Every skill, one place

A/B Test Design & Significance

Use when the user wants to check whether an A/B test result is statistically significant, or to size a test before running it. Also use when the user mentions A/B test, split test, statistical significance, p-value, confidence level, conversion lift, sample size, or "is this result real / can we call the test." Produces lift, p-value, a significance verdict, and required sample size.

ABM Program Design

Use when the user is setting up or fixing an account-based marketing program - deciding how many accounts to target, how to tier them, how many touches each tier gets, and whether the team can actually run it. Also use when the user mentions ABM, account-based marketing, target account program, 1:1 or 1:few or 1:many, account tiering, named accounts, or "our ABM program isn't producing pipeline". Checks capacity and coverage together and names which of the two is the binding constraint.

Ad Creative Testing

Use when the user wants to test ad creative - headlines, images, videos, hooks or offers - on Meta, LinkedIn, Google, TikTok or any paid channel, or wants to know whether a creative "winner" is real. Also use when the user mentions creative testing, ad testing, split test, A/B test an ad, which ad won, creative fatigue, hooks, or "should I scale this ad". Sizes the test before it runs so it can answer the question, then reads it out honestly - on the metric that pays, with uneven delivery, early stopping and multiple variants accounted for.

Agent Readiness Audit

Use when the user wants to know whether AI agents buying on a customer's behalf can find, evaluate and act on their product — machine-customer readiness, agentic commerce, or being included in AI-mediated comparisons. Also use when the user mentions AI agents buying, machine customers, agentic commerce, MCP, llms.txt, "can ChatGPT actually buy from us", or being left out of AI-generated shortlists. Scores five dimensions, names the blockers, and specifies the fixes in cost order.

AI Marketing Governance

Use when a marketing team has adopted AI faster than anyone wrote rules for it — deciding which tools are approved, what must never go into a prompt, who reviews before publish, and how AI-drafted claims get fact-checked. Also use when the user mentions AI policy, AI governance, AI usage rules, AI disclosure, hallucinated citations, fake statistics, made-up sources, prompt data leakage, "is it safe to put this into ChatGPT", or reviewing AI-written marketing copy. Produces an adoption-readiness verdict, a completed policy with a named owner, and a per-claim citation check applied before anything publishes.

Brand & Product Context

Use when starting work on a brand or product with the AAJ skills, or when any skill needs context about the business that isn't available yet. Also use when the user mentions onboarding, "set up my brand," brand brief, company context, who we are, our ICP, our positioning, brand voice, or "tell the agent about my business." Produces a structured .agents/product-marketing.md brief — company, product, ICP, positioning, value, voice, goals, funnel, and competitors — that every other AAJ skill reads first.

Brand Voice Definition

Use when the user wants to define or document their brand voice - write a voice guide, agree tone-of-voice rules, or work out why some copy sounds like them and some does not - from writing that already exists. Also use when the user mentions brand voice guide, tone of voice, voice and tone, style guide, "what does our voice actually sound like", or wants rules an AI or a new writer can follow. Measures on-brand samples for reading grade, sentence length, person, contractions, hedges and buzzwords, checks they agree with each other, contrasts them with off-brand writing, and emits a checkable profile for the brand-voice-governance engine.

Brand Voice Governance

Use when the user wants to check whether content actually sounds like their brand — enforcing a defined voice across AI-generated or team-written copy at scale. Also use when the user mentions brand voice guardrails, tone consistency, on-brand/off-brand, banned words, content governance, style compliance, AI-content review, "does this sound like us", or keeping a large volume of content on-message. Checks content block by block against the brand's own do/don't rules and emits a pass/revise verdict with an audit trail.

Buyer Persona Builder

Use when the user wants to build buyer personas or an ideal customer profile (ICP) — the target's goals, pains, buying triggers, objections, and where they research. Also use when the user mentions personas, ICP, target audience profile, customer avatar, "who are we selling to", or buyer journey. Produces structured personas grounded in real signals, not demographic guesswork.

Campaign Orchestrator

Use when the user has a marketing goal or problem but doesn't know which skill to reach for — "our funnel is broken", "we're launching next month", "growth has stalled", "where do I even start". Also use when the user asks for a campaign plan, a marketing plan, a GTM plan, or help sequencing work across several areas. Diagnoses which of the named Plays applies, then runs it through Diagnose → Design → Execute, calling the right skills in order and refusing to skip ahead.

