How to Achieve +250% Velocity with Generative AI

GENERATIVE AISOFTWARE DEVELOPMENTAI IN ENGINEERINGTECH LEADERSHIP

Elliot Beaty shares his playbook for 250% engineering velocity boost with AI. Real strategies, high-quality docs, agents fixing bugs, and future bottlenecks.

Hosted by:

Deejay

Featuring:

Eliott Beaty, Fruition

Episode Transcript

Deejay (00:15.31) Elliot, you've been posting on the CTO craft Slack, which we're both members of about your journey using Gen.ai in the development process. And you set some quite ambitious goals to maybe be doing very little development of code, like programmers tapping on keyboards by the end of ...

Episode Highlights

•Elliot's team aims to write almost no code by 2026 by pivoting fully to AI-driven development
•The team's development velocity has increased by roughly 250% since adopting AI tools last year
•An AI agent fixed a complex, two-day bug from a Jira ticket in just 30 minutes
•Increased development speed has created a new system bottleneck in QA, where tooling has not kept pace
•High-quality documentation has become a critical enabler for AI success by providing essential context to agents
•Current AI is described as monkey see, monkey do, excelling at imitating code but failing at novel architectural problems
•The senior engineer's role is shifting from writing code to ensuring quality and guiding AI agents
•The team will use dedicated AI Thursdays to encourage adoption and create space for learning new tools
•Elliot now considers AI tooling experience a mandatory skill for all new engineering hires
•The constant context switching required to manage AI agents has led to a noticeable increase in multitasking overload and mental fatigue.