https://newruntime.com/ 2026-07-22T00:00:00.000Z https://newruntime.com/posts/ 2026-07-22T00:00:00.000Z https://newruntime.com/posts/page/2/ 2026-07-22T00:00:00.000Z https://newruntime.com/posts/page/3/ 2026-07-22T00:00:00.000Z https://newruntime.com/posts/page/4/ 2026-07-22T00:00:00.000Z https://newruntime.com/signals/ 2026-07-16T00:00:00.000Z https://newruntime.com/signals/page/2/ 2026-07-16T00:00:00.000Z https://newruntime.com/signals/page/3/ 2026-07-16T00:00:00.000Z https://newruntime.com/signals/page/4/ 2026-07-16T00:00:00.000Z https://newruntime.com/signals/page/5/ 2026-07-16T00:00:00.000Z https://newruntime.com/signals/page/6/ 2026-07-16T00:00:00.000Z https://newruntime.com/signals/page/7/ 2026-07-16T00:00:00.000Z https://newruntime.com/signals/page/8/ 2026-07-16T00:00:00.000Z https://newruntime.com/signals/page/9/ 2026-07-16T00:00:00.000Z https://newruntime.com/patterns/ 2026-07-16T00:00:00.000Z https://newruntime.com/agents/ 2026-07-22T00:00:00.000Z https://newruntime.com/sources/ 2026-07-22T00:00:00.000Z https://newruntime.com/shifts/ 2026-07-22T00:00:00.000Z https://newruntime.com/deltas/ 2026-07-22T00:00:00.000Z https://newruntime.com/graveyard/ 2026-07-22T00:00:00.000Z https://newruntime.com/projects/ 2026-07-22T00:00:00.000Z https://newruntime.com/systems/ 2026-07-22T00:00:00.000Z https://newruntime.com/posts/cursor-agent-swarms-sqlite/ 2026-07-22T00:00:00.000Z https://newruntime.com/posts/fable-jacobi-counterexample-eval/ 2026-07-22T00:00:00.000Z https://newruntime.com/posts/gumclaw-company-operating-system/ 2026-07-22T00:00:00.000Z https://newruntime.com/posts/hilos-development-control-plane/ 2026-07-22T00:00:00.000Z https://newruntime.com/posts/ridge-ai-spend-process-cost/ 2026-07-22T00:00:00.000Z https://newruntime.com/posts/shared-document-human-agent/ 2026-07-22T00:00:00.000Z https://newruntime.com/posts/sierra-horizon-long-running-agent/ 2026-07-22T00:00:00.000Z https://newruntime.com/posts/ai-production-reserve-digest/ 2026-07-22T00:00:00.000Z https://newruntime.com/posts/working-backwards-before-coding/ 2026-07-22T00:00:00.000Z https://newruntime.com/posts/agent-api-design/ 2026-07-21T00:00:00.000Z https://newruntime.com/posts/agent-steps-as-graph/ 2026-07-21T00:00:00.000Z https://newruntime.com/posts/agentic-self-improvement-survey/ 2026-07-21T00:00:00.000Z https://newruntime.com/posts/ai-coding-workflow-verifiable-work/ 2026-07-21T00:00:00.000Z https://newruntime.com/posts/ai-native-engineering-team/ 2026-07-21T00:00:00.000Z https://newruntime.com/posts/anthropic-compute-meta/ 2026-07-21T00:00:00.000Z https://newruntime.com/posts/capital-one-vulnhunter-attacker-first-security-agent/ 2026-07-21T00:00:00.000Z https://newruntime.com/posts/claude-code-subagents-memory/ 2026-07-21T00:00:00.000Z https://newruntime.com/posts/claude-hud-agent-observability/ 2026-07-21T00:00:00.000Z https://newruntime.com/posts/coding-agent-cost-environment-config/ 2026-07-21T00:00:00.000Z https://newruntime.com/posts/pillar-sandbox-escapes/ 2026-07-21T00:00:00.000Z https://newruntime.com/posts/cognee-agent-memory-platform/ 2026-07-21T00:00:00.000Z