Rules or AI? How to choose for an automation task
Break down a business task, identify explicit rules and test where AI may help. Work through a request-routing example with a practical decision checklist.
Read the guideAI · Software · Automation
Practical guides by Eric Muriel: apply AI in your business, learn to build useful solutions and check the results. Clear explanations, context and limitations.
20 guides · Page 1 of 4
Break down a business task, identify explicit rules and test where AI may help. Work through a request-routing example with a practical decision checklist.
Read the guideBuild a simple test with questions, evidence and acceptance criteria. Use a worked exercise to find unsupported answers before relying on an assistant.
Read the guidePractise extracting commitments, owners and deadlines without inventing them. Includes fictional notes, a reusable instruction and a reference answer.
Read the guideWrite an operating note covering inputs, rules, owners, failures and recovery. Test the handover with a practical exercise that reveals missing information.
Read the guideDefine users, tasks, data and scope before building an app. Complete a practical brief using a fictional office-supply request.
Read the guideReplace vague requirements with checkable examples. Define inputs, actions and outcomes using a request-approval exercise.
Read the guideCreate a prototype with fictional data to check a user journey. Separate what the interface demonstrates from what still needs implementation.
Read the guideRun a short session around a task, observations and decisions. Turn general comments into changes you can check.
Read the guideCheck columns, identifiers and missing values with a fictional sample. Decide what to preserve, correct or set aside before importing.
Read the guidePrepare form-validation cases for empty fields, boundaries and save failures. Check error messages and whether entered data is preserved.
Read the guidePractise extraction with defined fields, missing values and supporting passages. Compare the output with an expected answer.
Read the guideRehearse repeated events, lost responses and conflicting data. Define an operation’s identity before enabling retries.
Read the guidePrepare a summary that preserves conditions, exceptions and missing information. Practise with a fictional notice and a review checklist.
Read the guideDistinguish additions, changes and removals using a short example. Keep previous and new wording available to check each difference.
Read the guidePractise drafting from confirmed facts. Separate evidence, open questions and commitments before reviewing a customer reply.
Read the guideDefine the period, check counts and limit conclusions to the evidence. Includes a numerical example you can verify by hand.
Read the guideCapture expected behaviour, observed behaviour and known impact. Separate symptoms, hypotheses and confirmed causes in a useful incident record.
Read the guideCheck pages, links, languages and main actions in a preview. Prepare a manual review with evidence and specific outstanding issues.
Read the guideChoose a useful AI use case, prepare examples and run a small pilot. A practical guide to measuring value, errors and the full cost of implementation.
Read the guideA practical learning path: define a problem, build a small AI workflow and check the results. Learn the difference between a demo and a reliable solution.
Read the guide