Case Study & Proof

Use when the user wants to turn a customer result into proof they can publish - a case study, a results page, a proof point for a landing page or a sales deck. Also use when the user mentions case studies, customer stories, social proof, testimonials, references, logos, "can we name the client", or has results they are not sure they are allowed to use. Scores whether the proof would convince a sceptic, checks whether it may actually be published and in what form, and gives the anonymised fallback when permission is missing.

Cold Email Sequence

Use when the user wants to write a cold outbound email sequence — the multi-touch cadence that opens conversations with target accounts. Also use when the user mentions cold email, outbound sequence, email cadence, prospecting emails, sales outreach, follow-up emails, break-up email, or "emails that get replies." Produces a 4–6 touch cold email sequence with subject lines, send timing, and one clear ask per email, grounded in the prospect's pain.

Community & Dark Social

Use when the user wants to market in the places analytics cannot see - Slack and WhatsApp groups, private communities, podcasts, forwarded emails, AI assistants - or asks whether to start a community of their own. Also use when the user mentions dark social, word of mouth, "direct" traffic that makes no sense, community-led growth, community marketing, or how to measure something that has no referrer. Maps where buyers already talk from what they say, checks whether a community should open at all, and reads the dark side of the funnel by trend rather than attribution.

Content Calendar Planning

Use when the user wants to plan a content calendar or editorial strategy — topic clusters, cadence, formats, and a repurposing plan across channels. Also use when the user mentions content calendar, editorial calendar, content strategy, topic clusters, pillar content, content cadence, or "what should we publish and when." Produces a structured calendar with clusters, schedule, and a repurposing flow.

Content Repurposing

Use when the user wants to turn one pillar asset — a report, blog post, webinar, case study, or data study — into a full set of distribution pieces across channels (LinkedIn carousel, X/LinkedIn threads, short posts, newsletter, stat cards, a short-form video script). Also use when the user mentions repurposing, atomizing content, content distribution, turning a report into social, "getting more out of" a piece, or a content-to-social flow. Produces an inventory of the reusable units in the source and drafted, channel-adapted derivatives with a sequencing plan — reusing only what the source actually says, never inventing facts or figures.

Copywriting

Use when the user wants to write, rewrite, or improve marketing copy — a homepage hero, landing page, ad, email, product page, or CTA. Also use when the user mentions copywriting, headlines, page copy, ad copy, microcopy, "make this sharper", or "why isn't this converting". Produces copy that ladders to the positioning, with every claim defensible, plus a score on clarity, concreteness, and claim-defensibility.

Creator Partnerships

Use when the user wants to work with creators or influencers - choosing who to pay, agreeing terms, or judging whether a sponsorship worked - on YouTube, LinkedIn, podcasts, newsletters, TikTok or Instagram. Also use when the user mentions influencer marketing, creator marketing, sponsorships, paid posts, B2B creators, podcast ads, newsletter sponsorships, or "is this creator worth it". Compares creators on the buyers they actually reach rather than follower counts, writes the terms both sides sign - including disclosure - and reads the result on what it sold, tracked and self-reported.

Customer Interview Synthesis

Use when the user has done, or is doing, customer or buyer interviews and wants to turn the notes into something a persona, a positioning statement or a roadmap can rest on - or wants to know whether they have done enough interviews. Also use when the user mentions customer interviews, discovery interviews, user research synthesis, affinity mapping, jobs-to-be-done interviews, "what did we learn from the calls", or "how many interviews do we need". Counts coded themes across interviews rather than quotes, weights them by what the problem costs, separates patterns from anecdotes, and says whether the programme has saturated.

Customer Survey Design

Use when the user wants to design a customer or market survey — choosing the questions, structure, scales, and sample size to get unbiased, decision-useful answers. Also use when the user mentions survey, questionnaire, NPS, customer feedback, market research survey, product-market fit survey, sample size, margin of error, "how many responses do I need," or "what should I ask my customers." Produces a structured survey with unbiased questions mapped to decisions, plus computed sample-size, invite, and segment-readability numbers from a runnable engine.

Discovery Call Framework

Use when the user wants a discovery call structure or question bank — how to run a first sales call that qualifies and uncovers real pain. Also use when the user mentions discovery call, sales call script, qualifying questions, sales questions, needs analysis, first call, demo call, or "what should I ask on a sales call." Produces a discovery call flow with a prioritized question bank, qualification checks, and next-step language that advances the deal.

