Agentic Engineering

AI Engineering. Software engineering fundamentals. Using coding agents. Building AI apps.

[Agentic Engineering @AgenticEng]

What exactly is a
“neocloud” #ai #agenticengineering #neocloud #elonmusk #gpu

[ClaudeDevs @ClaudeDevs]

Claude writes about 90% of Claude Code's code.

From June to September, merged PRs more than doubled while the share reverted fell by more than 40%.

We wrote about how we changed code review to get there, and how to adopt it:

https://t.co/9sZe64g3mb

[Agentic Engineering @AgenticEng]

#Coding #agents are changing what’s worth building #ai #agenticengineering #software

[Agentic Engineering @AgenticEng]

1,400 PRs. 800,000 lines deleted. From one vague prompt. #ai #agenticengineering #openai #cleanup #software “Find DEAD code…”

[Peter Steinberger 🦞 @steipete]

OpenClaw deleted around 400k LOC of its own tests without much change in code coverage. Modern models just love writing tests for every tiny change, even if they aren't useful. This skill helped. https://t.co/a1jSBpfpns

[Tak 🦞 @cherry_mx_reds]

Anthropic is now recommending that companies REMOVE unnecessary subagents from their AI systems.

This is a pretty significant shift in agent architecture, with their team finding that a single agent equipped with skills can frequently outperform complex multi-agent systems, and one customer seeing roughly 2x faster execution.

The emerging rules of thumb:

→ Skills: Teach the agent HOW to do something, including procedures, expertise, and instructions.

→ Tools / MCP: Give the agent the ability to DO things through APIs, actions, and live data.

→ Subagents: Use for parallel work, isolated context, or tasks a single agent struggles with.

The interesting part is progressive disclosure. Instead of spawning specialized agents or stuffing everything into a giant prompt, one agent discovers and loads skills and tools as needed.

Their advice is to fold existing subagents into the main loop, turn their instructions into skills, expose their actions as tools, and run evals to see if performance holds up.

As models have gotten smarter, improving agent architecture is becoming less about what you can add and more about what you can delete.

https://t.co/DNq60Skkmc

[Agentic Engineering @AgenticEng]

If #AI does the junior work, who becomes senior engineer. #agenticengineering #software #education #computerscience

[Agentic Engineering @AgenticEng]

@trq212 Good luck Thariq!

[Agentic Engineering @AgenticEng]

Billions see a #chatbot. 20 million may be seeing something completely different. #ai #agenticengineering #chatgpt #claude @karpathy

[Agentic Engineering @AgenticEng]

https://t.co/uPR50kXoxl

[Agentic Engineering @AgenticEng]

Adding another #AI to watch your AI may not solve the problem #agenticengineering #adversarial #risk #software

[Agentic Engineering @AgenticEng]

@davidfowl Why now?

[Agentic Engineering @AgenticEng]

Highly recommend the podcast Scott and Mark Learn To https://t.co/AtXNnDB6Yh by @shanselman and @Markrussinovich

[Agentic Engineering @AgenticEng]

The #AI wrote the #code Then he found the bug. #agenticengineering #vibecoding #programming

[Agentic Engineering @AgenticEng]

An #AI #coding agent removed its own #safety monitor #agenticengineering #openai

[Agentic Engineering @AgenticEng]

#AI just found a #bug hiding under 70% of the web #agenticengineering #php #securitybreach

[OpenAI @OpenAI]

OpenAI models helped researchers—operating as part of our Patch the Planet initiative—discover critical security flaws in PHP, an open-source programming language used to run an estimated 70% of websites.

Over the past two months, we led a coalition of maintainers, researchers, and security providers to prepare fixes and protections ahead of disclosure. This duration was necessary because the fix was quite intricate and required a major change to the PHP engine. Every site using PHP can now safely upgrade their version to stay secure, in addition to applying mitigations from various security vendors.

Due to the severity of these flaws and PHP’s widespread use, we consider this bug to be one of the most impactful vulnerabilities in recent memory. It also marks a new phase, where AI can find security bugs with internet-scale impact.

This is an example of the Defender’s Window in action: to our knowledge, frontier AI was able to find this vulnerability ahead of attackers, giving defenders time to prepare.
https://t.co/TW3jrSbB3f

[Agentic Engineering @AgenticEng]

@just_be_dev @dillon_mulroy https://t.co/h8Av9H95mk

[Agentic Engineering @AgenticEng]

What if #software engineers stop writing and reviewing #code #ai #agenticengineering #llm

[Agentic Engineering @AgenticEng]

@dhh https://t.co/h8Av9H95mk

[Agentic Engineering @AgenticEng]

What if #software engineers stop writing and reviewing #code #ai #agenticengineering #llm

[Agentic Engineering @AgenticEng]

@GergelyOrosz @Pragmatic_Eng https://t.co/h8Av9H9DbS

[Agentic Engineering @AgenticEng]

What if #software engineers stop writing and reviewing #code #ai #agenticengineering #llm

[Agentic Engineering @AgenticEng]

@bcherny https://t.co/h8Av9H9DbS

[Agentic Engineering @AgenticEng]

What if #software engineers stop writing and reviewing #code #ai #agenticengineering #llm