Back to Details

rfp-responder

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

rfp-responder

rfp-responder

Purpose

用途

Help Bid Managers, Proposal Leads, and Directors of Sales answer five questions at the response-strategy moment:
  1. What is this RFP actually asking? (parse sections, tag every requirement MANDATORY / WEIGHTED / NICE-TO-HAVE, extract scoring criteria, surface deadlines and format constraints)
  2. What is our true fit? (proof-point matrix per requirement: STRONG / PARTIAL / GAP, each backed by a verifiable source — case study, certification, customer quote, technical attestation, benchmark)
  3. What is our win-theme strategy? (Shipley method: 3-5 themes that ladder up across requirements, not generic value-prop bullets)
  4. What is our realistic winrate? (Shipley-derived factor model: fit, incumbent, relationship strength, decision-criteria alignment, late-entry, competitor count, deal size — produces estimate + confidence band)
  5. Should we bid? (deterministic verdict: BID / PARTNER-BID / NO-BID with named factors driving the call)
The skill surfaces GAPs explicitly. Leadership decides whether to close them, partner around them, or no-bid. It never invents claims.
帮助投标经理、提案负责人和销售总监在制定响应策略时解答五个问题：
  1. 这份RFP实际要求是什么？（解析各章节，为每个需求标记MANDATORY[强制要求]/WEIGHTED[加权要求]/NICE-TO-HAVE[锦上添花要求]，提取评分标准，明确截止日期和格式约束）
  2. 我们的真实匹配度如何？（针对每个需求的证明点矩阵：STRONG[高度匹配]/PARTIAL[部分匹配]/GAP[存在差距]，每个结果均有可验证来源支持——案例研究、认证、客户评价、技术证明、基准数据）
  3. 我们的制胜主题策略是什么？（Shipley方法：3-5个贯穿需求的主题，而非通用价值主张要点）
  4. 我们的实际中标率是多少？（基于Shipley方法的因子模型：匹配度、现有供应商优势、客户关系强度、决策标准契合度、后期介入、竞争对手数量、交易规模——生成估算值+置信区间）
  5. 我们是否应该投标？（确定性结论：BID[投标]/PARTNER-BID[合作投标]/NO-BID[不投标]，并列出驱动该决策的关键因素）
本工具会明确指出差距需求。由领导层决定是否弥补差距、通过合作填补差距或选择不投标。绝不编造声明。

When to use

使用场景

  • A 30+ page RFP / RFI / RFQ has landed with a 7-14 day response deadline
  • A security questionnaire (SIG, CAIQ, custom-buyer) needs structured Q&A — not prose
  • The team is preparing a bid / no-bid review and needs a defensible winrate estimate
  • Sales Engineering has a proof-point library but no system to map proofs to requirements
  • Leadership wants to see fit % (STRONG / PARTIAL / GAP) before committing pursuit budget
  • A late-entry opportunity needs honest assessment of the relationship deficit
Do not use for:
  • Free-form proposal narrative authoring → 
    business-growth/contract-and-proposal-writer
  • Contract redline AFTER award → 
    c-level-advisor/general-counsel-advisor
  • Marketing collateral / category content → 
    marketing-skill/*
  • Discount approval on the awarded deal → 
    commercial/deal-desk
  • Pricing-model design for a new product → 
    commercial/pricing-strategist
  • 收到30页以上的RFP/RFI/RFQ，响应截止期限为7-14天
  • 需要结构化问答的安全问卷（SIG、CAIQ、买方定制问卷）——而非散文式回答
  • 团队准备投标/不投标评审，需要有依据的中标率估算
  • 销售工程部有证明点库，但缺乏将证明与需求匹配的系统
  • 领导层希望在投入追踪预算前查看匹配度占比（STRONG/PARTIAL/GAP）
  • 后期介入的机会，需要如实评估关系劣势
请勿用于：
  • 自由格式提案撰写 → 
    business-growth/contract-and-proposal-writer
  • 中标后的合同红线修订 → 
    c-level-advisor/general-counsel-advisor
  • 营销素材/品类内容 → 
    marketing-skill/*
  • 中标交易的折扣审批 → 
    commercial/deal-desk
  • 新产品的定价模型设计 → 
    commercial/pricing-strategist

