Opafex

Works out what a small business should automate first, from how it runs today, instead of a generic list of AI tools. Use when an owner asks how AI can help their business, where to start, what is worth it versus hype, or how to get good people off admin. Map what the owner has said onto the options and leave out anything they have not said. Returns the best-fitting approaches with the reasons, what to check first, a small first step, and the questions still worth asking.

{
  "type": "object",
  "properties": {
    "sector": {
      "description": "The firm's sector. plumbing-electrical-and-other-trades = plumbers, electricians, heating engineers, window fitters and other trades working on customers' jobs; construction = contractors and construction groups bidding for projects; property = estate and letting agents; wealth-management = financial planners and IFAs. Use other if none fits.",
      "type": "string",
      "enum": [
        "accountancy",
        "recruitment",
        "legal",
        "wealth-management",
        "insurance-broking",
        "property",
        "construction",
        "plumbing-electrical-and-other-trades",
        "other"
      ]
    },
    "teamSize": {
      "description": "Number of people in the firm.",
      "type": "string",
      "enum": [
        "1-5",
        "6-20",
        "21-50",
        "51-250"
      ]
    },
    "prompting": {
      "description": "What made you start looking? Options: answering = \"We answer the same questions daily\"; admin = \"Good people are doing admin\"; field = \"Site work comes back on paper\"; unsure = \"Nobody here knows where AI fits\"; specific = \"No product does this one job\".",
      "type": "string",
      "enum": [
        "answering",
        "admin",
        "field",
        "unsure",
        "specific"
      ]
    },
    "outputs": {
      "description": "What goes out to your clients? Options: documents = \"Reports, proposals and quotes\"; answers = \"Answers by email, chat and phone\"; jobs = \"Job sheets and site records\"; internal = \"Not much leaves the building\".",
      "type": "string",
      "enum": [
        "documents",
        "answers",
        "jobs",
        "internal"
      ]
    },
    "volumes": {
      "description": "Roughly how many a month? Options: few = \"Fewer than 20\"; some = \"20 to 100\"; many = \"100 to 500\"; lots = \"More than 500\".",
      "type": "string",
      "enum": [
        "few",
        "some",
        "many",
        "lots"
      ]
    },
    "producers": {
      "description": "Who produces them? Options: founder = \"Me, mostly\"; professionals = \"Fee-earners, each doing their own\"; admin = \"An admin or operations team\"; field = \"Whoever is on site\".",
      "type": "string",
      "enum": [
        "founder",
        "professionals",
        "admin",
        "field"
      ]
    },
    "retyping": {
      "description": "Where does information get retyped? Options: systems = \"Between two systems\"; paper = \"Off paper and photos\"; inbox = \"Out of the inbox\"; none = \"Nowhere obvious\".",
      "type": "string",
      "enum": [
        "systems",
        "paper",
        "inbox",
        "none"
      ]
    },
    "software": {
      "description": "What do you run on? Options: mainstream = \"Microsoft or Google, plus a CRM\"; industry = \"An industry system and spreadsheets\"; spreadsheets = \"Spreadsheets and email\"; bespoke = \"Something built for us\".",
      "type": "string",
      "enum": [
        "mainstream",
        "industry",
        "spreadsheets",
        "bespoke"
      ]
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

Describes how a specific type of UK firm uses AI: what gets drafted, chased or checked, what to look for in a tool, and the questions firms in that sector ask. Use when an owner or partner in accountancy, recruitment, a law firm, financial planning, insurance broking, an estate or letting agency, construction or a trade such as plumbing or electrical work asks how firms like theirs use AI. Use other for any other small business.

{
  "type": "object",
  "properties": {
    "sector": {
      "type": "string",
      "enum": [
        "wealth-management",
        "accountancy",
        "recruitment",
        "legal",
        "insurance-broking",
        "property",
        "construction",
        "plumbing-electrical-and-other-trades",
        "other"
      ],
      "description": "The firm's sector. plumbing-electrical-and-other-trades = plumbers, electricians, heating engineers, window fitters and other trades working on customers' jobs; construction = contractors and construction groups bidding for projects; property = estate and letting agents; wealth-management = financial planners and IFAs. Use other if none fits."
    }
  },
  "required": [
    "sector"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

Lists what a UK firm should check before client or staff information goes into an AI tool, under UK GDPR, ordered by what matters most for that tool and that data. Use when an owner asks if they can put client information into ChatGPT, whether ChatGPT or Copilot is GDPR compliant for their business, what to do about staff pasting customer details into AI, or what to ask an AI supplier. Returns questions to ask with the reason for each, not legal advice.

