Loading…
Topic
Software Engineering
3 posts about Software Engineering. Every summary links to the original.
- 3 posts
- 3 companies
The Good Stuff
Paid picks we use ourselves. Links carry a referral code — a subscription through one earns us a commission at no extra cost to you.
Newest first
Posts
Dispatches from O'Reilly: Inside a software factory
A software engineer with over seven years of experience built a software factory called Squid to ship projects with minimal human intervention, but the first version was overbuilt and abandoned. The article formalizes the software factory as eight stages across three buckets: what to build, actual building and checking, and self-improving, with a shared context layer feeding data into the front of the pipeline. The human is most needed in brainstorming and planning, where taste and high-leverage decisions live, while agents handle grunt work and execution. The author recommends using the strongest model for planning and cheaper models for execution, and warns that a weak plan causes more retries and higher costs. The article advises starting with the smallest loop that automates one annoying part of your job, and buying off-the-shelf solutions when engineers you don’t supervise run agents.
Scaling AI Agents: What We Learned From 9 Real-World Cases
A new report from JetBrains examines nine real-world cases of scaling AI agents in software development, revealing that adoption rates alone do not guarantee improved team performance. One organization reached 95% AI adoption without seeing a change in developer velocity, while another tripled pull request throughput and reduced its defect backlog by 54%. The report finds that effective scaling requires making development environments agent-ready, establishing shared standards, and investing in team learning. Fin, for example, created a dedicated team to manage agent infrastructure and invested in linting and standardization to handle increased output. The key lesson is that organizations must change the systems and practices around agents, not simply deploy more of them.
Using AI to Build AI: How Agentforce Engineers Scale Automation Without Sacrificing Reliability
The Agentforce team at Salesforce faced the challenge of using AI to help build and maintain the Atlas Reasoning Engine without compromising reliability. The central risk was that AI could diagnose problems, modify the engine, test fixes, and review its own work while being confidently wrong. To address this, the team built an integrated engineering knowledge base using semantic retrieval to connect fragmented knowledge across incidents, fixes, and discussions. They implemented layered AI evaluation with an agent-as-a-judge model and human oversight, using different models to review work from different perspectives to avoid self-preference bias. As a result, typical bug-resolution time dropped from two to four weeks to one or two days, and system availability reached 100% in weekly reports during the observed period.
Related topics
All topics →Weekly digest
The best engineering reads, once a week.