AI skill · Volume 1 · Workflow W7
How do you build a TIC competitor battlecard from your own evidence?
It builds a competitor battlecard from your own evidence, or plays a sceptical buyer so you can practise answering objections, with a score.
It is workflow W7 of the twelve in The AI-Augmented TIC Sales Machine, sold on its own as one AI skill file (.zip) with a two-page start-here guide. Everything it writes is a draft for a person to check.
What you give it, and what comes back.
You attach: win/loss records, call transcripts and public material.
You get back: A battlecard built from your evidence, and objection practice with a score.
It does not: research the competitor. It builds from the evidence you give it.
The competitor and your evidence: win/loss records, call transcripts and public material. For objection practice, also the buyer's role, the industry, the objection and your approved objection-response library.
One run, start to finish
What it looks like when you use it.
Run in Claude (Opus 5, high effort), in our own Claude account with the skill installed on 20 September 2026. The firm, the records and the call notes are invented for this example, and the run is shown as it came back, unedited. No real competitor is named, here or in the run. Your assistant's wording will differ: AI answers change between assistants and between runs.
input · what was given to the skill
Our firm. Harbourline Testing Services. The competitor is described only as "the incumbent laboratory" at three shared accounts.
Our evidence, invented. Win/loss records for twelve months: four deals lost to the incumbent, three of them on lead time and one on price; two won after the incumbent missed a retailer deadline. Call notes: two customers said the incumbent's reports are hard to read; one said their account manager changed three times in a year. Public material: the incumbent's website lists a wider accreditation scope than ours, including battery testing.
output · what came back
Draft, internal only. A named owner must approve it before it is published to sellers. Never share with a customer.
Evidence base: 6 deals over 12 months, 3 call notes, 1 public website. That is a small sample. Treat the patterns as leads to test, not as settled fact.
what to notice
Every line is marked EVIDENCED or HYPOTHESIS, and the two are never mixed. The card says plainly where the competitor is genuinely better, tells sellers not to claim anything about the competitor's pricing because one lost deal proves nothing, and warns the owner not to let customers' complaints be repeated as our own claims about a named firm. That last point is a defamation risk in ordinary commercial language.
Then it says the thing a battlecard is not supposed to say: this card cannot fix the real problem, because three of the four losses were about turnaround, and that is an operations question, not a conversation.
The skill, or the report?
This workflow is not sold on its own. It comes with The AI-Augmented TIC Sales Machine, which sets out the method and the evidence for all twelve of its workflows, and every licence includes all twelve as ready-made skill files at no extra cost.