InfoQ Homepage AI Assisted Coding Content on InfoQ
-
Airbnb Implements Context-Aware Identity Model to Support Privacy-First Social Features
Airbnb has redesigned its identity system to support privacy-first social features in Experiences. The platform introduces context-specific profiles that separate global user identity from externally visible profiles, preventing cross-context linkage. The migration leveraged automated auditing, manual validation, and AI-assisted refactoring to enforce correct identity usage across services.
-
New DORA Report Claims Strong Engineering Foundations Drive AI Return on Investment
Google Cloud's DORA team released a report detailing a framework for assessing the ROI of AI in software development. It emphasizes that successful AI implementation depends on organizational systems rather than just tools. The report introduces a J-Curve model for value realization. It also discusses the importance of workforce retention and process redesign for achieving long-term gains.
-
OpenAI Introduces Websocket-Based Execution Mode to Reduce Latency in Agentic Workflows
OpenAI introduces a WebSocket-based execution mode for its Responses API to improve agentic workflow performance in coding agents and real-time AI systems. The update reduces latency by up to 40 percent by replacing HTTP request-response cycles with persistent connections, improving streaming, tool execution, and multi-step orchestration in production-scale AI systems.
-
Inside Claude Code Auto Mode: Anthropic’s Autonomous Coding System with Human Approval Gates
Anthropic has introduced auto mode in Claude Code, enabling multi-step software development workflows with reduced manual intervention. The feature combines automated execution with layered safety mechanisms, including input filtering, action evaluation, and two-stage classification, while maintaining human approval checkpoints for sensitive operations.
-
GitLab Adds Flat-Rate Code Reviews, Free-Tier AI Access, and Spending Caps
Open-core DevOps vendor GitLab has shipped versions 18.10 and 18.11 of its DevSecOps platform, with changes that give agentic AI to users on the free tier, that cut the per-review cost of automated code analysis, and give administrators hard limits on how much teams can spend on AI credits each month.
-
Cloudflare Introduces Project Think: a Durable Runtime for AI Agents
Cloudflare's Project Think introduces a new framework for AI agents, shifting from stateless orchestration to a durable actor-based infrastructure. It features a kernel-like runtime enabling agents to manage memory and run code securely. Innovations include Fibers for checkpointing progress and a Session API for relational conversations, enhancing agent efficiency and resilience.
-
Meta Reports 4x Higher Bug Detection with Just-in-Time Testing
Meta introduces Just-in-Time (JiT) testing, a dynamic approach that generates tests during code review instead of relying on static test suites. The system improves bug detection by ~4x in AI-assisted development using LLMs, mutation testing, and intent-aware workflows like Dodgy Diff. It reflects a shift toward change-aware, AI-driven software testing in agentic development environments.
-
Zendesk Says AI Makes Code Abundant, Shifting the Bottleneck to “Absorption Capacity”
Zendesk argues that GenAI shifts the bottleneck in software delivery from writing code to “absorption capacity”, which is the organisation’s ability to define problems clearly, integrate changes into the wider system, and turn implementation into reliable value. As code becomes abundant, architectural coherence, review capacity, and delivery flow become the main constraints.
-
GitHub Copilot CLI Reaches General Availability
GitHub has launched Copilot CLI into general availability, bringing generative AI directly to the terminal. Integrated with the GitHub CLI, it offers natural language command suggestions and code explanations. Recent updates introduce "agentic" workflows with Autopilot mode and GPT-5.4 support, alongside new enterprise telemetry for tracking usage across development teams.
-
Agentic AI Patterns Reinforce Engineering Discipline
Paul Duvall recently discussed his library of engineering patterns for AI assisted development and practices that ground high quality delivery. Related discussions from Paul Stack and Gergely Orosz highlight a shift toward remixing and specification driven development.
-
Uber Automates Design Documentation with Agentic Systems
Uber’s uSpec uses AI agents and the Figma Console MCP to automate design specs, cutting documentation time from weeks to minutes. Integrated with the Michelangelo platform, it uses a GenAI Gateway for PII redaction, ensuring data stays local. This reflects a 2026 industry shift between Uber’s "Visual-First" Figma workflow and a "Guide-First" approach favored by developers using agentic IDEs.
-
AI Coding Assistants Haven’t Sped up Delivery Because Coding Was Never the Bottleneck
Agoda recently published an observation arguing that while AI coding tools have measurably raised individual developer output, the resulting velocity gains at the project level have been surprisingly modest, because coding was never the real bottleneck. The post claims that the bottleneck has shifted upstream to specification and verification because these areas require human judgment.
-
Sonatype Launches Guide to Enhance Safety in AI-Assisted Code Generation
Sonatype Guide is a real-time guardrail system that sits between AI coding tools and the open-source ecosystem, ensuring AI-generated code uses safe, valid, and maintainable dependencies.
-
QCon London 2026: Refreshing Stale Code Intelligence
At QCon London 2026, Jeff Smith discussed the growing mismatch between AI coding models and real-world software development. While AI tools are enabling developers to generate code faster than ever, Smith argued that the models themselves are increasingly “stale” because they lack the repository-specific knowledge required to produce production-ready contributions.
-
Where Do Humans Fit in AI-Assisted Software Development?
An article on Martin Fowler’s blog by Kief Morris examines the role of humans in AI-assisted software engineering, arguing developers are unlikely to move fully “out of the loop.” Instead, teams may work “on the loop,” designing tests, specifications, and feedback mechanisms to guide AI agents, as industry discussions focus on how such systems should be verified and governed.