AI skill · Volume 1 · Workflow W5
How do you decide whether to bid for a TIC tender?
It recommends bid, bid with conditions or no-bid, drafts answers only from your approved content library with the gaps marked, and reviews the whole bid before it goes.
It is workflow W5 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: the tender, your scope, references and approved content library.
You get back: A bid or no-bid recommendation, answers from your own library with gaps marked, and a review of the assembled bid.
It does not: write from its own knowledge. Answers come from your library, with the gaps marked.
The tender, your accreditation scope and your references. For answers, also the tender question, your approved content library and who owns the gaps. For the final review, the assembled bid and the buyer.
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, its accreditation scope, the buyer and the tender are invented for this example, and the run is shown as it came back, unedited. 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. Accreditation scope: electrical safety and EMC for household appliances, and food contact migration for plastics. No battery testing, no radio testing, no site inspection service.
The tender, invented. A national retail group, RetailExample: a three-year framework for testing own-brand kitchen appliances, in four lots — electrical safety, EMC, battery safety for cordless items, and annual factory inspections at supplier sites in three countries. Bidders must tender for all four lots. A 48-hour response to sample receipt, penalties for late reports, and references from two retail customers of similar size. Our references: two appliance makers, one small retailer.
output · what came back
Draft, for the bid manager to review. Not a decision.
what to notice
Three of the six factors came back "not scorable", with the reason. An assistant that wanted to look useful would have scored all six and handed you a confident total. The refusal is the finding: a tender that does not say how it will be evaluated is a tender you are bidding blind.
The recommendation is also the one a bid manager would make. It says no, gives three conditions that would turn it into a yes, tells you to check a prospective partner's accreditation at the register rather than on their website, and suggests the subcontract route that gets the work without the penalty exposure. Nothing here is a decision: the bid manager still makes it.
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.