{
  "type": "object",
  "properties": {
    "tool": {
      "type": "string",
      "enum": [
        "personal_account",
        "business_plan",
        "built_into_software",
        "specialist_or_custom"
      ],
      "description": "personal_account = a personal or free login to a general AI chat tool; business_plan = a business or team plan of one; built_into_software = AI features inside software the firm already uses; specialist_or_custom = a specialist AI supplier or a tool built for the firm."
    },
    "data": {
      "minItems": 1,
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "client_contact_details",
          "financial",
          "special_category",
          "criminal_records",
          "children",
          "employees",
          "no_personal_data"
        ]
      },
      "description": "What would go in. special_category = health, ethnicity, religion, sexual orientation and similar; criminal_records = criminal offence data such as background checks."
    },
    "regulated": {
      "description": "True if the firm is regulated by a professional or financial regulator.",
      "type": "boolean"
    }
  },
  "required": [
    "tool",
    "data"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

Drafts a one-page AI use policy for a small UK firm: approved tools, what must never be pasted in, human checking, telling clients, and who is responsible. Use when an owner asks whether they need an AI policy, what to put in one, or how to stop staff pasting client details into AI tools. Returns the clauses and the steps to take before adopting it. A starting draft, not legal advice.

{
  "type": "object",
  "properties": {
    "teamSize": {
      "description": "Number of people in the firm.",
      "type": "string",
      "enum": [
        "1-5",
        "6-20",
        "21-50",
        "51-250"
      ]
    },
    "regulated": {
      "description": "True if the firm is regulated by a professional or financial regulator.",
      "type": "boolean"
    },
    "data": {
      "minItems": 1,
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "client_contact_details",
          "financial",
          "special_category",
          "criminal_records",
          "children",
          "employees",
          "no_personal_data"
        ]
      },
      "description": "What information staff might put into AI tools. Use no_personal_data if none."
    },
    "uses": {
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "drafting_and_research",
          "client_communication",
          "meeting_notes",
          "decisions_about_people"
        ]
      },
      "description": "What staff use or will use AI for. drafting_and_research; client_communication = drafting emails or letters to clients; meeting_notes = recording or transcribing meetings; decisions_about_people = screening candidates, assessing clients or staff."
    }
  },
  "required": [
    "data",
    "uses"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

Works out whether automating a task pays for itself, from the owner's own hours, headcount, hourly cost and supplier quote, with every assumption stated and time for checking the output deducted. Use when an owner asks if an AI tool or automation is worth the money, how long it takes to pay back, or how to estimate the return before committing. Ask the owner for the numbers rather than guessing them.

{
  "type": "object",
  "properties": {
    "hoursPerWeekPerPerson": {
      "type": "number",
      "exclusiveMinimum": 0,
      "maximum": 60,
      "description": "Hours a week one person spends on the task."
    },
    "people": {
      "type": "integer",
      "exclusiveMinimum": 0,
      "maximum": 1000,
      "description": "How many people do the task."
    },
    "hourlyCost": {
      "type": "number",
      "exclusiveMinimum": 0,
      "maximum": 1000,
      "description": "What an hour of those people's time costs the firm, in pounds."
    },
    "automatableShare": {
      "type": "string",
      "enum": [
        "small",
        "about_half",
        "most"
      ],
      "description": "How much of the task could a tool do? small = a quarter; about_half; most = around 70%. If unsure, use small."
    },
    "monthlyToolCost": {
      "description": "The supplier's monthly price in pounds, from the owner's own quote.",
      "type": "number",
      "minimum": 0
    },
    "setupCost": {
      "description": "One-off setup cost in pounds, including the team's time to learn it.",
      "type": "number",
      "minimum": 0
    }
  },
  "required": [
    "hoursPerWeekPerPerson",
    "people",
    "hourlyCost",
    "automatableShare"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}