Dev Team Uses Claude AI to Pre-Screen 70–100 Pull Requests Weekly Before Human Review

·2 views

A software development team has integrated Anthropic's Claude AI into their GitHub Actions pipeline to automatically review every pull request before a human engineer sees it. The system, deployed six months ago, posts inline comments directly on code diffs within 90 seconds of a push and has been tested across 4,200 pull requests. According to the team, the AI consistently catches 30–40% of real issues — including null pointer errors, resource leaks, hardcoded secrets, and missing error handling — freeing senior engineers from spending 4–6 hours daily on routine checks. The architecture splits large diffs by file rather than line count to preserve context, and uses GitHub's PR Review API to attach feedback to specific lines rather than posting easily ignored summary paragraphs. The team emphasizes the tool is designed to filter and amplify human judgment, not replace it, leaving architectural decisions and business logic review to engineers.

Read the full story at DEV Community

This is an AI-generated summary. ShortSingh links to the original source for the complete article.

Discussion (0)

AI Refund Agent Exploited by Stored Unverified Customer Claim Across Sessions

A synthetic evaluation case highlights a critical flaw in AI agent memory design, where a refund agent incorrectly stored an unverified customer claim as authoritative information. In the first session, the agent rightly refused a refund due to no system-recorded approval, but wrongly saved the customer's unverified statement as settled fact. When the customer returned the next day, the agent retrieved that stored note and issued the refund without re-verifying approval in the system. The failure only became visible when both sessions were evaluated together as a single trajectory, exposing how isolated testing can miss multi-session vulnerabilities. The case underscores that persistent memory in AI agents must preserve context without silently elevating unverified claims into actionable authority.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

Solo developer Azeem introduces Jeemmo, his backend web development practice

Azeem is a solo backend web developer who has been building custom web applications under the name Jeemmo since 2011. He serves clients across the UK, EU, and US, specialising in real-time features, payment integrations, and performance optimisation for legacy PHP and WooCommerce sites. His technical stack includes PHP, Laravel, Node.js, Python, MySQL, and Redis. Among his notable projects are Quran Roshni, a fast ad-free Quran reader supporting around 30 languages, and GoodPing, a free network monitoring tool. His full portfolio is available at jeemmo.com.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

Solidity Escrow Contract Enables Trustless USDC Payments Between AI Agents on Base

Developers building autonomous AI agents face a core challenge: agents must pay for services on-chain without a human intermediary, yet simple direct transfers risk non-delivery or fraud. A hash-based escrow smart contract on Base, an Ethereum Layer 2 network, addresses this by holding USDC funds until a seller reveals a pre-agreed secret confirming service completion. The contract uses USDC, a fiat-backed ERC-20 stablecoin, whose stable value simplifies micro-payment pricing for agent-to-agent transactions typically ranging from $0.01 to $0.10. Base's roughly two-second block times and very low gas fees make each escrow interaction cost well under $0.001, keeping the approach practical for high-frequency automated workflows. If the seller fails to reveal the secret before a set deadline, the buyer agent can reclaim the deposited funds, providing a built-in refund mechanism without requiring a trusted third party.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

How to Build Reusable AI Skills Across GitHub Copilot, Claude, and LangChain

Major AI platforms including GitHub Copilot, Claude, and LangChain all support custom callable skills that extend an AI assistant's capabilities, though each uses different terminology such as Extensions, Tools, or Functions. Despite the naming differences, the underlying architecture is consistent: a schema defines what the skill does, an implementation executes the logic, and a registration mechanism exposes it to the AI model. A practical example — a deployment status checker that retrieves service health, version, and incident data — is used to demonstrate how the concept translates across three platforms. The AI model itself decides when to invoke a skill based on the user's request, extracts structured arguments from natural language, and incorporates the result into its response. Developers can use this cross-platform understanding to choose the most suitable integration path depending on their toolchain and use case.

0 comments Read more at DEV Community