Competitive Battlecard Builder

Inside this Project, Claude carries the library itself:

• Every battlecard built so far, in one consistent format.
• The source behind each claim — what it was, and when it was published.
• The last-verified date per competitor, so you can see at a glance which cards have gone stale.
• What has changed between refreshes — the competitive movement history that makes a repository more useful than a folder of documents.

Run one Project for your whole competitive set rather than one per competitor. Comparison across cards is most of the value.

Reach for this Project when:

• You need a battlecard for a competitor that appears in deals.
• An existing card is out of date and needs a documented refresh.
• A rep needs trap questions before a competitive call.
• You want to know what changed about a competitor since the last review.

Use something else when:

• You are positioning one specific deal against one competitor — that belongs in MEDDPICC Deal Strategy Workspace, under Competition.
• You are answering formal competitive questions in an RFP — that is RFP Response Assistant, which carries the escalation and sign-off model those answers need.

Per competitor, you provide:

• The competitor name.
• Source material — their website and pricing pages, product documentation, review-site content, analyst summaries, and your own win and loss notes.
• The date each source was published or retrieved, wherever you have it. This Project treats undated material as weaker evidence.

Your own win and loss debriefs are the highest-quality input you have. They describe what actually happened in deals, which no public source will tell you.

Upload these when you create the Project. The approved claims list is not optional.

Without the approved claims list this Project can still build a card, but it cannot tell a rep which claims are safe to say out loud — which is the part that carries risk.

Claude accepts files up to 30MB each, and there is no fixed limit on how many you add, but everything in a Project's knowledge has to fit the context window. Fewer, sharper files beat a full archive.

Prepare files this way:

• Strip cover pages, legal boilerplate, and navigation chrome — they consume context and carry no signal.
• Prefer text formats. A clean export beats a scanned PDF.
• Name each file for what it contains, not when you exported it. Claude reads filenames.
• One subject per file. A merged reference document is harder to cite precisely.
• Date anything that goes stale, inside the file itself, so Claude can tell you when it is working from old material.

1. Create the Project. Name it for the competitive set — for example Competitive Library — Core Market. One Project for all competitors.
2. Paste the Project Instructions.
3. Replace the three bracketed fields. The approved claims source is the one that governs risk; fill it even if the answer is a person's name rather than a document.
4. Upload the knowledge files, approved claims list first.
5. Build your first card for the competitor you meet most often, and check every claim it produces against what you already know. That calibration pass tells you whether your source material is strong enough.
6. Set a refresh rhythm. Monthly for competitors in active deals, quarterly for the rest.

The bracketed fields below are placeholders you replace with your own details before you save the instructions. Leaving them unfilled produces generic output — that is the single most common reason a Project underperforms in its first week.

This Project has three, all new — the original version had none, which meant it produced generic cards:

• [FILL IN: Company Name] — your employer, which sets the perspective the cards are written from.
• [FILL IN: Your Top Three Competitors] — who you actually lose to. This focuses the library and lets Claude tell you when a named competitor is outside your usual set.
• [FILL IN: Your Approved Claims Source] — where approved competitive claims live and who owns them. Name the document, or the person, or say explicitly that no approved list exists — in which case every claim is treated as unverified until a human clears it.

Role

You are a competitive intelligence analyst for [FILL IN: Company Name]. You build and maintain battlecards that a rep can use in a live deal, where every claim is traceable to a dated source and clearly marked as approved, confirmed, or unverified.

Operating rules

• Every competitive claim traces to a dated source. No source, no claim.
• Never assert a competitor limitation without evidence for it.
• Mark review-site and third-party material as unverified.
• Never repeat a disparaging claim that cannot be substantiated.
• Concede genuine strengths honestly — a card conceding nothing is not credible.
• Only claims on the approved list are safe to say to a prospect.

The eight-part card

Positioning summary · where they are genuinely strong · where they are constrained · differentiation map · trap questions · proof points · objection responses · do-not-say list.

The full instructions continue with the evidence-status rubric, the refresh workflow, the five commands, output formats, and escalation.

This Project produces four deliverables:

• Battlecard — the full eight-part card, every claim carrying a source and a verification status.
• Refresh — an updated card plus an explicit list of what changed since the last version.
• Trap questions — questions that surface a competitor's genuine constraints, each tied to evidence.
• Library status — which cards exist, when each was last verified, and which are overdue.

A battlecard. Cartwell Systems is fictional.

Battlecard — Cartwell Systems · last verified 9 August 2026

Positioning. Positions as the enterprise-grade option for regulated industries, leading with compliance certifications and audit tooling. Targets 1,000-plus employee organisations in financial services and healthcare. [Source: their homepage and solutions pages, retrieved 9 Aug 2026.]

Where they are genuinely strong

• Compliance certification breadth. They publish more certifications than we hold. [Confirmed — their trust page, dated July 2026.] In regulated deals this is a real advantage and should not be argued with.
• Audit trail depth. Consistently praised in review-site content. [Unverified — review-site aggregation, not independently confirmed.]
• Established enterprise references. Three named public-sector logos on their site. [Confirmed — their customers page, retrieved 9 Aug 2026.]

Where they are constrained

• Implementation timeline. Their own documentation describes a phased onboarding of 90 to 120 days. [Confirmed — their implementation guide, dated March 2026.] This is their published figure, not our characterisation.
• Mid-market fit. Four of our last six wins against them were sub-500-seat accounts where the buyer cited cost and setup burden. [Confirmed — internal win/loss debriefs, Q1–Q2 2026, n=6. Small sample; treat as a pattern, not a rule.]

Differentiation map

Trap questions

1. "What does your implementation timeline look like, and who staffs it on your side?" — surfaces a published constraint without asserting anything about them.
2. "How does pricing change as you add departments beyond the first?"
3. "Which certifications do you actually need for this use case, and by when?" — tests whether their strongest advantage is relevant to this buyer.

Proof points

• 21-day median time to first value across 40 implementations. [Approved claim — positioning doc, verified 1 July 2026.]
• Named mid-market reference willing to take calls. [Approved — reference programme.]

Do not say: anything characterising Cartwell as insecure, unreliable, or failing customers. Nothing in the sourced material supports it, and unsubstantiated disparagement of a named competitor carries commercial and legal risk.