Devlery - AI news for builders
Devlery blog
AI news for builders.
Copilot turns issue search into an agent work map
GitHub added semantic issue search and task-based auto model routing to Copilot, pushing coding agents from code generation toward workflow operations.
Docusign Agent Studio turns contracts into an execution layer
Docusign unveiled an Iris-powered AI assistant, agents, Agent Studio, and an MCP beta. The bigger shift is contracts moving from signed PDFs into enterprise workflow execution.
34% fewer revisits, the agent cost of clean code
A 660-run SonarSource study with Claude Code suggests clean code may not raise pass rates, but it can reduce tokens and file revisits.
1,000 Desktop Tasks Turn Computer-Use Agents Into Verifiable Systems
OpenComputer shifts computer-use agent evaluation from LLM judges to reproducible desktop tasks and app-state verifiers.
The SDK Generator Shut Down, and Claude Took the Connection Layer
Anthropic’s Stainless acquisition shows Claude’s moat expanding from model quality into SDKs, MCP servers, and reliable API connectivity.
Real-Time Context Engine Goes GA, Opening a New Front in Agent Data
Confluent Intelligence GA shows the AI agent race shifting from model scores toward real-time data context, MCP operations, and governance.
MCP Comes to the Phone, and Local Agents Get a New Runtime Boundary
Google AI Edge Gallery now combines Gemma 4 on-device agents with MCP, local notifications, and persistent sessions.
An 80-year conjecture broke, and OpenAI showed a research automation pipeline
OpenAI says a general-purpose reasoning model disproved Erdos unit distance conjecture. The bigger story is verifiable research automation.
The 24-hour agent inside Google Search and the new edge of the link economy
Google Search agents expand AI Mode from link retrieval into background monitoring, booking, commerce, and generated mini-apps.
AI-Q Skill and the Data Boundary for Research Agents
NVIDIA AI-Q agent skill lets Claude Code, Codex, and other harnesses delegate enterprise research to a local AI-Q server.
Gemini for Science Puts Research Agents on the Nature Test Bench
Google Gemini for Science bundles hypothesis, code, and literature agents, backed by two Nature papers that raise the bar for research-agent validation.
OpenAI Added SynthID, Setting a New Baseline for AI Image Trust
OpenAI is pairing C2PA, Google SynthID, and a public verifier, shifting AI image verification from detection models to provenance infrastructure.