Email Lifecycle Sequence

Use when the user wants to build or fix lifecycle email — welcome sequences, onboarding emails, nurture, win-back, expansion, or re-engagement. Also use when the user mentions email sequences, drip campaigns, automated emails, lifecycle marketing, email flows, or "what emails should we be sending". Maps which sequences exist, checks the combined send load for fatigue, and writes the sequences that are missing.

Founder-Led Content

Use when a founder wants to run their own LinkedIn or social account as a go-to-market channel — deciding what to post before they have case studies, finding the themes only they can own, building a post bank, and setting a cadence that survives a bad quarter. Also use when the user mentions founder-led content, personal brand, founder brand, LinkedIn strategy, posting as the founder, thought leadership, content cadence, ghostwriting a founder, or "what should I post". Produces a readiness verdict before the first post, three tested themes, a bank drafted from material the founder already owns, and a per-post check against the rules.

GEO Citation Tracker

Use when the user wants to measure or monitor whether AI answer engines actually name and cite their brand over time — not whether a page is optimized, but what the engines are saying right now. Also use when the user mentions AI share of voice, LLM citation tracking, brand visibility in ChatGPT/Perplexity/Claude/AI Overviews, "are we showing up in AI answers", answer-engine monitoring, or wants to prove GEO work moved the needle. Designs the prompt set, scores the run, and says whether a change between runs is signal or noise.

GEO Content Optimization

Use when the user wants to optimize content so it gets cited by AI engines (ChatGPT, Perplexity, Claude, Google AI Overviews) and wins answer-engine snippets — i.e. GEO (generative engine optimization) and AEO (answer engine optimization). Also use when the user mentions AI citations, getting quoted by LLMs, llms.txt, answer-first content, featured snippets, or "make this content rank in AI answers." Rewrites/augments a page to maximize citation likelihood.

Incrementality & MMM

Use when the user wants to know whether marketing spend actually caused conversions, rather than just preceded them — incrementality testing, holdout or geo tests, iROAS, or media mix modelling. Also use when the user mentions incrementality, holdout test, geo test, lift test, iROAS, incremental CAC, MMM, "is this channel actually working", or doubts about attributed conversions. Designs the test, sizes it, then reads it out honestly — including whether it was ever powerful enough to answer the question.

Landing Page Brief

Use when the user wants to plan or spec a landing page before building it — structure, copy, sections, and conversion elements. Also use when the user mentions landing page brief, page wireframe, "what should go on this page", page outline, or wants a build-ready spec for a designer, developer, or page builder. Produces a section-by-section brief with copy direction and CTAs.

Lead Magnet & Free Tool Design

Use when the user wants to design a lead magnet, free tool, calculator, template, assessment or gated download that brings in buyers rather than downloads, or wants to know whether an existing one is worth keeping. Also use when the user mentions lead magnets, gated content, free tools, content upgrades, "what should we gate", email capture, or lead quality from downloads. Scores candidate ideas on the job they do for the buyer against the effort to build them, applies the rule "ungate ideas, gate tools", and reads a live magnet on qualified leads, not sign-ups.

Lifecycle & Retention

Use when the user wants to reduce churn, improve retention, or grow net revenue retention (NRR) through onboarding, lifecycle communication, and account expansion. Also use when the user mentions churn, retention, NRR/GRR, net dollar retention, activation, onboarding, customer lifecycle, upsell/expansion, or "why are customers leaving / how do we keep them." Produces churn, NRR, GRR, quick-ratio and lifetime math plus a diagnosis and a prioritized retention plan across onboarding, churn drivers, and expansion.

Market Sizing

Use when the user wants to size a market - TAM, SAM and SOM - for a pitch deck, a board plan, a new segment or a go-to-market decision. Also use when the user mentions market size, total addressable market, serviceable market, "how big is the opportunity", bottom-up sizing, or has a top-down analyst number they want to use. Builds the size bottom-up from counted accounts and sourced assumptions, derives SOM from the team's real capacity rather than a share of the market, and flags every link in the chain nobody sourced.