Workflow

工作流程

Step 1 — Parse the RFP

步骤1 — 解析RFP

Drop the RFP markdown / text into 
scripts/rfp_parser.py
. Output: structured JSON listing every requirement, tagged MANDATORY / WEIGHTED / NICE-TO-HAVE based on cue words (must / shall = MANDATORY; should / weighted scoring numbers = WEIGHTED; may / preferred / desired = NICE-TO-HAVE). Captures section structure, scoring criteria if disclosed, deadline, submission format constraints.
bash
python scripts/rfp_parser.py --input rfp.md --output json > parsed.json
将RFP的markdown/文本文件放入
scripts/rfp_parser.py
。输出：结构化JSON，列出所有需求，并根据提示词标记MANDATORY/WEIGHTED/NICE-TO-HAVE（must/shall = MANDATORY；should/加权评分数值 = WEIGHTED；may/preferred/desired = NICE-TO-HAVE）。同时捕获章节结构、已披露的评分标准、截止日期和提交格式约束。
bash
python scripts/rfp_parser.py --input rfp.md --output json > parsed.json

Step 2 — Score fit per requirement

步骤2 — 针对每个需求评分匹配度

Fill 
assets/rfp_intake_template.md
with your proof-point library (each proof tagged with type + verifiable source + which requirement-tags it covers) and proposed win-themes. Feed parsed RFP + intake into 
scripts/response_drafter.py
. Output: proof-point matrix per requirement with STRONG / PARTIAL / GAP, win-theme injection, GAP audit.
bash
python scripts/response_drafter.py --input draft_input.json --output markdown > matrix.md
Hard rule: GAP requirements are surfaced, never invented around. Leadership reads the GAP audit and decides: close the gap, partner-bid, or no-bid.
在
assets/rfp_intake_template.md
中填写你的证明点库（每个证明标记类型+可验证来源+覆盖的需求标签）和拟议的制胜主题。将解析后的RFP+输入文件导入
scripts/response_drafter.py
。输出：针对每个需求的证明点矩阵（含STRONG/PARTIAL/GAP）、制胜主题嵌入、差距审计报告。
bash
python scripts/response_drafter.py --input draft_input.json --output markdown > matrix.md
硬性规则： 差距需求会被明确指出，绝不编造内容掩盖。领导层查看差距审计报告后决定：弥补差距、合作投标或不投标。

Step 3 — Apply win-theme strategy

步骤3 — 应用制胜主题策略

Shipley method: 3-5 themes that span requirements. Each theme answers "why us over the incumbent / competitor on the criteria the buyer named." 
response_drafter.py
shows which themes thread through which requirements — a theme appearing in <2 requirements is decorative, not strategic, and gets flagged.
Shipley方法：3-5个贯穿需求的主题。每个主题需回答“基于买方指定的标准，为何选择我们而非现有供应商/竞争对手”。
response_drafter.py
会显示哪些主题贯穿哪些需求——仅出现在<2个需求中的主题属于装饰性内容，而非战略性内容，会被标记出来。

Step 4 — Estimate winrate

步骤4 — 估算中标率

Feed deal context (fit %, incumbent strength, relationship, decision-criteria alignment, late-entry, competitor count, deal size vs. average) into 
scripts/winrate_predictor.py
. Output: Shipley-derived estimate 0-100% + confidence band + factor breakdown + BID / PARTNER-BID / NO-BID verdict.
bash
python scripts/winrate_predictor.py --input deal_context.json --profile enterprise-software --output markdown
No-bid threshold: estimate < 20% triggers automatic no-bid recommendation.
将交易背景（匹配度占比、现有供应商优势、客户关系、决策标准契合度、后期介入、竞争对手数量、交易规模与平均值对比）导入
scripts/winrate_predictor.py
。输出：基于Shipley方法的0-100%估算值+置信区间+因子细分+BID/PARTNER-BID/NO-BID结论。
bash
python scripts/winrate_predictor.py --input deal_context.json --profile enterprise-software --output markdown
不投标阈值： 估算值<20%时自动触发不投标建议。

