{"date":"2026-07-14","title":"What happened in AI — Jul 14, 2026","generated_at":"2026-07-14T21:30:00Z","intro":["Two new open standards moved to formalize agent interoperability: Google's Agentic Resource Discovery spec for finding and verifying AI tools and agents, and a proposed cross-model operating contract for coding-agent tool calls. Google also shipped a Genkit Agents API with human-in-the-loop support, and one team ran an 80M-token single agent session with no compaction and no accuracy loss.","Agent trust tooling advanced too: LangSmith now traces coding agents end to end, a new monitor catches agents exfiltrating SSH keys, and AWS extended agentic QA into CI pipelines. Codex usage also passed 7M users as Anthropic published large-codebase and AI-native-org guidance."],"highlights":["Google and partners published an open Agentic Resource Discovery spec for finding and verifying AI tools and agents.","An agent ran all 89 Terminal-Bench 2.0 tasks in one 80M-token session with no compaction and no accuracy loss versus fresh sessions.","LangSmith now traces coding agents across Claude Code, Codex, Cursor, and Copilot — tool calls, costs, and retries in one view.","New open-source monitor \"Agentmetry\" catches coding agents reading ~/.ssh and phoning home.","Codex usage grew more than 10x in six months to 7M users, adding 1M in a single day.","Nvidia argues performance-per-watt, not chip count, now caps how much an AI factory can produce."],"article_count":15,"categories":[{"name":"Agent Orchestration & Standards","slug":"agent-orchestration-standards","summary":"Two open specs pushed toward standardized agent interoperability — a discovery protocol for tools and agents, and a proposed cross-model contract for coding-agent tool calls — while separate work tested how far a single agent context can stretch.","articles":[{"title":"Show HN: Running over 80M tokens in one agent session with no compaction","summary":"A single agent session ran all 89 sequential Terminal-Bench 2.0 tasks — over 80M tokens — with no compaction and no measurable accuracy loss versus a fresh session per task.","source":"hackernews_ai","url":"https://github.com/Kiz8-Team/pi-cwl","published":"Tue, 14 Jul 2026 16:26:42 +0000"},{"title":"Google's Genkit Ships Agents API with Detached Turns and Human-in-the-Loop for TypeScript and Go","summary":"Genkit's new Agents API packages message history, tool loops, streaming, and state persistence behind one chat() call, with detached turns for mid-flow human approval.","source":"infoq_ai_ml","url":"https://www.infoq.com/news/2026/07/genkit-agents-api-preview/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=AI%2C+ML+%26+Data+Engineering","published":"Tue, 14 Jul 2026 10:17:00 GMT"},{"title":"Google and Industry Partners Announce Agentic Resource Discovery Specification for AI Agents","summary":"Google and partners published Agentic Resource Discovery (ARD), an open standard for publishing, discovering, and verifying AI tools, APIs, and agents.","source":"infoq_ai_ml","url":"https://www.infoq.com/news/2026/07/agentic-resource-discovery-spec/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=AI%2C+ML+%26+Data+Engineering","published":"Tue, 14 Jul 2026 13:40:00 GMT"},{"title":"One Contract, Every Model: An Operating Standard for AI Coding Agents","summary":"A proposed operating-standard harness aims to give every model the same contract for coding-agent tool calls, cutting per-model glue code.","source":"hackernews_ai","url":"https://manazir.dev/blog/operating-standard-harness","published":"Tue, 14 Jul 2026 03:47:50 +0000"}]},{"name":"Evals, Observability & Agent Security","slug":"evals-observability-agent-security","summary":"New tooling targets agent trust: LangSmith traces multi-framework coding agents end to end, a monitor watches for credential exfiltration, and AWS pushed agentic QA further into CI pipelines, alongside a new team-level agent-maturity benchmark.","articles":[{"title":"How to Debug Coding Agents with LangSmith Traces","summary":"LangSmith now traces coding agents across Claude Code, Codex, Cursor, and Copilot, exposing tool calls, subagents, errors, costs, and retries in one view.","source":"langchain_blog","url":"https://www.langchain.com/blog/your-coding-agents-are-a-black-box-heres-how-to-crack-them-open","published":"Tue, 14 Jul 2026 16:05:06 GMT"},{"title":"Agentmetry, catch your AI coding agent reading ~/.ssh and phoning home","summary":"Agentmetry is a new open-source monitor built to catch coding agents reading SSH keys or exfiltrating data over the network.","source":"hackernews_ai","url":"https://github.com/blitzcrieg1/agentmetry","published":"Tue, 