Course Objective & Scope
Classic automation tools excel at fixed rules but break down when faced with free-form customer emails, varied PDFs or ambiguous requests. This course teaches how to embed AI nodes—LLM APIs, document parsing, intent and sentiment classification—inside deterministic workflows to build reliable hybrid automations.
Participants build a working case flow that turns unstructured inputs into validated JSON schemas, routes items by confidence and escalates edge cases to human review.
Who Should Attend?
- Specialists with basic automation experience looking to add AI steps to workflows
- Business analysts, operations development and process automation teams
- Units digitising customer operations, finance and procurement workflows
- Low-code/no-code builders
Key Takeaways
- Decide which steps in a flow belong to deterministic rules versus LLM calls
- Extract structured JSON outputs from free text and documents
- Validate LLM outputs against schemas and business rules before updating downstream systems
- Route low-confidence or high-risk cases automatically to a human approval queue
- Balance token cost, latency and accuracy when selecting models
Curriculum
Combining Deterministic Automation with AI
- The hybrid pattern: rule engine + LLM node + rule engine
- Keeping AI steps narrow, measurable and bounded
From Unstructured Input to Structured JSON
- Entity extraction from free text, forms and attachments
- Defining structured output / JSON schemas and required-field checks
Classification, Summarisation and Smart Routing
- Routing by category, urgency and sentiment
- Summarising ticket or interaction history before handing off to a team
Validation, Confidence Thresholds and Fallbacks
- Checking LLM outputs with regex and business rules
- Falling back to human review when inputs are ambiguous or incomplete
Cost, Latency and End-to-End Case Lab
- Splitting work between small/fast models and larger reasoning models
- Building and validating a full case workflow against a test dataset
Other Courses in This Category
-
Design multi-step, context-aware enterprise workflows using LLM APIs, prompt chaining, routers, evaluator-optimizer loops and tool calling patterns.
- Live Course
- 5 modules
-
Extract structured data from invoices, contracts, delivery notes and scanned PDFs using OCR and vision-language models, validate it against business rules and push it into ERP or finance systems.
- Live Course
- 5 modules
-
Triage shared inboxes, support tickets and contact forms with LLMs by intent, category, urgency and sentiment, extract key fields, route to the right team and generate draft replies.
- Live Course
- 5 modules
-
Accelerate the marketing and sales funnel with automated lead enrichment, scoring, personalised outreach, pre-meeting account briefs, CRM updates and proposal/follow-up workflows.
- Live Course
- 5 modules
-
Automate recruiting coordination, onboarding/offboarding checklists, employee policy Q&A, leave/expense/procurement approvals and internal service requests with human checkpoints.
- Live Course
- 5 modules
-
Connect systems without built-in connectors using REST APIs, webhooks, OAuth2/API keys, pagination and JSON transformations inside workflow automation platforms.
- Live Course
- 5 modules
Get in touch
