proomt

Search

Search posts, papers, and topics

All posts

Moove-itCarolina Esses2 min readintermediate

Case Study: How We Doubled Delivery Velocity with Anthropic Claude

Read on qubika.com

Summary

Qubika integrated Anthropic Claude (Chat, Code) and its Agentic Framework into Throne’s engineering workflow for bug fixes and feature work. Over the measured period they cut estimated effort by 52% and delivered code 2.1× faster while optimizing model selection for cost and latency.

  • Claude Chat, Claude Code, and QAF were embedded in daily engineering tasks for bug fixing and feature development.
  • Estimated engineering effort dropped from 1,376 h to 657 h, a 52% reduction, yielding a 2.1× delivery acceleration.
  • Workloads were matched to Claude model variants (Opus, Sonnet, Haiku) to balance reasoning quality, latency, and cost.
  • Continuous governance monitors performance and cost, guiding consolidation of workloads onto Claude where beneficial.

Engineering teams evaluating LLM‑assisted development can see concrete ROI numbers and governance practices for sustainable adoption.

5/10
devopsllmperformanceml infraanthropicclaude

Related reading

  1. From Individual Experiments to a Shared AI Practice: How Avant Scaled AI-Assisted Engineering

    Avant replaced many personal AI‑assistant setups with a single, organization‑wide Claude Code configuration that embeds the company’s coding standards, project‑tracking links, and documentation. Treated as an internal product, the setup is versioned, owned by delivery engineers, and iteratively improved. The shared tool speeds routine tasks (scaffolding, tests, migrations, docs) and enforces cons…

    Moove-itqubika.com2 min

  2. Claude Cowork and chat are now one Claude

    Claude merges its Cowork and chat interfaces into a single assistant and adds beta Docs, Slides, and Design capabilities, rolling out first to Pro and Max plans. The unified UI lets users ask Claude to generate reports, presentations, and other artifacts within the same conversation, with optional auto‑action settings. No new technical details or implementation specifics are provided.

    Hacker News front pageclaude.com3 minreleaseHN232226

  3. Article: Your Next DSL Author Is a Language Model

    Typed Domain Grounding (TDG) embeds a DSL inside a mainstream language the LLM already knows (e.g., Kotlin) and uses the host compiler as an oracle. The author describes five building blocks—embedding, choosing a host language with high training‑data frequency, compiler‑driven type safety, a generate‑compile‑repair loop, and an on‑demand teaching tool—and shows measured results from kUML, a Kotli…

    InfoQinfoq.com18 min

  4. Article: Architecting Secure and Scalable Facial Verification Systems

    A real‑world post‑mortem of a high‑volume face verification service that moved from a naïve synchronous API to an async, layered pipeline (edge validation, preprocessing, decoupled detection/verification, decision engine) to achieve 8.5k rpm, p99 < 1.8 s, 30 % cost savings, and strict privacy controls.

    InfoQinfoq.com15 min

  5. Changing the game: How Google uses agentic AI to secure hundreds of millions of lines of code

    Google’s AI & Infrastructure team built an agentic pipeline (Mantis) that runs pre‑submit AI‑driven scans on every code check‑in, validates findings with a fast triage agent (AST + call‑graph analysis) achieving >92% precision in <1 min, then auto‑generates fixes via a bug‑fix agent. Localized threat models and a two‑step scan cut false‑positives to ~3% and prevent hundreds of vulnerabilities eac…

    Google Cloud Bloggoogle.com4 min

  6. One style guide for everything Claude Code writes

    A detailed walkthrough of forking the nbj‑write‑clearly Claude Code skill to enforce the Google Developer Documentation style guide across all developer‑facing prose (docs, comments, commit messages, review feedback). The fork expands the trigger set, vendors the 70‑page guide offline via a Bun sync script, and adds a layered approach (global CLAUDE.md rules, on‑demand skill, per‑agent preloaded…

    Bjørn Johansenbjornjohansen.com5 min