The third golden age of software engineering – thanks to AI, with Grady Booch

Gergely Orosz interviews Grady Booch about software engineering as systems trade-offs and AI coding agents as another rise in abstraction. Booch welcomes disposable personal software and agent-assisted learning, while arguing that durable systems still require fundamentals, architecture, and judgment across technical, economic, human, safety, and ethical forces ([00:01:59]-[00:04:57], [00:53:50]-[00:56:46]).

Key Points Covered

• Software engineering balances systems forces: Booch defines the work as finding reasonably optimal rather than perfect solutions across technical, economic, human, ethical, and other constraints; code is only one mechanism ([00:01:59]-[00:04:57]).
• Abstraction rises recur: He traces shifts from algorithms and data to objects, libraries, services, and platforms, with each layer enabling larger systems while making some prior skills less central ([00:32:38]-[00:38:41], [00:46:46]-[00:48:44]).
• Agents continue rather than begin the third age: In Booch's framing, AI assistance accelerates use of an already large ecosystem of packages and system components that emerged around the millennium ([00:46:46]-[00:48:44]).
• Disposable and durable software need different rigor: He celebrates single-user, throwaway automation, but conditions reduced concern about internals on the software not needing to endure ([00:53:50]-[00:56:46]).
• Agents reproduce recurring patterns well: Booch says familiar web and CRUD structures fit agent training better than the full breadth of computing; the episode offers examples rather than comparative evaluation ([01:00:35]-[01:02:45]).
• Guided generation can accelerate learning: He uses Cursor to create a minimal D3 example, studies it, and iterates, while stressing that the domain contains many precedents and that his own foundations help him judge the result ([00:57:49]-[00:58:38], [01:03:41]-[01:05:33]).
• Developers should move toward systems-level skills: Booch expects automation in delivery pipelines and simple apps, but sees continuing demand for people who manage complexity, architecture, scale, and human-technical interactions ([01:06:26]-[01:09:05]).
• Multi-agent coordination has precedents: He recommends studying Society of Mind, blackboards, global workspaces, and subsumption architectures rather than assuming agent orchestration is wholly new; these are directions, not evaluated implementations in the interview ([01:09:05]-[01:13:10]).

Full video: https://www.youtube.com/watch?v=OfMAtaocvJw(opens in a new tab)