Augment Code
25 stories
Augment CodeToolsAugment Code's next chapter We've got big news. Cosmos, Auggie CLI, the Code Context Engine, and related technology are joining Harness .
Augment Code
Augment CodeToolsBeyond AI Coding Agents: How We Built Augment's Software Factory TL;DR: We built a software factory to automate mechanical work across the SDLC. Over eight months, size-adjusted output per developer grew 4.5× while merge times and revert rates fell.
Augment CodeToolsWe think the FDE should be part of the product, so we built one in Most agent platforms provide building blocks and leave the customer or a Forward Deployed Engineer to assemble them.
Augment CodeToolsHow a two-person engineering team handled 6× more product feedback and kept shipping TL;DR As our two-engineer Cosmos Advisor team shipped more automations to more customers, weekly product feedback grew rapidly - reaching 30+ feedback-threads per week.
Augment CodeToolsHow we rebuilt the Auggie CLI harness to make tasks 53% cheaper than Claude Code Every token you spend should buy as much finished work as possible is one of the core principles behind Cosmos and the Auggie CLI.
Augment CodeToolsThe software factory needs a faster review loop: further optimizing the path from PR to merge TL;DR In an AI-native engineering organization, generating code is no longer the slowest part of shipping software.
Augment CodeToolsUsing the Cosmos software factory to better understand our business I lead the Solutions Architecture team at Augment Code. My team supports large engineering organizations evaluating Cosmos, our agentic orchestration platform, as the software factory their teams…
Augment CodeToolsThe best value for every token: GPT-5.6 Sol is now our default in Cosmos In April, Matt wrote that the era of single-model engineering is over . Three models cleared the bar at the time, and he predicted there would be more by the end of the year - both better and…
Augment CodeToolsWhat is loop engineering, and how are leading software engineering teams using it? “Loop engineering” is the practice of designing agentic loops: systems that take work from a trigger through execution and verification to a finished outcome, with agents doing the middle and humans…
Augment CodeToolsThe bottleneck moved to verification. So we automated that too. Internally, a significant amount of engineering time is consumed by manually verifying that the code an agent writes works E2E in dev. We sought to change that.
Augment CodeToolsAn AI analyst that reads Linear, Slack, and GitHub and answers team queries off our dbt models At Augment Code , like at many other companies, the human data team was the bridge to the data. Every question came through us.
Augment CodeToolsAccelerating large engineering projects with Cosmos TL;DR. Agents can now write code, review PRs, and investigate incidents. The next bottleneck is the large project itself: the design, decomposition, and coordination work that happens around the PRs.
Augment Code
Augment CodeToolsAgents can now run the full SDLC in Cosmos. What do engineers do? Last month I opened a roughly 1,000-line PR. The colleague I asked to review it looked at it and said, “Okay, give me 45 minutes.
Augment CodeToolsHello, Cosmos: the platform for AI-native engineering teams Modern engineering teams want agents working everywhere across the software development lifecycle, not just in their IDEs.
Augment CodeToolsScaling incident management for an AI-native organization using Cosmos As coding and code review become increasingly automated in AI-native organizations, one of the next major bottlenecks is incident management.
Augment CodeToolsOpus 4.7 for 33% less: How Auggie beats Claude Code on cost and quality TL;DR: We benchmarked Auggie vs Claude Code on Opus 4.7. Auggie takes a modest lead in quality (67.4% vs 66.3% pass rate) while costing ~33% less, thanks to sharper retrieval that results in token…
Augment CodeToolsExcited, anxious, invigorated: what 219 engineering leaders told us about going AI-native TL;DR We surveyed 219 engineering leaders. 48% of their code is now AI-generated. 55% are worried about losing shared understanding of their own codebase.
Augment CodeToolsHow Cosmos accelerated our AI-native transformation by removing the code review bottleneck TL;DR. When agents write 100% of your code, the bottleneck moves to review: at one point we had 1,400 open PRs and a 20-hour median time-to-first-comment.
Augment CodeToolsWe don't need more agents. We need a better system. So we built one. Today we're putting Augment Cosmos into public preview. Cosmos is the operating system for agentic software development: agents that run anywhere (your env, our cloud) and work across your SDLC…
Augment Code
Augment CodeToolsIntroducing Augment Prism: model routing to reduce cost and maintain quality TL;DR: Prism is a new option in the Augment model picker that routes each user turn to whichever underlying model best fits the work.
Augment CodeToolsKarpathy skills on OpenClaw: agents don't write better code. But they do it more efficiently. We added Karpathy-inspired coding rules to root AGENTS.md and ran three coding agents through 40 OpenClaw PRs.
Augment CodeToolsAI transformation is a systems problem: a conversation with Justin Reock, DX Every engineering leader I talk to is trying to transform. They want their teams to be AI-native. They're rolling out tools, tracking adoption, watching dashboards.
Augment CodeToolsA good AGENTS.md is a model upgrade. A bad one is worse than no docs at all. We pulled dozens of AGENTS.md files from across our monorepo and measured their effect on code generation.
Augment CodeToolsThe era of single-model engineering is over Thirteen months ago, I wrote a post arguing that model pickers were a design failure : the tool should pick the model. Developers should focus on shipping.
Nothing matches this filter yet.