AI-216 AI & Data

Document AI & Intelligent Document Processing

Engineer the highest-volume enterprise AI use case properly: invoices, claims, contracts and forms turned into validated structured data. Learners build a classify-extract-validate pipeline over realistic scanned documents, attach calibrated per-field confidence, and route only the uncertain cases into a review queue. The course is scored on straight-through-processing rate against error rate, so learners leave able to argue where an auto-approval threshold belongs.

B4Professional

6modules

42skill atoms

2role journeys

Curriculum

What this course covers.

6 modules, 42 named skill atoms. Expand any module to see them.

1The IDP Pipeline7 skill atoms

classify then extract then validate stagesdocument type taxonomypage splitting on multi-document scansstraight-through processing as the target metricexception queue as a first-class pathcost per document versus manual baselinesuccess criteria fixed before build

2OCR and Its Failure Modes7 skill atoms

Tesseract vs cloud OCR enginescharacter and word confidence scoresdeskew denoise and binarisation preprocessing200 vs 300 dpi scan qualityhandwriting stamps and overlapping signaturesmulti-column and rotated pagesOCR error propagation into extraction

3Layout Understanding7 skill atoms

document VLMs as the 2026 default extraction pathreading order reconstructionbounding boxes as spatial featureswhen a fine-tuned encoder still wins on cost at volumethe LayoutLMv3 non-commercial licence trapheader footer and marginalia detectionsection segmentation on long contracts

4Key-Value and Table Extraction7 skill atoms

key-value anchoring to labelsline-item table detectionborderless table reconstructionmerged and spanning cellstotals and arithmetic cross-checksvendor template drift over timeLLM extraction under a constrained schema

5Structured Output and Confidence7 skill atoms

pydantic and JSON Schema contractsfield-level confidence calibrationnormalising dates currencies and addressesbusiness rule validationmaster-data matching against vendor and customer listsrepair vs reject on invalid outputidempotent reprocessing

6Human Review and STP Rates7 skill atoms

review queue design and field focus orderper-field confidence thresholdsreviewer throughput and seconds per documentcorrections harvested as training dataauto-approval threshold tuningSTP rate against escaped-error rateaudit trail and retention obligations

Where it fits

AI-216 in the role journeys.

This course appears in 2 of our 45 role journeys. Here is what a learner takes immediately before and after it in each.

GenAI / LLM Engineer

Professional stage

AI-405→AI-216→AI-208

AI Product Manager / BA

Professional stage

AI-504→AI-216→AI-511

Roles this course serves

AI Product Manager / BA GenAI / LLM Engineer

The capability ladder

This course is authored to band B4.

Every course we run is written to one rung of the CASI ladder, so a plan can be assembled to take a team from where they are to where they need to be.

What do B1–B6 mean?The CASI Capability Ladder — click to expand

Every course targets a band on the CASI Capability Ladder — our six-band proficiency scale, anchored to open standards (O*NET, ESCO, NICE, NIST AI RMF, Bloom's). A band tells you how deep a course goes, and what evidence proves it.

What the learner can doTypical evidence

AwareUnderstands concepts and vocabulary; uses tools with guidance

Knowledge checks

FoundationPerforms standard tasks correctly in familiar contexts

Guided labs, autograded exercises

PractitionerDelivers complete pieces of work independently

Scenario labs, proctored hands-on exams

ProfessionalHandles production-grade complexity, trade-offs and failure modes

Break-fix drills, design defenses

AdvancedEngineers systems end-to-end under constraints; leads others

Rubric-scored capstones, vivas

ExpertSets direction; recognised authority across teams

Portfolio + panel evaluation

A note on B6. Courses in this catalog target B1–B5. B6 is not taught — it is recognised, through a portfolio and a panel, once someone is setting direction for others. Every journey here is built to land a learner at B5.

Other AI courses at this level.

AI-112

Run AI-216 for your team.

This course runs at several lengths depending on how deep you need to go and how much of it your people already have. Tell us who is being trained and we will scope it.

Add it to a training plan Talk to our team Check your team’s level free

Document AI & Intelligent Document Processing

What this course covers.

AI-216 in the role journeys.

GenAI / LLM Engineer

AI Product Manager / BA

Roles this course serves

This course is authored to band B4.

Other AI courses at this level.

Departmental AI Adoption & Automation Design

Transformers from First Principles

Fine-Tuning with Hugging Face

Distributed Training Foundations

Synthetic Data Generation & Evaluation

Vector Databases & Hybrid Search

Run AI-216 for your team.