proomt

Search

Search posts, papers, and topics

All posts

InfoQSarah Deitke24 min readtalkintermediate

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

Read on infoq.com

Summary

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.

  • Structured, lab‑style AI workshops (e.g., using Cursor, batching LLM calls) achieved 95 % positive feedback and helped reach near‑universal AI‑tool adoption among engineers.
  • Internal AI observability dashboards track daily active users, tool usage by team, language, IDE, token consumption, and cost, providing data for leadership and ROI arguments.
  • 15‑minute AI office‑hours and a dedicated Slack/meetup channel spread best‑practices beyond engineering to design, QA, and learning teams.
  • Close vendor relationships (e.g., Cursor beta features, security/legal vetting) accelerate access to new capabilities and inform internal eval practices.

Scaling AI safely in a large engineering org requires more than tooling—it needs cultural buy‑in, measurable usage data, and clear guardrails. Duolingo’s approach shows a repeatable template: educate first, instrument usage, then automate high‑confidence workflows like code review.

6/10
devopsllmobservabilityaieducationcode review

Related reading

  1. Presentation: Complexity and Creativity in Software Engineering

    Phillip Mortimer argues that AI‑generated code makes all software effectively "write‑only" due to volume, and proposes managing this by treating tests as the sole specification, automating code reviews with LLMs, and decoupling intent from implementation.

    InfoQinfoq.com28 mintalk

  3. We now auto-approve and merge 15% of PRs

    This article describes how a team implemented a bot to auto-approve and merge 15% of low-risk pull requests, aiming to reduce code review bottlenecks and improve development velocity. The system relies on custom deterministic linters, basic end-to-end tests, and a risk scoring mechanism to identify safe changes.

    Swizec Tellerswizec.com3 min

  4. How to Review AI-Generated Python Code Efficiently

    A practical five‑step workflow for reviewing AI‑generated Python code, covering intent clarification, automated quality checks (linters, type checkers, security scanners, tests), risk‑first manual reading, a checklist of common AI mistakes, and fix‑verify loops, plus a ready‑to‑use dev‑environment setup.

    Real Pythonrealpython.com26 min

  5. 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

  6. Presentation: Context Engineering at LinkedIn: How We Built an Organizational Context Layer for AI Agents with MCP

    LinkedIn built a “Contextual Agent Playbooks and Tools” layer that wraps internal services (code search, docs, feature flags, etc.) behind the open‑source Model Context Protocol (MCP). By feeding LLM‑powered coding agents the exact internal artifacts they need, the agents can diagnose incidents, generate PRs, and update incident tickets in minutes, delivering a reported 20 % productivity gain wit…

    InfoQinfoq.com28 mintalk