Free, always, for people For teachers and helpers Accessibility Privacy Legal llms.txt site.md
howtobedigital

Spaced Learning Practice

Build the practice in 180 days

Services first, recurring revenue second. The first automation priority is not adaptive AI — it is content lineage and QA workflow, because unsafe automation at item creation contaminates every later personalisation decision.

Stage-gated plan

PeriodBuildCommercial milestoneExit gate
Days 0–30Positioning, claims policy, research library, retention map, diagnostic method, security baseline, partner deck15 buyer interviews and 3 design partnersOne paid diagnostic or signed pilot intent
Days 31–60Competency schema, item template, fixed scheduler, email/Teams delivery, response capture, baseline dashboardConvert first curriculum and run internal dogfoodEnd-to-end traceability from source to response
Days 61–90SSO, consent, segmentation, delayed test, support playbook, experiment planLaunch one paid 100–1,000 learner pilotData quality and SME acceptance meet agreed threshold
Days 91–120Reusable connectors, AI drafting workspace, QA queues, multilingual workflow, executive reportSecure rollout decision and second clientAt least 50% of delivery assets reusable
Days 121–180Campaign operations, model monitoring, SLA dashboard, incident process, quarterly reviewConvert pilot to annual service and activate one channel partnerRepeatable implementation and positive unit economics
Automation map — AI drafts, humans approve
TriggerAutomated workRequired human gate
Source content uploadedParse, deduplicate, classify sensitivity, citations, detect expiryClient SME confirms authoritative sources
Objective approvedSuggest prerequisite map, misconceptions, evidence typesLearning scientist and SME approve
Item requestedDraft scenarios, distractors, rationales, variants, metadataID edits; SME signs correct answer and rationale
Item changedFactual consistency, duplication, reading level, bias, accessibility checksQA owner resolves failures
Low mastery detectedSelect approved remediation and shorten next intervalProgram owner pre-approves policy boundaries
Source or policy changesFind affected items, pause risky campaigns, draft updatesSME approves replacement content
Monthly reviewGenerate retention, transfer, burden, fairness, and SLA reportMeasurement lead signs interpretation

Worked example: a financial-services client changes an approved customer-verification policy. The lineage graph identifies every scenario whose answer depends on the old clause. Automation pauses those items, drafts replacements from the new approved text, and routes them to the compliance SME. Nothing reaches learners until the SME confirms the answer and rationale.

Every item needs source passage, objective, role, difficulty, correct answer, rationale, distractor rationale, misconception, language, version, approver, validity date, and accessibility status. NIST controls support ground-truth testing, adversarial evaluation, PII detection, subgroup monitoring, and human escalation.

Engine overview · Partner pilot