Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

YouTube

How to Scale AI Without Breaking the Bank - Typeform's Strategy

JavaScript Conferences by GitNation via YouTube

Overview

Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Learn how to implement enterprise-scale AI infrastructure without breaking your budget through this 23-minute conference talk from TechLead London 2025. Discover Typeform's practical approach to democratizing AI access across engineering teams using AWS Bedrock and MCP servers, moving beyond simple ChatGPT Plus subscriptions to create a comprehensive, cost-controlled AI ecosystem. Explore the architectural decisions behind choosing AWS Bedrock over direct vendor integrations to solve billing chaos and eliminate high-friction IAM/VPN requirements. Master the implementation of self-serve Bedrock API keys and internal CLI tooling that enables unlimited, unmetered LLM access for every engineer. Understand how to support federated usage patterns that allow engineers to use their preferred AI tools—whether Cursor, Cline, or Emacs—while maintaining centralized security and billing control. Examine real-world applications including transforming engineering hiring processes by replacing algorithmic tasks with AI-pairing interviews, and building MCP servers for design system prototyping. Gain insights into the core principles of empowerment over prescription, and learn why a "paved road" approach enables tool flexibility while maintaining organizational control and preventing vendor lock-in.

Syllabus

- Intro: Typeform context & Stack
- The Reality Gap: Hype vs. Actual Enterprise Adoption
- The Strategy: Democratizing Access & Federating Usage
- Architecture: Why we chose AWS Bedrock
- The Friction: Why IAM Roles & VPNs kill adoption
- The Unlock: Switching to Bedrock API Keys
- Internal Tooling: The "Generate Bedrock Token" CLI
- Build vs. Buy: Why AWS Bedrock beats direct Anthropic accounts
- Result: Unlimited, unmetered LLM access for every engineer
- Federated Usage: "Bring Your Own Tool" Cursor, Emacs, CLI
- Hiring: Replacing algo-tasks with AI-pairing interviews
- Design System: Building an MCP Server for prototyping
- Core Principles: Empowerment over Prescription
- Conclusion & Resources

Taught by

JavaScript Conferences by GitNation

Reviews

Start your review of How to Scale AI Without Breaking the Bank - Typeform's Strategy

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.