Early Adoption of Agentic Coding Tools by GitHub Projects
A new study analyzes over 25,000 agentic pull requests across thousands of GitHub repositories to understand how AI agents collaborate with humans.
- Analyzed 25,264 agentic pull requests across 2,361 popular GitHub repositories.
- Identifies specific patterns in how humans and AI agents collaborate on software tasks.
- Shifts focus from individual code generation to project-level productivity metrics.
- Provides empirical data on the actual adoption rates of agentic coding tools.
A recent research paper investigates the growing integration of agentic coding tools within the GitHub ecosystem. By analyzing 25,264 agentic pull requests from 2,361 popular repositories, the study provides a data-driven look at how autonomous AI agents are contributing to real-world software development.
The research moves beyond simple code generation to examine project-level productivity and the specific patterns of human-agent collaboration. This provides critical insights into how developers manage and review contributions made by autonomous agents rather than just human contributors.
This study marks a shift from evaluating individual AI code snippets to understanding the systemic impact of agentic workflows on the software development lifecycle.
Understanding how to effectively review and manage agent-generated pull requests.
Assessing the real-world productivity gains and integration risks of agentic workflows.
Provides empirical evidence of how the software engineering landscape is evolving.
- Agentic
- Refers to AI systems capable of autonomous reasoning and taking actions to achieve a goal, rather than just responding to prompts.
- Pull Request (PR)
- A method of submitting contributions to a software project, allowing for review and discussion before code is merged.
ProgrammingType-safe LLM outputs with Zod: stop guessing what the model returns.
![[AINews] not much happened today](https://images.weserv.nl/?url=substackcdn.com%2Fimage%2Ffetch%2F%24s_%21uoZg%21%2Cf_auto%2Cq_auto%3Agood%2Cfl_progressive%3Asteep%2Fhttps%253A%252F%252Fpbs.substack.com%252Fmedia%252FHNOP2m2bAAAC2k7.jpg&w=520&fit=cover&q=70&output=webp&dpr=2&we=1&il=1)
Programming[AINews] not much happened today
ProgrammingA Receipt Is Not Proof Forever. It Is a Promise to Reopen the Claim.
ProgrammingBuilding a Document-RAG Agent on GCP's Agent Development Kit (ADK)
ProgrammingThe (no longer) missing multi-agent pattern: triggering dynamic workflows from an agent
How Klarna’s AI Agent Strategy Backfired But Became A Useful Lesson - Forbes
Klarna's AI agent strategy backfired but provided valuable insights for the company.
Singapore enterprise AI startup Whale raises $40m more in Series C - DealStreetAsia
Singapore-based enterprise AI startup Whale has successfully raised $40 million in a Series C funding round.
30% of Cathie Wood's Portfolio Is Invested in These 5 Artificial Intelligence (AI) Stocks - The Motley Fool
Cathie Wood has invested 30% of her portfolio in five artificial intelligence stocks. The stocks are part of her Ark Investment Management fund.
Airbus picks Iliad's Scaleway for AI, defence work in sovereignty push - Reuters
Airbus has chosen Iliad's cloud provider Scaleway to deliver AI infrastructure for its defence initiatives, supporting a European sovereignty agenda.
Copyright Clash Twists as Midjourney Challenges Film Studios Over Internal AI Exploitation - Telugu Times
Image generation service Midjourney is reportedly suing major film studios, alleging they used its AI to train their own models without proper licensing. This legal action adds a new dimension to ongoing copyright disputes surrounding AI training data.
BusinessApplied Computing wants to give oil and gas operators an AI model for the entire plant
Applied Computing has raised $20M to develop an AI model for oil and gas operators. The model aims to cover entire plant operations.