Writing · 8 notes
Notes from the field
Architecture, evaluation, rollout and the organisational work around them. Written from inside deployments, not from the conference stage.
- March 20, 20266 min
From NLU to GenAI: What Actually Breaks When You Migrate an Enterprise Voicebot
The technology migration was the easy part. What broke was everything around it — evaluation criteria, KPIs, team workflows, and stakeholder expectations.
- #digital-assistants
- #migration
- #enterprise
- #architecture
- March 20, 20266 min
The S.H.I.F.T. Framework: How I Think About Enterprise AI Governance
Most enterprise AI initiatives fail not because of technology, but because of missing governance. Here's the framework I use to fix that.
- #framework
- #governance
- #enterprise
- March 17, 20265 min
Lab → Shadow → Pilot → Rollout: How We Test GenAI Before It Talks to Real Customers
You can't A/B test a digital assistant that handles financial inquiries with 'let's see what happens.' Here's the 4-stage framework I use.
- #methodology
- #testing
- #evaluation
- #enterprise
- March 15, 20265 min
Why Enterprise GenAI Is Different
Consumer AI tools are impressive. Enterprise AI deployment is a different game entirely. Here's what changes when you go from demo to production.
- #enterprise
- #genai
- #strategy
- March 12, 20264 min
Why I Left Consulting to Build Enterprise AI From the Inside
After 10+ years at Accenture, Capgemini, and KPMG, I went in-house. The transition from advisor to builder changed everything.
- #career
- #consulting
- #enterprise
- #genai
- March 12, 20267 min
Voicebot vs Chatbot: What Changes When You Add Voice to Enterprise AI
Text-based chatbots and voice assistants share architecture but differ in almost everything else. Here's what I've learned building enterprise-scale voice systems.
- #digital-assistants
- #architecture
- #enterprise
- March 8, 20267 min
Agentic AI in the Enterprise: Why Orchestration Is the Hardest Problem Nobody Talks About
Every vendor shows seamless agent handoffs in demos. In enterprise production environments, 'seamless' is a fantasy. Here's what actually works.
- #agentic-ai
- #architecture
- #orchestration
- #digital-assistants
- March 8, 20267 min
How We Evaluate LLMs in Production (Not Just Vibes)
Benchmarks tell you how a model performs on tests. Production evaluation tells you how it performs on your problems. Here's the methodology I use.
- #evaluation
- #llm
- #methodology