Please confirm you are human
This browser or connection looks automated. Press and continuously hold the control for 3 seconds to enable Google-hosted web results and, when separately allowed, AI-assisted answers.
A successful check enables 100 search requests. Interactive access does not authorize scraping, systematic collection, or reuse of search output.
News
How we rebuilt the Auggie CLI harness to make tasks 53% cheaper than Claude Code
1+ day, 14+ hour ago (754+ words) Earlier this year we rebuilt the Auggie CLI's harness from the ground up. On SWE-bench Pro, at the same pass rate, Auggie v2 completes a task for $1.27 where Claude Code spends $2.70. That is 53% cheaper. Even though v1 was already 27% less expensive than…...
How Supply Chain Attacks Reach Your Codebase
1+ day, 16+ hour ago (920+ words) A supply chain attack reaches code a team owns by traveling five trust links: the dependency resolver, the package registry, the build and CI system, the update mechanism, and the third-party vendor with standing access. Coding agents now resolve and…...
AI-Generated Code Security: Closing the Governance Gap
1+ day, 16+ hour ago (1089+ words) AI-generated code security accountability belongs to the organization producing the code because its development system controls the authorship record, review evidence, acceptance decision, and attestations that auditors can examine after an agent-authored change ships. Accountability for AI-generated code rests on…...
The software factory needs a faster review loop: further optimizing the path from PR to merge
2+ day, 14+ hour ago (618+ words) This is loop engineering: improving the complete system that turns generated code into a verified, understood, merge-ready change rather than optimizing any single tool in isolation. A conventional AI code review tool like CodeRabbit or Greptile analyzes a diff and…...
Using the Cosmos software factory to better understand our business
2+ day, 14+ hour ago (704+ words) 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 build in. A question I get often is: "Mayur, how healthy are our…...
AI Governance Tools for Agent-Written Code
5+ day, 8+ hour ago (901+ words) AI governance tools built on rule engines assume a human authored each change; agent-written code needs a platform layer that records authoring context plus session-level actions and approvals, because an artifact gate evaluates only what arrives at the boundary. Artifact…...
Secure SDLC When Agents Write the Code
6+ day, 39+ min ago (1032+ words) A secure SDLC supports agent-authored code when teams bind every change to a scoped workload identity and enforce controls server-side, because programmatic commits bypass client hooks and arrive faster than human review queues can absorb. Every phase gate in a…...
The AI Productivity Plateau
1+ week, 2+ day ago (244+ words) Report · The AI Productivity Plateau A benchmark of AI adoption, productivity, and measurement from 427 responses from senior engineering leaders. 91% of teams report higher productivity from AI, but only 12% are extremely confident in the metrics behind that claim — a 79-point gap between…...
SBOM for Agent-Driven Pipelines: Generation & Compliance
1+ week, 3+ day ago (581+ words) Generate a signed software bill of materials from lock files on every artifact-producing CI/CD build. That approach ties each SBOM to the software the pipeline actually assembled and catches dependency changes introduced by agents. The following table compares manual…...
Secrets Management for Agent-Driven Pipelines
1+ week, 3+ day ago (827+ words) For agent-driven CI/CD pipelines, OIDC-based workload identity should replace stored cloud credentials for cloud-access jobs that support federation. A secrets manager with automated rotation covers static credentials. Each job exchanges a signed OIDC JWT for a short-lived cloud token…...