Step 5 — Decide

步骤5 — 决策

Take parsed RFP + proof-point matrix + GAP audit + winrate estimate into the go / no-go review. Skill does not commit pursuit budget — leadership does.
将解析后的RFP+证明点矩阵+差距审计报告+中标率估算结果带入投标/不投标评审。本工具不负责审批追踪预算——该决策由领导层做出。

Scripts

脚本

  • scripts/rfp_parser.py
    — section + requirement extractor (regex + cue-word heuristics, stdlib only)
  • scripts/response_drafter.py
    — proof-point matrix + win-theme injection + GAP audit
  • scripts/winrate_predictor.py
    — Shipley-derived factor model + bid/no-bid verdict, industry-profile-tuned
All scripts: stdlib only (argparse, json, sys, pathlib, re, collections, statistics). 
--help
and 
--sample
work on all three.
  • scripts/rfp_parser.py
    — 章节+需求提取器（正则表达式+提示词启发法，仅使用标准库）
  • scripts/response_drafter.py
    — 证明点矩阵+制胜主题嵌入+差距审计
  • scripts/winrate_predictor.py
    — 基于Shipley方法的因子模型+投标/不投标结论，可根据行业配置文件调整
所有脚本：仅使用标准库（argparse、json、sys、pathlib、re、collections、statistics）。三个脚本均支持
--help
和
--sample
参数。

References

参考资料

  • references/shipley_method_canon.md
    — Shipley Proposal Guide v6, Shipley Capture Guide, APMP BoK, Tom Sant, Tom Searcy + Henry DeVries, Strategic Proposals research, Larry Newman
  • references/rfp_strategy_canon.md
    — FAR, GSA, Forrester, Gartner, Bain, McKinsey, B2B International on RFP win-rates and buyer behavior
  • references/rfp_anti_patterns.md
    — Shipley failure modes, APMP cases, Strategic Proposals research, federal loss reviews, MIT Sloan, Bain commercial-discipline, Gartner
  • references/shipley_method_canon.md
    — Shipley提案指南第6版、Shipley捕获指南、APMP知识体系（BoK）、Tom Sant、Tom Searcy + Henry DeVries、战略提案研究、Larry Newman
  • references/rfp_strategy_canon.md
    — FAR、GSA、Forrester、Gartner、贝恩、麦肯锡、B2B International关于RFP中标率和买方行为的研究
  • references/rfp_anti_patterns.md
    — Shipley失败模式、APMP案例、战略提案研究、联邦项目失败复盘、MIT斯隆商学院、贝恩商业纪律研究、Gartner

