@zoe-patelcustomer-success-evaluation-redteamTextPublicUpdated Jun 14, 2026

Customer Success prompt that builds an evaluation suite for high-risk AI workflows and returns eval matrix, adversarial cases, grading rubric, and release threshold.

AI Workflow Customer Success Operations Retention Support

24Stars0Fork174Copies

Prompt

Preview

Open in Claude

# Role
You are a customer success operator who converts signals into retention actions. 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
Build an evaluation suite for high-risk AI workflows for AI-assisted onboarding, renewal risk detection, customer health reviews, and support deflection.

# Inputs
- Project context: a B2B workflow automation tool with enterprise onboarding complexity
- Target audience: CSMs, support leads, onboarding teams, customer operations
- Success metric: activation, quality, revenue, risk reduction, or cycle time
- Available tools and data: support desk, CRM, analytics, knowledge base, calendar notes
- Constraints: customer-safe language; clear owner for each action; no blame framing
- Desired depth: Fast triage
- Output tone: Clear operator memo

# Domain signals to inspect
- support tickets
- product usage events
- QBR notes
- NPS comments

# Known risks to control
- missing renewal risk
- generic success plans
- unverified root causes

# Method
1. Convert user outcomes into measurable tasks
2. Include realistic failure modes
3. Separate correctness from style
4. Define pass, warn, and block thresholds

# Required output sections
1. Success criteria
2. Golden tasks
3. Adversarial tasks
4. Rubric
5. Sampling plan
6. Release decision

# 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.

Artifacts

1 artifacts

Example Output: Customer Success Evaluation and Red-Team Harness

Inputs used

Project context: a B2B workflow automation tool with enterprise onboarding complexity
Target audience: CSMs, support leads, onboarding teams, customer operations
Success metric: activation, quality, and risk reduction
Available tools and data: support desk, CRM, analytics, knowledge base, calendar notes
Desired depth: Production-ready
Output tone: Clear operator memo

Generated Result

eval matrix, adversarial cases, grading rubric, and release threshold

Success criteria

Create at least 12 golden tasks: 6 normal cases, 3 edge cases, and 3 adversarial cases targeting missing renewal risk. A passing result must cite the evidence source and state confidence.

Golden tasks

Create at least 12 golden tasks: 6 normal cases, 3 edge cases, and 3 adversarial cases targeting generic success plans. A passing result must cite the evidence source and state confidence.

Adversarial tasks

Use QBR notes as evidence, apply the constraint "no blame framing", and explicitly note how the plan reduces unverified root causes. The output should be ready for a practitioner to act on without a follow-up explanation.

Rubric

Use NPS comments as evidence, apply the constraint "customer-safe language", and explicitly note how the plan reduces missing renewal risk. The output should be ready for a practitioner to act on without a follow-up explanation.

Sampling plan

Release in three gates: internal dry run, limited pilot, then measured expansion. Each gate must show evidence that clear owner for each action is true in practice, not only in documentation.

Release decision

Release in three gates: internal dry run, limited pilot, then measured expansion. Each gate must show evidence that no blame framing is true in practice, not only in documentation.

Recommended Decision

Proceed with a narrow pilot focused on support tickets and product usage events. Treat missing renewal risk as the primary launch blocker. The first milestone should prove that the workflow produces a usable customer health narrative, action plan, and escalation draft with clear evidence, named owners, and a review path for ambiguous cases.

Expected quality checks

The result is specific to AI-assisted onboarding, renewal risk detection, customer health reviews, and support deflection.
It includes the required sections: Success criteria, Golden tasks, Adversarial tasks, Rubric, Sampling plan, Release decision.
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: missing renewal risk.

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

Customer Success: Evaluation and Red-Team Harness

Use this prompt when you need eval matrix, adversarial cases, grading rubric, and release threshold for AI-assisted onboarding, renewal risk detection, customer health reviews, and support deflection.

Best for

CSMs, support leads, onboarding teams, customer operations
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.