LangChain raised its deepagents-cli coding agent's score on Terminal Bench 2.0 from 52.8% to 66.5%, reaching the top 5 on the leaderboard, by rebuilding only the harness and leaving the underlying mod…
A developer's analysis of coding agent architecture shows that swapping only the harness around a fixed model — keeping weights, tasks and context window constant — raised SWE-bench Verified bug-fixin…
Students at Coimbatore Institute of Technology completed the second session of a hands-on cloud-native systems and applied AI workshop led by Santhosh NC, a lead infrastructure consultant at Thoughtwo…
Cassie Shum, speaking at QCon, presented lessons learned from building production-ready agentic AI systems on knowledge graphs, drawing on her work at RelationalAI and more than 20 years as an enginee…
Thoughtworks' Birgitta Böckeler argues that AI's surge in code production—Meta reported a 106% increase in significant lines of code per human-landed diff in a year, and DX data shows median pull requ…
Spec-driven development spans three distinct levels, from spec-first to spec-as-source, according to Birgitta Böckeler of Thoughtworks, writing on martinfowler.com. The AI Unified Process, a methodolo…
InfoQ has opened enrollment for its InfoQ Certified AI-Assisted Engineering Program, a five-week online certification for senior engineers and architects who run coding agents on production code, with…
An exploratory evaluation by Thoughtworks technologist Birgitta Böckeler found no clear quality difference between AI coding agents using test-driven development (TDD) inside the agent loop versus not…
Spec driven development, a workflow that makes the specification the source of truth for AI coding agents, is gaining traction but risks becoming waterfall with a chatbot, according to a developer's a…
Anthropic, METR, DORA, and Thoughtworks data indicate that software implementation is becoming cheaper while specification, verification, and ownership remain costly, according to a response to Senko …
Thoughtworks' internal IT organization has developed Structured Prompt-Driven Development (SPDD), a method that treats prompts as first-class delivery artifacts to make LLM-assisted code changes gover…
Thoughtworks' podcast episode on the future of software engineering highlighted open problems in agentic engineering, and a developer responded by detailing how their IRC-A architecture addresses thes…
A Thoughtworks technologist built a 150,000-line application entirely with AI agents (Claude Code and Cursor) and then ran an experiment showing that refactoring a 17,155-line Rust data-access file re…
Birgitta Boeckeler, a Distinguished Engineer at Thoughtworks focused on AI-assisted software delivery, discusses harness engineering for AI agents on the SE Radio podcast. She explains that harnesses …
CEOs must prioritize AI governance over speed to win the corporate AI race, according to Teneo and Thoughtworks leaders. A Teneo survey found 53% of investors expect AI ROI within six months, but only…
Registration has opened for QCon AI New York 2026, a production-AI conference for senior engineers, taking place December 15-16 at The Westin Jersey City Newport. The program, chaired by Eder Ignatowi…
Ben O'Mahony, Principal AI Engineer at Thoughtworks, presented a talk on using OpenTelemetry data from developer interactions with an AI-powered Language Server Protocol to train smaller, faster model…
A developer explores using LLM-as-a-Judge to evaluate AI-generated code, shifting from deterministic pass/fail tests to probabilistic scoring. The approach involves a golden dataset of curated test ca…
Honeycomb completed a multi-month migration of its Kafka infrastructure from self-hosted Confluent Platform and ZooKeeper on AWS EC2 to open-source Apache Kafka 4.1.1 running in KRaft mode on AWS EKS.…
A developer created an AI-assisted Architecture Decision Record (ADR) template that uses large language models to generate documentation in 3-5 minutes instead of 30-40. The template covers ADR struct…