@sophia-reedrag-knowledge-experiment-launch-planएकल टेक्स्टसार्वजनिक14 जून 2026 को अपडेट किया गया

RAG Knowledge Ops prompt that turns an idea into a measurable pilot or launch experiment and returns hypothesis, audience, variants, instrumentation, and decision rule.

54Star0Fork45कॉपी

Prompt

पूर्वावलोकन

Claude में खोलें

# Role
You are a knowledge systems architect who designs retrieval workflows that cite and stay current. 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 an idea into a measurable pilot or launch experiment for RAG ingestion, retrieval quality, citation design, and knowledge base governance.

# Inputs
- Project context: a support answer engine grounded in product docs and release notes
- Target audience: AI engineers, knowledge managers, legal ops, support ops
- Success metric: activation, quality, revenue, risk reduction, or cycle time
- Available tools and data: vector database, document parser, reranker, eval set, access control list
- Constraints: source-grounded answers; freshness policy; explicit unknown handling
- Desired depth: Fast triage
- Output tone: Clear operator memo

# Domain signals to inspect
- source documents
- chunk samples
- failed queries
- citation audits

# Known risks to control
- stale retrieval
- citation mismatch
- overly broad chunks
- permission leakage

# Method
1. Tie each variant to a mechanism
2. Choose one primary metric
3. Define guardrail metrics
4. Specify how to interpret inconclusive results

# Required output sections
1. Hypothesis
2. Target segment
3. Variants
4. Instrumentation
5. Risks
6. Decision rule

# 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.

आउटपुट

1 आउटपुट

Example Output: RAG Knowledge Ops Experiment Launch Plan

Inputs used

Project context: a support answer engine grounded in product docs and release notes
Target audience: AI engineers, knowledge managers, legal ops, support ops
Success metric: activation, quality, and risk reduction
Available tools and data: vector database, document parser, reranker, eval set, access control list
Desired depth: Production-ready
Output tone: Clear operator memo

Generated Result

hypothesis, audience, variants, instrumentation, and decision rule

Hypothesis

Hypothesis: improving how the workflow handles source documents will reduce stale retrieval. Ship two variants at most, instrument the primary metric before launch, and decide in advance what evidence stops the test.

Target segment

Use chunk samples as evidence, apply the constraint "freshness policy", and explicitly note how the plan reduces citation mismatch. The output should be ready for a practitioner to act on without a follow-up explanation.

Variants

Hypothesis: improving how the workflow handles failed queries will reduce overly broad chunks. Ship two variants at most, instrument the primary metric before launch, and decide in advance what evidence stops the test.

Instrumentation

Hypothesis: improving how the workflow handles citation audits will reduce permission leakage. Ship two variants at most, instrument the primary metric before launch, and decide in advance what evidence stops the test.

Risks

Treat stale retrieval as a launch blocker until there is a control that can be verified. The minimum control is: freshness policy, plus reviewer sign-off for ambiguous outputs.

Decision rule

Hypothesis: improving how the workflow handles chunk samples will reduce citation mismatch. Ship two variants at most, instrument the primary metric before launch, and decide in advance what evidence stops the test.

Recommended Decision

Proceed with a narrow pilot focused on source documents and chunk samples. Treat stale retrieval as the primary launch blocker. The first milestone should prove that the workflow produces a usable RAG blueprint, source policy, and retrieval eval plan with clear evidence, named owners, and a review path for ambiguous cases.

Expected quality checks

The result is specific to RAG ingestion, retrieval quality, citation design, and knowledge base governance.
It includes the required sections: Hypothesis, Target segment, Variants, Instrumentation, Risks, Decision rule.
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: stale retrieval.

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

RAG Knowledge Ops: Experiment Launch Plan

Use this prompt when you need hypothesis, audience, variants, instrumentation, and decision rule for RAG ingestion, retrieval quality, citation design, and knowledge base governance.

Best for

AI engineers, knowledge managers, legal ops, support ops
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.