Assumptions

假设前提

  • The RFP is the ground truth. If the buyer asked it, answer it — in the order they asked, in the format they specified. Re-organizing for narrative flow is for proposals, not RFPs.
  • Proof points must be verifiable. A claim is only as strong as the case study, certification, customer reference, or technical attestation backing it. Unsourced claims become GAPs.
  • Win-themes are buyer-side, not seller-side. "We're the leader in X" is a marketing claim; "Your operations team reduces incident MTTR by 60% with the same headcount" is a win-theme. Shipley canon, not optional.
  • Winrate estimates are directional. The model is a discipline tool to force honest pursuit-qualification — not an oracle. Confidence band always wider than the point estimate suggests.
  • Industry profiles tune base rates — government RFPs reward compliance discipline; enterprise SaaS rewards reference accounts; healthcare rewards regulatory + security depth.
  • Late entry is a structural disadvantage. Entering after the RFP issued, with no relationship history, drops base rate ~15%. The skill names this, doesn't hide it.
  • RFP是唯一依据。 买方提出的问题必须如实回答——按照他们的提问顺序和指定格式。调整叙事结构属于提案撰写范畴，而非RFP响应。
  • 证明点必须可验证。 声明的可信度取决于支持它的案例研究、认证、客户参考或技术证明。无来源的声明会被视为差距。
  • 制胜主题需站在买方视角，而非卖方视角。 “我们是X领域的领导者”是营销声明；“您的运营团队可在保持现有人员规模的前提下将事件平均修复时间（MTTR）缩短60%”才是制胜主题。这是Shipley准则，而非可选要求。
  • 中标率估算仅作方向参考。 该模型是用于督促如实评估追踪价值的纪律工具——而非预言机。置信区间始终比点估算值显示的范围更宽。
  • 行业配置文件调整基准率 — 政府RFP重视合规纪律；企业SaaS重视参考客户；医疗行业重视监管+安全深度。
  • 后期介入是结构性劣势。 在RFP发布后介入且无过往合作记录，会使基准率下降约15%。本工具会明确指出这一点，而非隐瞒。

Anti-patterns

反模式

  • Inventing a proof point to fill a GAP. Hard rule violation. GAPs surface for leadership decision, not for prose-laundering. See 
    references/rfp_anti_patterns.md
    .
  • Responding to every RFP. Without a qualified bid / no-bid gate, the team burns capacity on <20% winrate pursuits and loses the 50%+ pursuits to lack of focus. Bain commercial-discipline research.
  • Generic response with no win-theme. A proposal that could be sent verbatim by any competitor is decorative. Shipley failure mode #1.
  • Missing a mandatory disqualifier late. FedRAMP / HIPAA / ISO 27001 / SOC 2 / on-shore data residency caught on Day 12 of a 14-day response = wasted pursuit. Parser surfaces these on Day 1.
  • Answering the question YOU wanted asked. RFP responder discipline: answer what they asked, in their words, in their order. Re-framing belongs in cover letters, not in the compliance matrix.
  • No compliance matrix. Every requirement should map to a response section + page number. Evaluators score on a matrix; respondents who don't provide one self-disqualify on traceability.
  • Late-entry without acknowledging the relationship deficit. Entering cold against an incumbent with a 3-year relationship and no champion = sub-20% winrate. Pretending otherwise wastes Sales Engineering capacity.
  • Treating WEIGHTED requirements like MANDATORY. Score-weighted requirements reward depth on the high-weight items, not uniform mediocrity across all. Shipley capture method.
  • 编造证明点填补差距。 违反硬性规则。差距需提交领导层决策，而非用文字掩盖。详见
    references/rfp_anti_patterns.md
    。
  • 响应所有RFP。 若无合格的投标/不投标门槛，团队会在中标率<20%的项目上浪费精力，同时因精力分散错失中标率50%+的项目。贝恩商业纪律研究表明了这一点。
  • 无制胜主题的通用响应。 任何竞争对手都能原样发送的提案毫无意义。这是Shipley失败模式之首。
  • 后期发现强制 disqualifier（ disqualification因素）。 在14天响应周期的第12天才发现FedRAMP/HIPAA/ISO 27001/SOC 2/本地数据驻留要求 = 浪费追踪资源。解析器会在第1天就指出这些要求。
  • 回答你想被问到的问题。 RFP响应纪律：回答买方提出的问题，用他们的措辞，按他们的顺序。重新表述属于求职信范畴，而非合规矩阵。
  • 无合规矩阵。 每个需求都应映射到响应章节+页码。评估人员按矩阵评分；未提供矩阵的响应者会因可追溯性不足自动失去资格。
  • 后期介入却不承认关系劣势。 在无支持者的情况下，与有3年合作历史的现有供应商竞争 = 中标率<20%。若假装情况并非如此，会浪费销售工程资源。
  • 将加权要求视为强制要求。 加权评分要求奖励在高权重项目上的深度投入，而非所有项目的平均平庸表现。这是Shipley捕获方法。

