pilot focused on tool schemas and user tasks. Treat tool overuse as the primary launch blocker. The first milestone should prove that the workflow produces a usable agent architecture, tool contract, memory policy, and eval suite with clear evidence, named owners, and a review path for ambiguous cases.

Expected quality checks

The result is specific to production agent workflows, tool calling, MCP connectors, and evaluation loops.
It includes the required sections: Decision to support, Metric contract, Data sources, Analysis method, Dashboard layout, Decision memo.
It separates evidence, assumptions, risks, and recommended next actions.
It includes practical verification steps, not only generic advice.
It names the most important failure mode for this domain: tool overuse.

Reuse note

Before copying the output into production work, replace all default variables with your real data and run a human review for high-impact decisions.

README

README.md

AI Agents: Data Product Brief

Use this prompt when you need metric contract, analysis plan, dashboard outline, and decision narrative for production agent workflows, tool calling, MCP connectors, and evaluation loops.

Best for

AI engineers, platform teams, automation builders
Teams that already have partial context but need a sharper, reusable artifact
AI workflows where the output must be auditable, editable, and easy to hand off

How to use

Replace the variables in the prompt with your real project context.
Keep the default constraints unless your team has stronger internal rules.
Review the generated output against the checklist in the example artifact.

Design notes

This seed follows current prompting practice: explicit role, structured inputs, domain evidence, operational guardrails, and a concrete output contract. It is written in English for international PromptHub users.