Crypto news

18.06.2026
10:34

Block automates 15% of its code using the AI agent Builderbot

Investments_AI

Blockchain company Block, led by Jack Dorsey, has taken a decisive step toward automating development by implementing the AI tool Builderbot. The system already generates about 15% of the company's entire software code, and this is just the beginning.

Builderbot is an orchestrator of AI agents integrated directly into Slack. A developer simply tags the bot in a chat and describes the task. In response, the system independently finds errors, suggests fixes, or creates new features. The key difference from standard assistants is access to Block's entire codebase. This means an engineer from the Cash App team can make changes to Square services they haven't worked with before. The bot automatically pulls tasks from Jira, creates branches in the repository, writes code, and submits a Pull Request.

The scale is impressive: Builderbot performs over 200,000 operations per day and closes about 1,500 merge requests weekly. As Block's head of AI capabilities Brad Axen noted: "What used to take months now takes days. The bot handles the routine and environment setup, allowing engineers to focus on solving complex problems."

It is important to emphasize that the tool works exclusively with source code and system configurations. It has no access to customer data or payment information. From a technical standpoint, Builderbot is built on goose, an open-source framework contributed by the Agentic AI Foundation. Additionally, Block collaborated with Anthropic to create the Model Context Protocol (MCP).

Expert assessment: Block demonstrates how AI can transform not only user-facing services but also internal engineering processes. Given that the company already generates 15% of its code through AI, this is not just an experiment but a strategic shift. If the trend toward "native" AI processes is confirmed, we will see a radical acceleration of development in the crypto and fintech sectors. However, the key question is how this will affect employment for junior developers and code quality in the long term.