|
By Ken Ahrens
We’ve been building an AI agent that can take a production bug, find the root cause in captured traffic, write a fix, and validate it before a human reviews it. We call it Agent Factory. Last week we ran it on ourselves, against a real bug in our own production service. The first thing we did was get the workflow wrong.
|
By Speedscale Team
This is Part 2 of the AI Software Factory series. In Part 1, we established that the Agile methodology is buckling under the weight of “elastic code.” When AI agents can generate functionality in seconds, two-week sprints and manual task management become organizational bottlenecks. We introduced the concept of the AI Software Factory: a shift from managing human tasks to managing business intent through a “Funnel of Increasing Trust.” But a factory requires infrastructure.
Sponsored Post
|
By Matthew LeRay
A customer pings support: "I tried to check out twice this morning and got a 500 each time, but it works fine for everyone else." The session ID is in the email. You have full request/response capture in your environment, you have Datadog Synthetics already running browser checks against the same flow, and you still spend the next two hours grepping logs because none of those tools let you say "show me just this user's requests, in order, and re-run them."
|
By Bailey Ahrens
Before I ever ran Claude in my terminal, I thought I already understood AI tools pretty well. Like most people, I had used ChatGPT, Google Gemini, and Perplexity for everyday tasks. Such as helping with schoolwork, organizing ideas, summarizing information, or getting through something faster when time was tight. They were useful, but they still felt separate from how real work happened.
Part of the motivation for this post is how cloud API economics are shifting: Anthropic is moving large enterprise customers toward per-token, usage-based billing (unbundled from flat seat fees), which makes “always call the API” a moving cost line for teams at scale. A hybrid or local layer is one way to keep spend bounded while you still use premium models where they matter.
|
By Josh Thornton
The terminal is a developer’s most trusted tool. It sees your source code, your secrets, the commands you run in production. When a terminal adds AI and cloud features, it’s worth asking what it’s doing on the network.
|
By Matthew LeRay
The alert fires at 2 AM. Your observability platform’s synthetic test just failed. Login is broken. So you open your laptop, pull up the dashboard, and stare at a single red dot: the browser test. You know the problem is somewhere in the stack, but not where. Is it the auth service? The token validator? The user profile API? The API gateway timing out? You’re now about to spend the next 45 minutes correlating traces, tailing logs, and manually hitting endpoints until you find it.
|
By Josh Thornton
The biggest risk to your product isn’t AI-generated code that doesn’t work. It’s generated code that seems fine. AI doesn’t optimize for correctness. It creates something passable. Something that passes the smell test. And when everybody in the industry is pushed to move faster and do more with less, you end up shipping software that looks correct. It passed your quick visual check. It passed all the tests. But no one ever fully understood it.
|
By Ken Ahrens
Every week there is another model drop, another agent framework, and another workflow tweak you are supposed to evaluate. Meanwhile, the largest companies, the ones operating at the highest scale and leaning hardest on AI, are also the ones making headlines for reliability strain: capacity limits, outages, and services that buckle under load.
|
By Alan Mon
Last week, a fleet of autonomous robotaxis in China suddenly stopped working—at scale. Over a hundred vehicles stalled across a city, stranding passengers in traffic and raising immediate concerns about safety, reliability, and trust in autonomous systems. This wasn’t just a bad day for self-driving cars. It was a distributed systems failure, one that happened in the physical world, not just in dashboards.
The "Free" AI Tool That Will Ruin Your Code#speedscale #aiagents #aicoding #devops #softwareengineer
|
By Speedscale
Relying on AI and interns to build custom traffic replay tools is a scalability nightmare that introduces security risks, brittle code, and massive maintenance costs...use Speedscale instead. Learn more: speedscale.com.
|
By Speedscale
Stop burning cloud credits blindly, here is how big tech actually scales AI with software factories. Learn more.
- May 2026 (13)
- April 2026 (27)
- March 2026 (20)
- February 2026 (20)
- January 2026 (30)
- December 2025 (16)
- November 2025 (12)
- October 2025 (14)
- September 2025 (16)
- August 2025 (14)
- July 2025 (8)
- June 2025 (1)
- May 2025 (4)
- April 2025 (16)
- March 2025 (10)
- February 2025 (1)
- January 2025 (7)
- December 2024 (13)
- November 2024 (9)
- October 2024 (24)
- September 2024 (13)
- August 2024 (10)
- July 2024 (4)
- June 2024 (4)
- May 2024 (2)
- April 2024 (5)
- March 2024 (4)
- February 2024 (3)
- January 2024 (1)
- December 2023 (3)
- November 2023 (3)
- October 2023 (4)
- September 2023 (2)
- August 2023 (13)
- July 2023 (2)
- June 2023 (4)
- May 2023 (2)
- April 2023 (2)
- March 2023 (7)
- February 2023 (6)
- January 2023 (4)
- December 2022 (3)
- November 2022 (4)
- October 2022 (2)
- September 2022 (3)
- August 2022 (5)
- July 2022 (5)
- June 2022 (2)
- May 2022 (4)
- April 2022 (4)
- March 2022 (4)
- February 2022 (14)
- January 2022 (6)
- December 2021 (3)
- November 2021 (4)
- October 2021 (5)
- September 2021 (5)
- August 2021 (6)
- July 2021 (5)
- June 2021 (6)
- May 2021 (6)
- April 2021 (2)
- March 2021 (5)
- February 2021 (2)
- January 2021 (2)
- November 2020 (1)
Continuous Resiliency from Speedscale gives you the power of a virtual SRE-bot working inside your automated software release pipeline. Forecast the real-world conditions of every build, and know you’ll hit your SLO’s before you go to production.
Feed Speedscale traffic (or let us listen) and we’ll turn it into traffic snapshots and corresponding mock containers. Insert your own service container in between for a robust sanity check every time you commit. Understand latency, throughput, headroom, and errors -- before you release! The best part? You didn’t have to write any scripts or talk to anyone!
Automated Traffic Replay for Every Stakeholder:
- DevOps / SRE Pros: Understand if your app will break or burn up your error budget before you release.
- Engineering Leads: Let Speedscale use traffic to autogenerate tests and mocks. Introduce Chaos testing and fuzzing.
- Application Executives: Understand regression/performance, increase uptime and velocity with automation.
Before you go to production, run the projection.