https://newruntime.com/posts/coinbase-ai-era-interviews/ 2026-07-21T00:00:00.000Z https://newruntime.com/posts/genception-video-generator-vision-backbone/ 2026-07-21T00:00:00.000Z https://newruntime.com/posts/ghostwriter-agent-memory-poisoning/ 2026-07-21T00:00:00.000Z https://newruntime.com/posts/gemini-enterprise-agent-platform-demos/ 2026-07-21T00:00:00.000Z https://newruntime.com/posts/kimi-k3-frontend-model-race/ 2026-07-21T00:00:00.000Z https://newruntime.com/posts/langchain-agentic-operating-model/ 2026-07-21T00:00:00.000Z https://newruntime.com/posts/linear-loops-duplicate-signal/ 2026-07-21T00:00:00.000Z https://newruntime.com/posts/linear-loops-agent-workflows/ 2026-07-21T00:00:00.000Z https://newruntime.com/posts/claude-code-long-running-loops/ 2026-07-21T00:00:00.000Z https://newruntime.com/posts/model-match-effort-selection/ 2026-07-21T00:00:00.000Z https://newruntime.com/posts/open-weight-cyber-gap/ 2026-07-21T00:00:00.000Z https://newruntime.com/posts/senior-engineers-read-large-codebases/ 2026-07-21T00:00:00.000Z https://newruntime.com/posts/ai-native-development-stages/ 2026-07-21T00:00:00.000Z https://newruntime.com/posts/unabyss-shared-context-layer/ 2026-07-21T00:00:00.000Z https://newruntime.com/posts/ai-engineering-under-the-hood/ 2026-07-21T00:00:00.000Z https://newruntime.com/posts/language-models-need-sleep/ 2026-07-16T00:00:00.000Z https://newruntime.com/signals/agent-readable-rest-can-beat-a-human-focused-sdk/ 2026-07-16T00:00:00.000Z https://newruntime.com/signals/verification-capacity-coding-agent-bottleneck/ 2026-07-16T00:00:00.000Z https://newruntime.com/signals/opencode-model-swappable-agent-harness/ 2026-07-16T00:00:00.000Z https://newruntime.com/signals/agent-skills-need-behavioral-evals/ 2026-07-16T00:00:00.000Z https://newruntime.com/signals/monogram-answer-becomes-interface/ 2026-07-16T00:00:00.000Z https://newruntime.com/signals/company-memory-updates-at-correction-time/ 2026-07-16T00:00:00.000Z https://newruntime.com/signals/cowork-usage-operations-and-artifacts/ 2026-07-16T00:00:00.000Z https://newruntime.com/signals/model-behavior-varies-by-language-and-context/ 2026-07-15T00:00:00.000Z https://newruntime.com/signals/colibri-runs-a-744b-model-in-25-gb-of-memory/ 2026-07-15T00:00:00.000Z https://newruntime.com/signals/atomic-task-graphs-outperform-react-loops/ 2026-07-15T00:00:00.000Z https://newruntime.com/signals/fable-cost-per-completed-task/ 2026-07-15T00:00:00.000Z https://newruntime.com/signals/retrieval-does-not-create-company-memory/ 2026-07-15T00:00:00.000Z https://newruntime.com/signals/netflix-generates-the-whole-page/ 2026-07-15T00:00:00.000Z https://newruntime.com/signals/local-agent-is-a-runtime-not-one-model/ 2026-07-15T00:00:00.000Z https://newruntime.com/signals/ai-feedback-needs-behavioral-traces/ 2026-07-14T00:00:00.000Z https://newruntime.com/signals/the-reverse-information-paradox-makes-companies-pay-for-ai-twice/ 2026-07-14T00:00:00.000Z https://newruntime.com/signals/cubesandbox-microvm-execution-layer/ 2026-07-14T00:00:00.000Z https://newruntime.com/signals/a-product-scan-shows-ai-moving-into-work-surfaces/ 2026-07-14T00:00:00.000Z