14 Jul 2026 16:41:48 +0000"},{"title":"Accelerating software delivery with agentic QA automation using Amazon Nova Act – Part 2","summary":"AWS extended its Nova Act QA Studio with batch regression test suites and pipeline integration for parallelized, agent-run test execution.","source":"aws_ml_blog","url":"https://aws.amazon.com/blogs/machine-learning/accelerating-software-delivery-with-agentic-qa-automation-using-amazon-nova-act-part-2/","published":"Tue, 14 Jul 2026 16:47:32 +0000"},{"title":"Show HN: Benchmark your eng team's AI agent maturity in 5 minutes","summary":"A free 5-minute benchmark grades an engineering team's AI-agent maturity, built from data collected across hundreds of conversations with engineering leaders.","source":"hackernews_ai","url":"https://agent-benchmarks.com/software-factory/","published":"Tue, 14 Jul 2026 06:48:47 +0000"}]},{"name":"AI Infrastructure & Efficiency","slug":"ai-infrastructure-efficiency","summary":"Infrastructure coverage turned to constraints: Google Cloud detailed serving Claude at production scale across regions, while Nvidia argued power budget, not chip count, now caps AI factory output.","articles":[{"title":"Claude at scale on Google Cloud: Frontier AI, built for enterprise production","summary":"Google Cloud detailed running Claude in production at scale — managing accelerators, holding latency steady across regions, and keeping regulated data in-region for long-context requests.","source":"google_cloud_blog","url":"https://cloud.google.com/blog/products/ai-machine-learning/claude-at-scale-on-google-cloud-frontier-ai-built-for-enterprise-production/","published":"Tue, 14 Jul 2026 16:00:00 +0000"},{"title":"Why Performance per Watt Is the Ultimate Metric for AI Infrastructure Efficiency","summary":"Nvidia argues performance-per-watt, not raw throughput, is the metric that determines how many tokens a power-constrained AI factory can generate — and its revenue ceiling.","source":"nvidia_blog","url":"https://blogs.nvidia.com/blog/performance-per-watt-ai-infrastructure-efficiency/","published":"Tue, 14 Jul 2026 15:00:20 +0000"}]},{"name":"Coding Agents, Platforms & Adoption","slug":"coding-agents-platforms-adoption","summary":"Coding-agent competition sharpened as Codex usage passed 7M users while Anthropic published large-codebase and AI-native-org practices, and Oracle and OpenAI both pushed enterprise guidance for adopting agentic tooling.","articles":[{"title":"How Claude Code Works in Large Codebases: Best Practices and Where to Start","summary":"Anthropic published best practices for running Claude Code effectively in large, unfamiliar codebases.","source":"claude_blog","url":"https://claude.com/blog/how-claude-code-works-in-large-codebases-best-practices-and-where-to-start","published":"2026-07-14T01:02:52.517426+00:00"},{"title":"Running an AI-Native Engineering Org","summary":"Anthropic outlined how an AI-native engineering org restructures workflows and roles around coding agents rather than bolting agents onto existing process.","source":"claude_blog","url":"https://claude.com/blog/running-an-ai-native-engineering-org","published":"2026-07-14T01:02:52.517426+00:00"},{"title":"[AINews] Codex usage up >10x in 6 months to 7M users, +1M in the past ~day; did Codex overtake Claude Code??","summary":"OpenAI's Codex usage grew more than 10x in six months to 7M users, adding 1M in a single day — a scale signal in the coding-agent race with Claude Code.","source":"latent_space","url":"https://www.latent.space/p/ainews-codex-usage-up-10x-in-6-months","published":"Tue, 14 Jul 2026 01:22:27 GMT"},{"title":"Oracle opens Fusion Agentic Applications to pro-code developers and coding agents","summary":"Oracle opened its Fusion Agentic Applications to pro-code developers and coding agents, extending its no-code agent builder toward a programmable API surface.","source":"search_agent_engineering_news","url":"https://news.google.com/rss/articles/CBMisAFBVV95cUxPejd6SzBOMEtLQ0RINEpDZGRqS1U5VGRtUlZCenZYSmJZcUZhVWYta212YTNDWGtJNmdxVnF1NDl3N3JhMks2N1QwV3JDSFdIZlYyQWV5TlQxS3Foa25vWk1OeFVRZHdVdkVZOWJDMlZ2N1R0YzdVbnItU1lmNERuWVhjcklVV0d6WTVWX3N1RTNWWUJjTnhBejBOQXdFdXVBX29HNE4zZHRIa05nRE03Nw?oc=5","published":"Tue, 14 Jul 2026 12:00:20 GMT"},{"title":"How to manage AI investments in the agentic era","summary":"OpenAI's framework for managing AI investment centers on measuring useful work per dollar rather than raw usage, then scaling only the workflows that clear that bar.","source":"openai_blog","url":"https://openai.com/index/managing-ai-investments-in-agentic-era","published":"Tue, 14 Jul 2026 10:00:00 GMT"}]}]}