What's Worth Knowing In AI Right Now? (with Henry Garner)

About this episode

The episode discusses the rapidly evolving landscape of AI in software development with insights from Henry Garner, CTO of JUXT.

AI is changing the way we all build software — that much seems clear. But the landscape is moving so fast that even the people paid to keep up are struggling. MCP or skills? Fine-tune or just prompt? LangChain or let a thousand agents loose? With almost 70 competing technologies and a shelf life of maybe six months on any advice, how do you figure out what's actually worth your time? Henry Garner is CTO of JUXT, a consultancy with about 150 senior engineers working at the coalface of AI-assisted development, including building AI platforms for tier-one banks. JUXT publishes a quarterly AI Radar — 68 technologies rated and reviewed — and Henry's been watching his own team go through the full adoption arc, from "spicy autocomplete" skepticism through to building Byzantine-fault-tolerant distributed systems over a weekend with Claude. Along the way we cover MCP vs skills, Conway's Law for LLMs, neurosymbolic AI and the unexpected return of Prolog, the "Ralph Wiggum loop" for getting agents to converge on correct implementations, and Allium — a new behavioral specification language Henry's co-authored that sits between human prose and TLA+, aiming to give LLMs just enough structure…

People in this episode

Host: Kris Jenkins

Guest: Henry Garner

Topics covered

• AI development
• software engineering
• technology landscape
• AI tools
• neurosymbolic AI
• behavioral specification

Keywords

• AI
• software development
• MCP
• LangChain
• neurosymbolic AI
• Prolog
• Allium
• AI Radar
• distributed systems
• Conway's Law

Mentioned in this episode

Organizations: JUXT

More episodes of Developer Voices

• Asciinema: Terminal Recording Done Right (with Marcin Kulik) · February 19, 2026 · 1h 27m
• Building the SpacetimeDB Database, Game-First (with Tyler Cloutier) · February 4, 2026 · 1h 41m
• Will Turso Be The Better SQLite? (with Glauber Costa) · December 11, 2025 · 1h 51m
• Can Google's ADK Replace LangChain and MCP? (with Christina Lin) · November 20, 2025 · 1h 5m
• Building Observable Systems with eBPF and Linux (with Mohammed Aboullaite) · October 31, 2025 · 1h 11m
• Solving Git's Pain Points with Jujutsu (with Martin von Zweigbergk) · October 9, 2025 · 1h 12m