Marketing Budget Planning

Use when the user wants to set or sanity-check a total marketing budget — how much to spend overall, as a percentage of revenue, by company stage and business model — and split it across brand, demand gen, content, and tooling. Also use when the user mentions marketing budget, % of revenue on marketing, how much should we spend on marketing, or budget allocation across functions. Produces a budget from AAJ's stage bands (labelled as AAJ's own estimates), published reference points (Gartner, SaaS Capital) and a function-level split.

Marketing Leadership Model

Use when the user is deciding how to staff marketing leadership - hire a head of marketing or CMO, bring in a fractional CMO, or retain an agency - and wants the comparison on their own numbers rather than a vendor's. Also use when the user mentions fractional CMO, in-house vs agency, first marketing hire, marketing team structure, cost of a marketing hire, ramp time, or "should we hire or outsource marketing". Prices all three options over a horizon including ramp, search time, recruiting and the founder's own hours, finds the month the lines cross, prices the exit, and checks which shape of help fits the work that actually exists.

Marketing Loops

Use when the user wants to build or diagnose a compounding growth loop — referral, viral, content, or paid-recycling — rather than optimize a linear funnel. Also use when the user mentions growth loops, viral loop, viral coefficient, k-factor, referral loop, content loop, network effects, compounding growth, flywheel, "how do we grow without spending more", or "why doesn't our growth compound". Computes the loop factor, shows what it buys in amplification and effective CAC, finds the throttling stage, and projects users over time.

Marketing Maturity Assessment

Use when the user wants to know how mature their marketing is as a whole - where the function is strong, where it is weak, and what to fix first - or wants a structured way to assess a client's or a portfolio company's marketing. Also use when the user mentions marketing maturity, marketing audit, growth audit, marketing health check, "where do we stand", "what should we fix first", or a before-and-after on the marketing function. Scores the 18 statements of AAJ's Marketing Maturity Scorecard across six dimensions, names the weak links for the company's stage, asks for the evidence behind high self-scores, and compares with a previous run. Not a benchmark against other companies.

Marketing Psychology

Use when the user wants to apply behavioral science or persuasion principles to marketing — pricing pages, landing pages, onboarding, emails, offers, or CTAs. Also use when the user mentions psychology, cognitive bias, behavioral economics, persuasion, social proof, anchoring, loss aversion, scarcity, friction, or "why aren't people converting". Diagnoses which decision friction is actually blocking the buyer, then selects the principles that address it — with an explicit line between persuasion and manipulation.

Marketing Report & KPI Dashboard

Use when the user wants to build a board-ready marketing report, a KPI dashboard, or a monthly/quarterly performance review — turning raw funnel, spend, and pipeline numbers into metrics and a narrative leadership can act on. Also use when the user mentions marketing reporting, KPI dashboard, board deck, marketing metrics, funnel conversion, CAC or ROI reporting, attribution narrative, or "what do I show the board / how is marketing performing." Produces a full-funnel KPI snapshot (stage conversion, CAC, efficiency, attainment) with period-over-period deltas and a decision-focused narrative.

Messaging Framework

Use when the user wants to build a messaging framework or message hierarchy — the organized set of what to say, to whom, and in what order. Also use when the user mentions messaging, message hierarchy, messaging pillars, core message, talking points, message map, value pillars, or "what should our messaging be." Produces a messaging framework — one core message, 3–4 pillars with proof, audience variants, and what to keep off-message.

Objection Handling

Use when the user wants to handle sales objections or build objection and competitor battlecards — structured responses to the pushback that stalls deals. Also use when the user mentions objections, objection handling, "it's too expensive," competitor comparison, battlecards, rebuttals, deal blockers, status quo, or "how do I respond when they say X." Produces an objection-handling framework and competitor battlecards — the top objections with grounded, non-defensive responses and honest competitive comparisons.

Onboarding & Activation

Use when the user wants to improve product onboarding, activation rate, or time-to-first-value — getting new signups to the moment the product actually works for them. Also use when the user mentions activation, aha moment, time-to-value, first-run experience, product onboarding, user adoption, or "people sign up and never come back". Defines the activation moment from data, finds where new users stall, and specifies the fix.

Paid Media Budget Allocation

Use when the user wants to plan, split, or optimize a paid advertising budget across channels (Google, Microsoft, LinkedIn, Meta, TikTok, YouTube, Amazon, Capterra/G2, and more) to hit a CAC target or a customer goal. Also use when the user mentions ad budget allocation, channel mix, media plan, paid spend split, CAC target, marginal CAC, diminishing returns, or "how should I split my ad spend." Produces a defensible per-channel allocation with projected customers, blended CAC, LTV:CAC, payback, and pacing.

