Block's CTO argues that LLMs are a wasted resource when they sit idle overnight and on weekends. He envisions a future where AI agents work continuously, proactively building features, running multiple experiments in parallel, and anticipating the needs of the human team so that new options are ready for review in the morning.
Related Insights
Block's CTO quantifies the impact of their internal AI agent, Goose. AI-forward engineering teams save 8-10 hours weekly, a figure he considers the absolute baseline. He notes, "this is the worst it will ever be," suggesting exponential gains are coming.
The problem with AI agents isn't getting them to work; it's managing their success. Once deployed, they operate 24/7, generating a high volume of responses and meetings. Your biggest challenge will shift from outreach capacity to your human team's ability to keep up with the AI's constant activity and output.
The most significant productivity gains come from applying AI to every stage of development, including research, planning, product marketing, and status updates. Limiting AI to just code generation misses the larger opportunity to automate the entire engineering process.
High productivity isn't about using AI for everything. It's a disciplined workflow: breaking a task into sub-problems, using an LLM for high-leverage parts like scaffolding and tests, and reserving human focus for the core implementation. This avoids the sunk cost of forcing AI on unsuitable tasks.
OpenAI announced goals for an AI research intern by 2026 and a fully autonomous researcher by 2028. This isn't just a scientific pursuit; it's a core business strategy to exponentially accelerate AI discovery by automating innovation itself, which they plan to sell as a high-priced agent.
A key strategy for labs like Anthropic is automating AI research itself. By building models that can perform the tasks of AI researchers, they aim to create a feedback loop that dramatically accelerates the pace of innovation.
Contrary to the classic engineering rule to "never rewrite," Block's CTO believes AI will make this the new standard. He is pushing his teams to imagine a world where for every release, they delete the entire app (`rm -rf`) and rebuild it from scratch, with AI respecting all incremental improvements from the previous version.
The agent development process can be significantly sped up by running multiple tasks concurrently. While one agent is engineering a prompt, other processes can be simultaneously scraping websites for a RAG database and conducting deep research on separate platforms. This parallel workflow is key to building complex systems quickly.
The ideal AI-powered engineering workflow isn't just one tool, but a fluid cycle. It involves synchronous collaboration with an AI for planning and review, then handing off to an asynchronous agent for implementation and testing, before returning to synchronous mode for the next phase.
At Block, the most surprising impact of AI hasn't been on engineers, but on non-technical staff. Teams like enterprise risk management now use AI agents to build their own software tools, compressing weeks of work into hours and bypassing the need to wait for internal engineering teams.