Distinct from

与其他工具的区别

  • business-growth/contract-and-proposal-writer
     — free-form narrative proposals where YOU set the structure (executive briefs, capability statements, unsolicited proposals). RFP-responder handles buyer-dictated structured Q&A where the buyer set the questions, sections, scoring criteria, and format. Different artifact, different decision logic.
  • c-level-advisor/general-counsel-advisor
     — contract redline and IP/risk review AFTER award. RFP-responder operates BEFORE award, on the response strategy.
  • marketing-skill/*
     — external marketing assets (web copy, content, ASO, SEO, brand voice) for many-to-many audiences. RFP-responder produces a single-buyer artifact with deterministic compliance requirements.
  • commercial/deal-desk
     — per-deal discount routing on a closing opportunity. RFP-responder is pursuit-stage; deal-desk is close-stage.
  • commercial/pricing-strategist
     — pricing-model design for a new product. RFP-responder consumes existing pricing as input to the commercial-terms section.
  • business-growth/contract-and-proposal-writer
     — 自由格式叙事提案，由你设定结构（执行摘要、能力声明、主动提案）。rfp-responder处理买方指定的结构化问答，其中买方设定了问题、章节、评分标准和格式。二者产出的成果不同，决策逻辑也不同。
  • c-level-advisor/general-counsel-advisor
     — 中标后的合同红线修订和知识产权/风险审查。rfp-responder在中标前运作，聚焦响应策略。
  • marketing-skill/*
     — 面向多受众的外部营销资产（网页文案、内容、ASO、SEO、品牌调性）。rfp-responder产出针对单一买方的成果，需满足确定性合规要求。
  • commercial/deal-desk
     — 针对即将成交的项目进行逐单折扣审批。rfp-responder处于追踪阶段；deal-desk处于成交阶段。
  • commercial/pricing-strategist
     — 新产品的定价模型设计。rfp-responder将现有定价作为输入，用于商业条款章节。

Forcing-question library (Matt Pocock grill discipline)