Paid Search Account Audit

Use when the user wants to audit a Google Ads or Microsoft Ads search account - their own, a client's, or one inherited from an agency - and find where the spend is wasted and where it is starved. Also use when the user mentions Google Ads audit, PPC audit, paid search review, search terms report, negative keywords, wasted ad spend, impression share lost to budget, "is our agency doing a good job", or "why is our CPA so high". Reads the account against its own target and its own numbers - never a published benchmark - in a fixed order: tracking, waste, starved winners, landing pages, with fixes ranked by the spend they touch.

Partnerships & Co-Marketing

Use when the user is choosing a co-marketing partner, has been asked to "do some co-marketing", or is planning a joint webinar, guide, integration launch or customer introduction. Also use when the user mentions partnerships, co-marketing, partner marketing, joint webinar, integration launch, channel partners, lead sharing, or "a company wants to partner with us". Scores partners on overlap rather than fame, writes the terms both sides sign before work starts, and reads the result out on pipeline rather than sign-ups.

Pipeline & Forecast

Use when the user wants to forecast sales or check pipeline health — whether there's enough pipeline to hit the number and what's likely to close. Also use when the user mentions sales forecast, pipeline coverage, weighted pipeline, quota attainment, pipeline gap, commit vs best case, coverage ratio, or "will we hit our number." Produces a weighted forecast (commit vs best case), a pipeline coverage ratio against the target, the gap, and how much new pipeline is needed.

Positioning Statement

Use when the user wants to write, sharpen, or pressure-test a positioning statement, value proposition, or core messaging for a product or company. Also use when the user mentions positioning, messaging, value prop, "what do we do / who is it for", category, differentiation, or competitive alternative. Produces a defensible positioning statement, supporting proof points, and a one-line value proposition, with variants by audience lens.

PR & Earned Media

Use when the user wants press coverage without a PR agency — pitching journalists, newsletter writers, podcast hosts or analysts, and deciding whether a story is worth pitching at all. Also use when the user mentions PR, earned media, press, media list, journalist pitch, press release, newsworthy, media outreach, getting covered, or "how do we get press". Produces a scored story verdict, a short targeted media list, a pitch draft checked against the rules, and the materials you must have ready before sending.

Pricing & Packaging

Use when the user wants to design or sanity-check pricing and packaging — the tiers, what's in each, and the price points. Also use when the user mentions pricing, packaging, tiers, plans, price points, good-better-best, pricing model, value metric, ARPU, or "how should we price this." Produces a packaging structure (tiers and what's in each), price points with rationale, and a modeled blended ARPU and revenue mix.

Pricing Page Teardown

Use when the user wants to review a pricing page - their own or a competitor's - or is thinking about changing a price and asks whether a test would tell them anything. Also use when the user mentions pricing page audit, pricing page teardown, price test, price experiment, A/B testing a price, revenue per visitor, "should we raise prices", or "can we test this". Scores the page on 21 checks a buyer would notice, ranks the fixes against competitors, works out before launch whether a live price test can answer the question at your traffic, and reads a test against its planned size.

Product Launch

Use when the user is planning a launch - a new product, a new market, a major feature, a pricing change - or is unsure how big a launch something deserves. Also use when the user mentions a launch plan, launch date, go-to-market for a release, launch tiers, go/no-go, launch checklist, "should we announce this", or a launch that is slipping. Tiers the launch first, scores readiness on the same twelve-item gate as the AAJ Launch Readiness Planner, and builds the dated work-back plan and launch-day go/no-go.

Programmatic SEO

Use when the user wants to generate many search-targeted pages from a template and a dataset — location pages, comparison pages, integration pages, calculator pages, "best X for Y" pages. Also use when the user mentions programmatic SEO, pSEO, scaled content, template pages, or "we have a database, can we turn it into pages". Models whether the build pays back before anything gets written, then specs the template and the quality bar.

