Super Intelligence InstituteCorporate learning & development
Get a proposal

D1 Foundations & Fluency

D2 Applied Thinking & Knowledge Work

D3 Agentic & Technical Capabilities

D4 Leadership & Management

D5 Business Functions

D6 Responsible Adoption & Transformation

All workshopsLearning portfolioLearning formatsPrivate corporate delivery

Agentic & Technical Capabilities

Building SI Agents and Automations

A five-day build program: participants design, build, test and document working SI agents and automations with no-code, low-code and light-code tools.

Duration
5 daysor 10 half-day virtual sessions
Level
Advanced
Formats
Public workshop, Private corporate, On-site, Live virtual, Blended
Public dates
To be announced
Register interestRequest for your team

01 — Overview

The challenge

Many organizations have more SI ideas than people who can build them. Waiting for central IT for every use case slows adoption, while uncontrolled building creates risk. Organizations need citizen developers and digital teams who can build useful SI solutions within proper guardrails.

About this workshop

An intensive, project-based workshop in which participants build functioning prototypes. Starting with assistants that use tools and knowledge, participants progress to retrieval-based knowledge agents, multi-step automations connected to business systems, and evaluated, documented solutions ready for an internal pilot. Each participant or team leaves with a working prototype for a real use case.

02 — Who it is for

  • Technical & digital teams
  • Functional specialists
  1. 07.1Digital, automation and IT professionals extending their skills into SI.
  2. 07.2Citizen developers and power users with automation experience.
  3. 07.3Business analysts and process owners who build no-code solutions.
  4. 07.4Members of SI centers of excellence and innovation teams.

Recommended prerequisites

  • Prompt Engineering and Context Engineering, or equivalent experience.
  • Experience with at least one automation or no-code tool (for example Power Automate, Zapier or Make) is strongly recommended.
  • A basic understanding of APIs and data formats such as JSON is helpful. Light-code exercises are optional.

Level: Advanced

For builders and technical professionals. Prior experience required.

Competency families

Technical

03 — Learning objectives

By the end of the workshop, participants will be able to:

  1. 01Build assistants with instructions, knowledge sources and tools.
  2. 02Implement retrieval-augmented generation (RAG) over organizational documents and evaluate answer quality.
  3. 03Connect SI steps to business systems through multi-step automations and APIs.
  4. 04Design agents with guardrails, permissions, human approval steps and logging.
  5. 05Test, evaluate and document a solution so that it can move to a supervised pilot.

04 — Curriculum

5 days, 10 modules. In live virtual delivery each day runs as two half-day sessions.

Day01

  1. Assistants with knowledge and tools

    • Configuring instructions, knowledge and actions
    • Choosing the right building platform
    • Build: a team assistant for a defined task

  2. Use-case scoping

    • Selecting a buildable use case
    • Defining inputs, outputs and success criteria
    • Data access and permissions

Day02

  1. Retrieval-augmented generation

    • How RAG works: indexing, retrieval and generation
    • Preparing documents for reliable answers
    • Build: a knowledge agent with citations

  2. Evaluating answer quality

    • Test sets and acceptance criteria
    • Telling retrieval errors from generation errors
    • Iterating to measurable improvement

Day03

  1. Automations with SI steps

    • Triggers, actions and data flow
    • Classification, extraction and drafting steps
    • Build: an intake-to-response automation

  2. Connecting systems

    • APIs and connectors
    • Tool use and the Model Context Protocol
    • Error handling and retries

Day04

  1. Agents with guardrails

    • Planning and multi-step tool use
    • Permissions, approval steps and limits
    • Build: an agent with human approval checkpoints

  2. Security and reliability

    • Prompt injection and data-leakage risks
    • Logging and monitoring
    • Cost and performance considerations

Day05

  1. Capstone build

    • Completing the team prototype
    • Evaluation against acceptance criteria
    • Documentation and handover

  2. Demonstration and pilot plan

    • Live demonstrations and peer review
    • Pilot proposal and governance requirements
    • Personal development plan

05 — Practice & tools

Hands-on exercises

  1. 01Build a team assistant with instructions, knowledge and an action.
  2. 02Build and evaluate a document question-answering agent with citations.
  3. 03Build an automation that classifies incoming requests, drafts responses and routes exceptions to a person.
  4. 04Red-team your own agent for prompt injection and data leakage.
  5. 05Capstone: build, evaluate and demonstrate a prototype for a real use case.

Practical skills developed

  1. 01No-code and low-code agent building.
  2. 02Knowledge base preparation, chunking and retrieval configuration.
  3. 03Workflow automation with SI steps, triggers and integrations.
  4. 04Tool use and API calls, including the Model Context Protocol (MCP).
  5. 05Evaluation, monitoring and solution documentation.

Tools, technologies and workflows

Agent builders
e.g. Microsoft Copilot Studio, custom GPTs, Claude Projects or Google agent tools
Automation platforms
e.g. Power Automate, n8n, Make or Zapier
Retrieval and data
search and retrieval features of the chosen platform, connected to SharePoint, Google Drive or similar sources
Light-code (optional)
Python notebooks and model APIs, written with SI coding assistants

Product names are examples, not endorsements. Private workshops use your organization’s approved tools; our teaching is vendor-neutral.

Technology maturity: Emerging

Assistant building and workflow automation are established. Tool-using agents and MCP-based integrations are emerging and change quickly; the program focuses on patterns that are reliable today and marks experimental approaches as such.

Maturity map

06 — Outcomes

Participants can independently build SI assistants, knowledge agents and automations.

Expected outcomes

  • Solutions include guardrails, evaluation and documentation from the start.
  • The organization gains working prototypes ready for supervised pilots.
  • Builders apply consistent security and quality practices.

Participants leave with

  1. 01A working prototype for a real use case, with documentation.
  2. 02An evaluation report against acceptance criteria.
  3. 03A pilot proposal including governance and monitoring requirements.
  4. 04Reusable build templates and checklists.

07 — Dates & delivery

Public sessions

No public dates are published yet.

Register your interest below and we will contact you as soon as a session is scheduled. Dates, venue and fees are confirmed before you commit to anything.

Available formats

For your organization

This workshop can be delivered privately for your teams — on-site, at a venue or live virtual — with cases and exercises adapted to your context.

Request a proposal

08 — Register interest

Register interest

Tell us that you would like to join this workshop. Registering interest is not a booking: we contact you when dates are confirmed, and you decide then.

Fields marked (required) must be filled in.

I am interested in (optional)

Preferred format (optional)

Helps us plan where and when to schedule public sessions.