@maya-chenagentic-engineering-executive-decision-memo텍스트공개2026. 6. 14. 업데이트

Agentic Engineering prompt that creates an executive memo that makes tradeoffs explicit and returns one-page recommendation, options table, risks, and next actions.

AI Agents AI Workflow Code Review Evals Software

19스타0Fork64복사

Prompt

미리보기

Claude에서 열기

# Role
You are a staff engineer who designs reliable coding-agent workflows, tests, and rollout gates. 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
Create an executive memo that makes tradeoffs explicit for AI-native software delivery with coding agents, CI automation, and repo governance.

# Inputs
- Project context: a Codex-powered triage and implementation workflow for a TypeScript monorepo
- Target audience: staff engineers, engineering managers, platform teams
- Success metric: activation, quality, revenue, risk reduction, or cycle time
- Available tools and data: GitHub, CI logs, code search, unit tests, MCP repo tools
- Constraints: small reversible changes; tests before implementation; clear ownership boundaries
- Desired depth: Fast triage
- Output tone: Clear operator memo

# Domain signals to inspect
- repository structure
- pull request history
- CI logs
- architecture decision records

# Known risks to control
- hallucinated APIs
- weak tests
- hidden coupling
- unsafe repository writes

# Method
1. Lead with the decision
2. State assumptions and confidence
3. Compare options on the same criteria
4. End with named owners and dates

# Required output sections
1. Decision needed
2. Recommendation
3. Options
4. Evidence
5. Risks
6. Next actions

# 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.

생성물

생성물 1개

Example Output: Agentic Engineering Executive Decision Memo

Inputs used

Project context: a Codex-powered triage and implementation workflow for a TypeScript monorepo
Target audience: staff engineers, engineering managers, platform teams
Success metric: activation, quality, and risk reduction
Available tools and data: GitHub, CI logs, code search, unit tests, MCP repo tools
Desired depth: Production-ready
Output tone: Clear operator memo

Generated Result

one-page recommendation, options table, risks, and next actions

Decision needed

The immediate decision is whether a Codex-powered triage and implementation workflow for a TypeScript monorepo is mature enough for a controlled pilot. The strongest evidence should come from repository structure and pull request history; if either source is missing, mark the recommendation as provisional rather than filling the gap with assumptions.

Recommendation

Recommendation: run a narrow pilot before broad rollout. Prefer a governance-forward pilot if evidence suggests weak tests; prefer a speed-forward pilot only when pull request history and CI logs are already reliable.

Options

Option A optimizes speed by shipping a limited workflow around CI logs. Option B optimizes control by adding reviewer sign-off and rollback steps. Option C waits until evidence from architecture decision records is stronger. Use the same success metric for all three options.

Evidence

Evidence to trust: architecture decision records, repository structure, and reviewer notes from unit tests. Evidence to treat cautiously: anecdotes that are not tied to a time window, cohort, or source owner.

Risks

Treat hallucinated APIs as a launch blocker until there is a control that can be verified. The minimum control is: tests before implementation, plus reviewer sign-off for ambiguous outputs.

Next actions

Next actions: validate pull request history, assign a reviewer for weak tests, and schedule a decision checkpoint after the first pilot cohort. Do not expand scope until the review path works in practice.

Recommended Decision

Proceed with a narrow pilot focused on repository structure and pull request history. Treat hallucinated APIs as the primary launch blocker. The first milestone should prove that the workflow produces a usable implementation plan, eval rubric, and release checklist with clear evidence, named owners, and a review path for ambiguous cases.

Expected quality checks

The result is specific to AI-native software delivery with coding agents, CI automation, and repo governance.
It includes the required sections: Decision needed, Recommendation, Options, Evidence, Risks, Next actions.
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: hallucinated APIs.

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

Agentic Engineering: Executive Decision Memo

Use this prompt when you need one-page recommendation, options table, risks, and next actions for AI-native software delivery with coding agents, CI automation, and repo governance.

Best for

staff engineers, engineering managers, platform teams
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.