RAG is why the reports of my career's death are exaggerated
LLMs are most useful at narrow tasks. The more complex the chore, the more it needs to be decomposed and guided with the right context, controls, quality gates, and security.
As in, the more you need the skills of a talented software architect to build that system.
The reports of the death of my career were an exaggeration. RAG (Retrieval Augmented Generation) is actually one of the reasons I'm not worried.
Aishwarya Srinivasan puts it well: RAG is the actual architecture behind successful enterprise AI systems. Building production-ready RAG systems demands real software architects and engineers.
If you're already familiar with the concept of RAG, her myth-busting and 10 essential RAG patterns are still worth your time.
https://youtu.be/v0ynfDPpe4E
We've been implementing RAG across widely varying contexts at Codality and getting quite good at wrangling GenAI to do our bidding... like we have with every development tool we've ever been handed (that we didn't toss aside).
If you're considering a RAG-powered brain for your organization, let's talk.
Jessie Grenfell
Jessie has spent 20+ years architecting and delivering software for organizations where complexity is the norm — financial services, insurance, nonprofits, and regulated industries where getting it wrong isn't an option. She specializes in the hard problems: unique operational workflows, cross-system integrations, and the kind of compliance requirements (HIPAA, CCPA, SOC 2) that most developers treat as someone else's job.
At Codality, she leads every principal engagement from discovery through delivery — because she's seen what happens when that thread gets cut.