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 to pin down what a system should do without falling into waterfall thinking.

If you're trying to make sense of the AI tooling landscape, or you've hit that wall where your agents keep drifting away from what you actually wanted, Henry's thesis — velocity through clarity of intent — might well help out yours.

--

Support Developer Voices on Patreon: https://patreon.com/DeveloperVoices
Support Developer Voices on YouTube: https://www.youtube.com/@DeveloperVoices/join

Juxt: https://www.juxt.pro/
Juxt AI Radar: https://www.juxt.pro/ai-radar/
Allium on GitHub: https://github.com/juxt/allium
Allium Documentation: https://juxt.github.io/allium/
Composition at a Distance (Henry's blog post): https://www.juxt.pro/blog/composition-at-a-distance/
A New Vocabulary for an Old Problem (Henry's blog post): https://www.juxt.pro/blog/new-vocabulary-for-an-old-problem/
Model Context Protocol (MCP): https://modelcontextprotocol.io/
LangChain: https://www.langchain.com/
LangGraph: https://www.langchain.com/langgraph
Gas Town (Steve Yegge): https://github.com/steveyegge/gastown
Kiro (spec-driven AI IDE): https://kiro.dev/
Phoenix (LLM observability): https://github.com/Arize-ai/phoenix
Temporal: https://temporal.io/
Taalas (LLM-on-a-chip): https://taalas.com/

Kris on Bluesky: https://bsky.app/profile/krisajenkins.bsky.social
Kris on Mastodon: http://mastodon.social/@krisajenkins
Kris on LinkedIn: https://www.linkedin.com/in/krisjenkins/

--

0:00 Intro
4:04 How Is AI Affecting Developer Jobs?
12:03 Vibe Coding vs Delegated Coding
21:02 Is MCP Dead?
31:05 Agent Orchestration: LangChain vs Gastown
41:01 What Is Neurosymbolic AI?
50:04 Is Fine-Tuning Still Worth It?
59:04 LLM Observability in Production
1:06:01 The Ralph Wiggum Loop
1:16:01 Introducing Allium
1:22:01 The Allium Workflow
1:30:01 Distilling Specs to Find Bugs
1:39:02 Outro

Developer Voices

A wide-ranging conversation between developer podcast host Chris Jenkins and Henry Garner (CTO at JUX) covering the current AI landscape for software engineers. Topics include the impact of AI coding tools on developer jobs, the MCP vs skills debate, when fine-tuning still makes sense vs using frontier models, neurosymbolic AI and the potential return of Prolog-style symbolic reasoning, multi-agent orchestration frameworks (LangGraph, Gastown), LLM observability tools like Phoenix and Temporal, and a behavioral specification language called Ali developed at JUX. The conversation emphasizes maintaining engineering judgment and design oversight while delegating implementation to AI agents.

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