Sales Enablement

Use when the user wants to give a sales team the material to move deals - battlecards, case studies, one-pagers, demo scripts, objection guides, business-case templates, security packs, mutual action plans - or asks why the content marketing produces goes unused. Also use when the user mentions sales enablement, sales collateral, sales content audit, rep adoption, sales and marketing alignment, or "what do reps actually need". Audits what exists against what each deal stage needs, checks whether reps use it and whether it is current, and ranks what to build next by the revenue being lost for want of it.

Sales Process Design

Use when the user wants to design or fix their sales process — the stages a deal moves through, what has to be true to advance, and what each side does. Also use when the user mentions sales process, sales stages, pipeline stages, deal stages, exit criteria, sales playbook, qualification, MEDDIC, BANT, or "our pipeline is messy." Produces a defined stage-by-stage sales process with entry triggers, verifiable exit criteria, owner actions, and a fitting qualification framework.

SEO / GEO / AEO Readiness Audit

Use when the user wants to audit a web page or site for SEO, GEO (generative- engine / AI citation readiness), and AEO (answer-engine / featured-snippet readiness). Also use when the user mentions SEO audit, AI search visibility, getting cited by ChatGPT/Perplexity/Claude, featured snippets, llms.txt, schema, crawlability, or "why don't we show up in AI answers." Produces a 0–100 score across 5 weighted categories, a grade, and prioritized fixes.

SEO Content Brief

Use when the user wants to plan or spec a piece of content before writing it — a content brief, an outline for a target keyword, or a blog post that needs to rank and get cited. Also use when the user mentions content brief, keyword targeting, search intent, SERP analysis, outlining an article, or "what should this post cover". Produces a writer-ready brief: intent classification, the answer block, heading structure, entities to cover, citation and internal-link targets, and the cannibalisation check.

Signup Flow Optimizer

Use when the user wants to improve a signup, registration, trial-start or checkout flow — reducing form fields, cutting steps, or fixing where people abandon. Also use when the user mentions signup conversion, form abandonment, trial start rate, registration flow, checkout friction, or "people visit and don't sign up". Scores the flow's friction, ranks what to remove by what it's worth, and specifies the rebuilt flow.

Target Account List

Use when the user wants to build or prioritize a target account list — which accounts to go after, scored by fit. Also use when the user mentions target accounts, ICP fit scoring, account prioritization, ABM list, named accounts, tiering accounts, lead scoring by firmographics, or "who should we sell to first." Produces a fit-scored, tiered account list (A/B/C) with the scoring rationale and the signals each account matched.

Unit Economics & LTV:CAC

Use when the user wants to calculate or sanity-check unit economics — LTV, CAC, the LTV:CAC ratio, and CAC payback — for a subscription, ecommerce, or services business. Also use when the user mentions lifetime value, customer acquisition cost, payback period, churn, contribution margin, or "are our unit economics healthy / can we afford to spend more." Produces the metrics plus a verdict against named reference points (Skok, Bessemer) and what to fix.

Value Proposition

Use when the user wants to write or sharpen a value proposition — the core promise of a product for a specific audience. Also use when the user mentions value prop, core promise, "what do we say we do", main message, hero message, tagline, or "why should anyone buy this." Produces a one-line value proposition plus supporting proof points, with variants by audience.

Webinar & Event Programs

Use when the user is planning a webinar, virtual event, roundtable, workshop or conference presence and wants it to create pipeline, or is looking back at one and asking whether it was worth it. Also use when the user mentions webinar ROI, cost per attendee, show rate, event follow-up, run of show, field events, or "how many registrations do we need". Plans the event backwards from a pipeline target using the user's own conversion rates, checks the run-of-show before invitations go out, and reads the result on meetings and pipeline against cost, never on registrations.

Website Conversion Audit

Use when the user wants to audit a landing page, homepage, or website for conversion — clarity, calls to action, trust, friction, speed, and tracking. Also use when the user mentions CRO, conversion rate, "why isn't this page converting", landing page review, page teardown, or improving signups/leads. Produces a 0–100 conversion score across 6 weighted categories, a grade, and prioritized fixes.

Win-Loss Analysis

Use when the user wants to understand why deals are won or lost and turn it into patterns they can act on. Also use when the user mentions win/loss, win-loss analysis, why we lose deals, deal post-mortem, lost-deal reasons, competitive losses, sales feedback, or "why aren't we closing." Produces a structured win-loss summary — top win and loss reasons, patterns by segment and competitor, the no-decision rate, and prioritized fixes for product, pitch, and process.