Additional Resources

Official Documentation

The primary reference for all Kindo platform features, configurations, and best practices.

Slide Decks

Presentation materials for each content module (available in PPTX and PDF formats).

🚧 Coming soon: Slide decks will be uploaded after pilot session confirmation. 11 decks total (one per module).

Video Overviews

NotebookLM-generated video overviews for each content module (~5-10 min each).

🚧 In progress: Video overviews are being generated via NotebookLM. 8 of 11 triggered, downloads pending. Will be available before the pilot session.

Interactive Training Assistant

A Kindo-powered chatbot trained on the full platform documentation. Ask questions and get step-by-step guidance at your own pace.

🚧 Coming soon: The interactive training assistant chatbot will be shared with the pilot group before the session. (Tony's email, March 17)

Use Case Templates

Cybersecurity Workflows

  • Firewall Rule Optimizer — Categorize firewall rules for cleanup (risky, over-permissive, unused, redundant) → Exercise A
  • NIST CSF Compliance Mapper — Map evidence to NIST CSF controls and evaluate compliance → Exercise B
  • Alert Triage — Analyze security alerts from CrowdStrike, Splunk, or other tools
  • Vulnerability Reporting — Aggregate vulnerability scan results and prioritize remediation
  • Threat Hunting — Query integrated tools for indicators of compromise

Additional Use Cases

  • Incident response automation
  • IAM access reviews
  • Cloud infrastructure audits
  • Compliance reporting (ISO 27001, SOC 2, PCI DSS)
  • Log analysis and anomaly detection

Integration Guides

Step-by-step setup instructions for integrations relevant to Deloitte's stack:

Best Practices Quick Reference

Prompt Engineering

  • State the agent's role explicitly ("You are a senior security analyst...")
  • Define expected output format (tables, JSON, structured reports)
  • Specify boundaries and constraints ("Only report Critical and High severity findings...")
  • Include examples for nuanced tasks
  • Add confidence levels to make output actionable

Knowledge Store Tips

  • Attach only files relevant to the agent's task
  • Prefer structured formats (Markdown, CSV, JSON) over unstructured text
  • Keep reference files current with a regular review cadence
  • For large documents, consider breaking them into focused chunks

Agent Construction

  • Give each step one job. If a step analyzes, prioritizes, writes a report, and files a ticket, it's doing too much.
  • Name steps descriptively. "Fetch Open Vulnerabilities" is more maintainable than "Step 1".
  • Use the right step type. LLM Steps for reasoning, API Action Steps for deterministic reads/writes, Action Steps for integrated product actions.
  • Test iteratively. Build one step, test it, then add the next step. Don't try to build the entire agent at once.

Community & Support

  • GitHub Repository: client-kindo-lms (training materials and resources)
  • Kindo Support: Contact your Kindo account team (Ron Williams, Tony Wong, Bryan Vann, Sean Walker, Joana Dias)