强制问题库（Matt Pocock审查纪律）

Walked one at a time before any script runs. Recommended answer + canon citation per question. Never bundled.
  1. "What's your STRONG / PARTIAL / GAP split on the MANDATORY requirements?" Recommended: STRONG ≥ 70% on MANDATORY before bidding. PARTIAL/GAP on any MANDATORY = either close the gap pre-submission or no-bid. Canon: Shipley Proposal Guide v6 — capture-management discipline, "Pgw (probability of win) is bounded by your weakest MANDATORY."
  2. "Is there an incumbent, and how strong is their position?" Recommended: strong incumbent (3+ years, no displacement event) drops base winrate ~30%. Don't bid without a named displacement trigger. Canon: Forrester B2B-RFP research — incumbents win 70-80% of renewal RFPs absent a named failure event.
  3. "Did you enter the conversation before or after the RFP issued?" Recommended: late-entry (after RFP issued, no prior engagement) drops winrate ~15% and signals the RFP was scoped to someone else's strengths. Canon: Tom Searcy + Henry DeVries How to Win Big Business — "If you didn't help write the RFP, you're column fodder."
  4. "What are your 3-5 win-themes, and does each thread through ≥2 requirements?" Recommended: themes that appear in only one requirement are decorative. Themes must ladder up across MANDATORY + WEIGHTED sections. Canon: Shipley Capture Guide — win-themes are the buyer-side answer to "why us" across the evaluation criteria, not seller-side feature lists.
  5. "For every claim in the response, can you name the verifiable source?" Recommended: every claim → case study / certification / customer reference / technical attestation / benchmark. Unsourced claims = GAPs. Canon: APMP BoK — "Substantiation: every assertion in a proposal must be backed by evidence the evaluator can independently verify."
  6. "What's the bid / no-bid threshold you committed to BEFORE seeing this RFP?" Recommended: pre-committed threshold (e.g., winrate ≥ 25%, STRONG ≥ 70% on MANDATORY, named champion). Post-hoc rationalization is how teams end up bidding 5% pursuits. Canon: Bain RFP-win-rate studies — disciplined bid/no-bid gates lift win-rate from ~15% to ~35%.
  7. "What does the buyer's evaluation team actually score on?" Recommended: if the RFP discloses scoring criteria, weight your response effort proportionally. If undisclosed, ask. If you can't ask, that itself is a relationship-deficit signal. Canon: Strategic Proposals proposal-management research — evaluators score on the rubric they were given, not on your narrative.
Walk depth-first. Lock 1-3 before opening 4-7. After all 7 are answered, invoke 
rfp_parser.py
→ 
response_drafter.py
→ 
winrate_predictor.py
in sequence. If question 6 lands on "we don't have a threshold," set one now or no-bid.
在运行任何脚本前，需逐一回答这些问题。每个问题都有推荐答案+准则引用。切勿批量处理。
  1. “你们在强制要求上的STRONG/PARTIAL/GAP占比是多少？” 推荐：投标前，强制要求的STRONG占比≥70%。任何强制要求存在PARTIAL/GAP = 要么在提交前弥补差距，要么不投标。 准则：Shipley《提案指南第6版》——捕获管理纪律，“中标概率（Pgw）受限于你最薄弱的强制要求”。
  2. “是否存在现有供应商，其地位如何？” 推荐：强势现有供应商（合作3年以上，无替代事件）会使基准中标率下降约30%。若无明确的替代触发因素，请勿投标。 准则：Forrester B2B-RFP研究——若无明确的失败事件，现有供应商在续约RFP中赢得70-80%的项目。
  3. “你是在RFP发布前还是之后参与对话的？” 推荐：后期介入（RFP发布后参与，无前期互动）会使中标率下降约15%，且表明RFP的范围是为其他供应商的优势设定的。 准则：Tom Searcy + Henry DeVries《如何赢得大额业务》——“如果你没有参与撰写RFP，你只是陪跑者。”
  4. “你们的3-5个制胜主题是什么，每个主题是否贯穿≥2个需求？” 推荐：仅出现在一个需求中的主题属于装饰性内容。主题必须贯穿强制要求+加权要求章节。 准则：Shipley《捕获指南》——制胜主题是针对买方评估标准的“为何选择我们”的买方视角答案，而非卖方视角的功能列表。
  5. “响应中的每个声明，你能否说出可验证的来源？” 推荐：每个声明→案例研究/认证/客户参考/技术证明/基准数据。无来源的声明=差距。 准则：APMP知识体系（BoK）——“证实：提案中的每个断言都必须有评估人员可独立验证的证据支持。”
  6. “在看到这份RFP之前，你们承诺的投标/不投标阈值是什么？” 推荐：预先设定的阈值（例如，中标率≥25%，强制要求的STRONG占比≥70%，有明确的支持者）。事后合理化解释会导致团队参与中标率仅5%的项目。 准则：贝恩RFP中标率研究——严格的投标/不投标门槛可将中标率从约15%提升至约35%。
  7. “买方的评估团队实际依据什么评分？” 推荐：如果RFP披露了评分标准，按比例分配响应精力。若未披露，请询问。若无法询问，这本身就是关系劣势的信号。 准则：战略提案管理研究——评估人员依据给定的评分表评分，而非你的叙事内容。
按深度优先顺序处理。先确定1-3的答案，再处理4-7。所有7个问题回答完毕后，按顺序调用
rfp_parser.py
→
response_drafter.py
→
winrate_predictor.py
。如果问题6的答案是“我们没有阈值”，请立即设定阈值或选择不投标。