# Agentic Software Engineering

How software is built with AI agents: new agents and tools, the models and methods behind them, evidence from practice, and what companies and governments learn from using them.

The publications:

- Agentic Software Engineering (Friday): AI writing code: the models, tools and research that make it better, and how companies and governments use it.

Subscribe: https://observatory.mgorsky.net/subscribe/ · RSS: https://observatory.mgorsky.net/feeds/se.xml · Page: https://observatory.mgorsky.net/agentic-software-engineering/

Video: [Agentic Software Engineering Daily, 14-Oct-26](https://youtube.com/shorts/cn8jsXZ6xkw)

## The latest: [Agentic Software Engineering, 9-Oct-26](https://observatory.mgorsky.net/archive/74/)

- **[Google rewrites giflib in Rust using Gemini and differential fuzz testing](https://www.infoq.cn/article/LVsjSV4pIlh3Liz0KZZE)**
  Google's security team used Gemini to translate giflib, an image library of about 3,000 lines of C, into an ABI-compatible Rust replacement that drops the process sandbox and keeps the same latency. The three-stage pipeline preserves exported symbols and struct definitions, while a differential fuzzer ran six days and 200 million iterations without finding functional drift. The Rust build was unaffected by CVE-2026-26740, a heap write flaw found upstream. InfoQ China reported this; it is not on Google's own channels.
  _Fact · InfoQ China · reported by InfoQ; not on Google's own channels · translated from Chinese_
- **[Claude Code Costs About $13 a Day per Developer](https://pub.towardsai.net/claude-code-costs-about-13-a-day-per-developer-and-agent-teams-use-roughly-7x-the-tokens-8fdea1ea40ad?source=rss----98111c9905da---4)**
  Anthropic's own documentation gives an average cost of about $13 per developer per day for Claude Code, according to Towards AI. The same documentation states that 90% of users stay under $30 a day. The article also reports that agent teams use roughly seven times the tokens. This is from Anthropic's own announcement.
  _Fact · Towards AI (Medium) · Anthropic's own announcement_
- **[Pi pod launches to run pi coding agents in self-hosted sandboxes](https://pipod.dev/)**
  Pi pod is a new open-source project that runs pi coding agent sessions in isolated sandboxes, called pods, on a server you operate, in composable environments. Its author, Evan, describes it as an effort to consolidate sandboxing, native clients, role-based access control session sharing and surface automation on top of pi. The self-hosted edition is available on GitHub, with a hosted service planned. It is not yet available.
  _Release · Hacker News · not yet available_
- **[Stack Overflow survey links AI coding to developer burnout](https://www.businessinsider.com/developers-are-burned-out-as-ai-coding-reshapes-work-survey-2026-10)**
  Stack Overflow's 2026 Developer Survey, released Tuesday, polled 30,903 developers across 169 countries. Nearly half report complacency, a third unhappiness, and just over 22% happiness. Burnout or tech fatigue is the top reason among the complacent, at 21%. Almost two-thirds use AI coding assistants or agents; 62% use general AI chat tools, and 31% of daily AI users spend four hours or more with them. It was announced, not measured.
  _Fact · Business Insider (AI) · announced, not measured_
- **[Cursor adds iOS remote control for local agents](https://cursor.com/changelog/remote-control-local-agents)**
  Cursor releases Remote Control, letting users view and message local agents running on their computer from the Cursor iOS app. The feature is on by default except for Enterprise organizations, where admins can enable it in Org settings under Security and identity. Agents continue running locally, so the computer must stay on and online; a "Keep this computer awake" setting is available.
  _Release · Cursor (Anysphere)_

## Every issue

- [Agentic Software Engineering, 9-Oct-26](https://observatory.mgorsky.net/archive/74/): Google rewrites giflib in Rust using Gemini and differential fuzz testing
- [Observatory: Agentic Software Engineering, 2 October 2026](https://observatory.mgorsky.net/archive/18/): OpenAI launches Ultrafast tier and GPT-6.1 Sol