For product & platform teams

Training programs for teams shipping AI systems

Cohort-style learning with real deliverables — code, playbooks, and evaluations. Designed for teams who want leverage, not hype.

Beginner

Automation Bootcamp (1-week)

From spec to deploy: ship a working workflow with monitoring, retries, and docs.

  • Scope → MVP
  • Workers/Functions
  • Queues & retries
  • Observability & docs
Beginner

Workflow AI Design Blueprint

Turn messy processes into automation-ready flows with clear owners, steps, and metrics.

  • Process discovery & mapping
  • Designing human-in-the-loop steps
  • Tool selection & routing patterns
  • Blueprint docs your team can own
Intermediate

Prompt Design Certification

Frameworks, evaluation, guardrails, and governance — with graded exercises.

  • Prompt patterns
  • Safety & policies
  • Evals & testbeds
  • Change mgmt
Intermediate

AI Video SOP Generation & Automation

Turn screen recordings into structured SOPs with titles, timestamps, owners, and automated reviews — published to your KB.

  • Ingest Loom/mp4 → transcript + steps
  • Auto-title, tags, owners, due dates
  • Export to Notion/Confluence/Docs
  • Review & reminders via Slack/Email
Intermediate

AI Assistant Observability & SLOs

Instrument your assistants like production services — with traces, metrics, and SLOs for quality.

  • LLM-specific metrics & events
  • Session analytics & funnels
  • Alerting on failures & drift
  • Executive-ready dashboards
Advanced

Data for AI Teams (GPTs & Gemini Gems)

Hands-on data pipelines and analysis: build assistants trained on your company data for secure, reproducible insights.

  • Data governance & PII handling
  • Embeddings + retrieval over docs/DBs
  • Chat-SQL/Python analysis loops
  • Dashboards & scheduled reports
Advanced

Architecting Multi-Tenant AI Apps

Tenancy models, security, observability, and upgrade paths for white-label platforms.

  • Tenant isolation models
  • RBAC & audit trails
  • Billing (Stripe)
  • Migrations & upgrades
Advanced

AI Guardrails & Safety Engineering

Design, test, and ship guardrails that keep your assistants safe, compliant, and predictable in production.

  • Safety policies & red-teaming loops
  • Classification, filters & rule engines
  • Golden sets for safety & refusals
  • Dashboards & regression checks
Advanced

Advanced Retrieval Engineering (RAG That Actually Works)

Hands-on retrieval patterns that survive real users, messy data, and evolving content — not just demos.

  • Hybrid search & chunking strategies
  • Embedding selection & evaluation
  • Caching & failure fallbacks
  • Retrieval observability & tuning