Why backlog zero is now achievable and what that means for engineering culture
The speaker argues that AI tools like Claude have made it possible to achieve "backlog zero" by dramatically reducing development time. Tasks that previously required months of planning and team coordination can now be completed in a single coding session.
Summary
The speaker presents the concept of "backlog zero" as now being achievable for development teams, fundamentally changing how engineering work gets done. They illustrate this transformation through a personal example of re-implementing a Go microservice in Ruby using Claude AI, which was completed in a single session rather than requiring the traditional multi-month process of roadmap planning, team advocacy, and coordination that would have been necessary before November (presumably referring to when advanced AI coding tools became available). The speaker emphasizes that this technological shift has created unprecedented creative freedom for developers, where the primary constraint is no longer implementation time but rather imagination and ideation. They highlight the ability to generate multiple implementation approaches quickly and compare different styles or have them reviewed to determine optimal solutions. This represents a fundamental shift in engineering culture where long-standing technical debt and desired architecture changes can be addressed immediately rather than being perpetually deferred due to resource constraints.
Key Insights
- The speaker claims that backlog zero is now a realistic goal for development teams due to AI capabilities
- The speaker describes re-implementing a Go microservice in Ruby in a single Claude session, contrasting this with the months-long advocacy and planning process required before November
- The speaker argues that AI tools can generate multiple implementation approaches that can be compared and reviewed to find the best solution
- The speaker states that imagination has replaced time as the primary blocker for completing development tasks
- The speaker suggests that tasks which previously took months to complete can now be knocked out quickly with AI assistance
Topics
Transcript
[0:00] Backlog zero is a realistic thing for teams to be able to go after. All the things that you wish you would ever wanted to do, it's now just achievable. They course you got to balance it with all of the extra stuff that you can just deliver at the same time, but it's so sweet to be able to think that hey, we actually have a path to getting rid of all of our backlogs. And all of the architecture changes or whatever. Recently I was taking a go microservice and re-implementing it in Ruby. It was a single cloud code session. Before November, this was something that I would have had to advocate for on a road…
Full transcript available for MurmurCast members
Sign Up to AccessMore from How I AI
Muse dodged every trap in this billing ticket
A billing ticket resolution task was used to benchmark agentic AI performance, and Muse excelled by successfully navigating multiple challenges including account linking errors, duplicate refund issues, and prompt injection attempts. The agent demonstrated superior performance by investigating thoroughly, fixing the account link, issuing the correct refund, updating the plan, and marking the ticket as resolved.
Meta's Muse is the best AI agent I've tested
The speaker provides their initial impressions of Meta's Muse AI agent, declaring it the best agentic AI they've tested. Muse excelled across four different knowledge work tasks including billing management, customer responses, inbox triage, and research, outperforming alternatives.
Meta's Muse: best AI agent, worst designer
The speaker tests Meta's AI model on video editing and finds it excels at technical tasks like cutting and timing but significantly underperforms on creative work like design and overlays. They conclude that while the model is strong for coding and agent tasks, it falls short compared to Claude Opus 3.5 for creative applications.
No two Muse agents are the same
The speaker discusses how Muse agent setups are highly personalized and variable, emphasizing the importance of understanding underlying system architecture rather than obsessing over individual details. They describe adopting a more flexible, liberating approach to design that accepts good outputs without requiring perfectionism.
Is Meta’s Muse Wonder model any good?
Clare Vo reviews Meta's Muse Wonder AI model and finds it excels at agentic work and coding tasks but significantly underperforms on creative design work compared to competitors like Claude Opus 3.5. The model shows promise as a personal AI agent with strong domain expertise and memory capabilities, but lacks the design sensibility needed for front-end development.