proomt

Search

Search posts, papers, and topics

All posts

Moove-itFernanda Mezquita2 min readintermediate

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

Read on qubika.com

Summary

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…

  • A centrally managed AI‑assistant that encodes company standards can turn a productivity tool into a consistency‑enforcing infrastructure.
  • Ownership by the delivery teams (instead of a separate innovation group) drives adoption and continuous improvement.
  • Even without hard metrics, the reported benefits are faster routine work, more uniform code quality, and easier reviews across pods.
  • Extending the shared setup beyond code (to monitoring, design, business logic) is presented as the next phase.

Embedding AI into the engineering workflow as a shared, versioned product aligns the model’s output with internal standards, reducing friction in code review and lowering the chance of regressions—key for scaling fast‑moving fintech products.

5/10
devopsllmarchitecturesoftware engineering

Related reading

  1. Towards Self-Driving Codebases

    The post argues that AI agents could eventually handle low‑level engineering tasks—bug fixing, debugging, UI consistency, growth experiments—if the dev toolchain is made “agent‑legible”. It outlines missing primitives (global memory, code‑base rot prevention, better dev environments) and proposes a bootstrapping process to measure and improve a repo’s “agent readiness”. The piece is largely specu…

    Hacker News front pagedetail.dev9 minHN12099

  2. 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

  5. How to upskill enterprise AI builders by using daily micro habits

    Google Cloud Consulting proposes a four‑pillar micro‑learning framework for enterprise AI upskilling: 5‑minute browser‑based exercises, pre‑configured sandboxes, daily streaks, and delivering runnable code each session. A pilot (Advent of Agents) showed >150k participants, 859k code runs, and a 31% daily return rate, suggesting short, frictionless tasks improve engagement versus traditional bootc…

    Google Cloud Bloggoogle.com3 min

  6. Presentation: Teaching Engineers, Trusting AI: How Education Enabled Autonomous Code Review

    Duolingo’s DevEx AI team built a program of AI‑literacy workshops, observability dashboards, office‑hours, and vendor partnerships to get engineers comfortable with LLM‑based tools. With that foundation they launched a PR‑risk‑assessment bot that auto‑approves low‑risk pull requests, cutting review bottlenecks while keeping defect rates flat.

    InfoQinfoq.com24 mintalk