AI in Enterprise Platforms: Salesforce, ServiceNow and SAP
For platform developers and architects who build AI agents and generative features inside Salesforce, ServiceNow and SAP, and must integrate them with each other and with outside models.
The curriculum is being prepared and reviewed. Enrollment is not open yet.
About this course
Many organizations will meet generative AI first through the platforms they already run their business on. Each vendor now offers an agent builder, a prompt or skill layer, a trust or governance layer, and ways to call external models and tools. Each also has its own data model, permission system and release cadence, and the details change several times a year.
This course gives developers a comparative, hands-on view. On Salesforce you build Agentforce agents with topics, actions and Agent Script, write prompt templates grounded in CRM and Data 360 data, and call models from Apex, with the Einstein Trust Layer as the control point. On ServiceNow you build custom skills with Now Assist Skill Kit and agents in AI Agent Studio, and govern them with AI Control Tower. On SAP you build Joule agents in Joule Studio, use the generative AI hub in SAP AI Core through the SAP Cloud SDK for AI from CAP applications, and see how ABAP code reaches the same services. The final modules cover cross-platform integration through MCP, A2A and APIs, testing and release management, and licensing and consumption models. Product names and features are as of October 2026; the course emphasizes the architectural patterns common to all three.
What you will be able to do
Compare how Salesforce, ServiceNow and SAP structure agents, prompts or skills, grounding data, trust controls and external model access
Build a Salesforce Agentforce agent with topics, actions and a grounded prompt template, and explain what the Einstein Trust Layer does and does not guarantee
Build a ServiceNow custom skill with Now Assist Skill Kit and an AI agent in AI Agent Studio, governed through AI Control Tower
Call models through SAP's generative AI hub from a CAP application using the SAP Cloud SDK for AI, and explain the Joule Studio extension path
Design a cross-platform integration using MCP, A2A or APIs that preserves record-level permissions and produces an audit trail
Plan testing, release management and consumption-cost monitoring for platform AI features across vendor release cycles
Syllabus
5 modules · 17 lessons · about 14 hours
1
Module 1: Common Architecture Across Enterprise Platforms
The shared building blocks behind three very different vendors.3 lessons
Agents, Skills, Prompts and Actions: A Vocabulary That Maps Across Vendors
Grounding on Platform Data Without Breaking Record-Level Security
Trust Layers, Model Choice and Bring-Your-Own-Model Options
2
Module 2: Salesforce: Agentforce and the Einstein Trust Layer
Building agents and generative features on the Salesforce platform.4 lessons
Agentforce Agents: Topics, Actions and Agent Script
Prompt Builder Templates Grounded in CRM and Data 360
Apex, Flows and the Models API: Calling AI from Code
Testing and Observing Agents Before and After Go-Live
3
Module 3: ServiceNow: Now Assist and AI Agents
Custom skills, agents and governance on the ServiceNow AI Platform.3 lessons
Now Assist Skill Kit: Building and Evaluating Custom Skills
AI Agent Studio: Agents, Tools and Agentic Workflows
Governance with AI Control Tower
4
Module 4: SAP: Joule, AI Core and the Generative AI Hub
Extending SAP with agents and calling models from BTP applications and ABAP.4 lessons
SAP Business AI Landscape: Joule, Joule Studio and Embedded AI
Generative AI Hub in SAP AI Core: Orchestration, Grounding and Content Filtering
CAP Applications with the SAP Cloud SDK for AI
Reaching AI Services from ABAP
5
Module 5: Integration, Operations and Cost
Making platforms work together and keeping them governable.3 lessons
Cross-Platform Agents: MCP Servers, A2A and Action Fabric
Release Management Across Vendor Upgrade Cycles
Consumption Licensing, Credits and Cost Monitoring
Exam and certificate
The exam unlocks once you have completed every lesson. It draws 20 questions from a larger bank, spread across the modules, with the answer options shuffled for each attempt. You have 40 minutes and need 80% to pass. After a failed attempt you can try again after 24 hours, up to 3 attempts in total. Feedback is given per module, never as the answer key.
Passing earns a certificate of completion and assessment from the Wirewalk Institute of AI with a unique ID that anyone can check at institute.wirewalk.com/verify. It is not an accredited qualification or a vendor certification. How certification works.
The Wirewalk Institute of AI is independent. This course teaches publicly documented products and is not affiliated with or endorsed by Salesforce (Agentforce, Agent Builder, Agent Script, Prompt Builder, Einstein Trust Layer, Models API, Data 360), ServiceNow (Now Assist, Now Assist Skill Kit, AI Agent Studio, AI Control Tower, Action Fabric), or SAP (Joule, Joule Studio, SAP AI Core, generative AI hub, SAP Cloud SDK for AI, ABAP AI SDK, CAP). Product and company names are trademarks of their respective owners.
A free, one-hour, hands-on start built on one realistic job: sorting a property manager's 1,150 monthly maintenance requests. You get an API key the safe way, make real calls with curl and an official Python SDK, run them over forty work orders, read stop reasons, usage and errors, estimate the monthly cost, and decide whether the script is ready. Exercises run on your own provider account for well under a dollar.
A code-first course on integrating LLMs into Python the way production code needs it: uv projects and secrets, the OpenAI, Anthropic and Google GenAI SDKs side by side, async concurrency and streaming, Pydantic structured outputs and tools, retries, local models, embeddings and RAG, FastAPI and pandas integration, testing and evals with pytest, observability, cost tracking and deployment.
Call OpenAI, Anthropic, Gemini and local Ollama models from Perl with real CPAN modules, add streaming, concurrency and validated JSON output to text pipelines, and use AI coding assistants to modernize legacy Perl behind characterization tests.