https://newruntime.com/signals/tcs-is-building-a-large-forward-deployed-ai-engineering-unit/ 2026-07-14T00:00:00.000Z https://newruntime.com/signals/gpt-5-6-behaves-like-a-family-of-configured-systems/ 2026-07-14T00:00:00.000Z https://newruntime.com/signals/airbnb-agentic-coding-loop/ 2026-07-14T00:00:00.000Z https://newruntime.com/signals/uber-platform-for-thousands-of-agents/ 2026-07-13T00:00:00.000Z https://newruntime.com/signals/openai-moves-deeper-into-applied-ai-consulting/ 2026-07-13T00:00:00.000Z https://newruntime.com/signals/claude-code-model-and-effort-are-separate-controls/ 2026-07-13T00:00:00.000Z https://newruntime.com/signals/chatgpt-separates-chat-from-work/ 2026-07-13T00:00:00.000Z https://newruntime.com/signals/large-task-planning-becomes-ticket-graph/ 2026-07-12T00:00:00.000Z https://newruntime.com/signals/cheap-code-moves-bottleneck-to-review/ 2026-07-12T00:00:00.000Z https://newruntime.com/signals/databricks-benchmarks-real-coding-agent-economics/ 2026-07-12T00:00:00.000Z https://newruntime.com/signals/the-future-engineer-is-defined-by-judgment-not-typing-speed/ 2026-07-12T00:00:00.000Z https://newruntime.com/signals/improve-routes-architect-and-executor-models/ 2026-07-12T00:00:00.000Z https://newruntime.com/signals/render-packages-deployment-primitives-for-agent-workloads/ 2026-07-11T00:00:00.000Z https://newruntime.com/signals/an-ai-coding-workflow-starts-with-data-and-interfaces/ 2026-07-11T00:00:00.000Z https://newruntime.com/signals/trycase-disposable-linux-agent-verification/ 2026-07-10T00:00:00.000Z https://newruntime.com/signals/codex-can-be-embedded-in-shell-pipelines/ 2026-07-10T00:00:00.000Z https://newruntime.com/signals/deep-agents-package-long-running-harness/ 2026-07-10T00:00:00.000Z https://newruntime.com/signals/gpt-5-6-shorter-prompts/ 2026-07-10T00:00:00.000Z https://newruntime.com/signals/advisor-model-guides-cheaper-executor/ 2026-07-09T00:00:00.000Z https://newruntime.com/signals/claude-code-startup-context-can-be-reduced-to-13k-tokens/ 2026-07-09T00:00:00.000Z https://newruntime.com/signals/parallel-agents-make-large-migrations-tractable/ 2026-07-08T00:00:00.000Z https://newruntime.com/signals/pxpipe-trades-text-tokens-for-rendered-visual-context/ 2026-07-08T00:00:00.000Z https://newruntime.com/signals/codex-can-operate-as-a-product-management-workbench/ 2026-07-08T00:00:00.000Z https://newruntime.com/signals/loop-engineering-treats-the-agent-as-a-process-not-a-prompt/ 2026-07-08T00:00:00.000Z https://newruntime.com/signals/openwiki-codebase-docs-as-agent-memory/ 2026-07-07T00:00:00.000Z https://newruntime.com/signals/continuous-evals-for-multi-agent-systems/ 2026-07-07T00:00:00.000Z https://newruntime.com/signals/claude-code-recovers-after-failed-command/ 2026-07-07T00:00:00.000Z https://newruntime.com/signals/agent-memory-evaluated-as-system-behavior/ 2026-07-06T00:00:00.000Z https://newruntime.com/signals/loop-engineering-expands-beyond-coding/ 2026-07-05T00:00:00.000Z https://newruntime.com/signals/gemini-live-and-deep-agents-form-a-low-latency-voice-workflow/ 2026-07-05T00:00:00.000Z https://newruntime.com/signals/ai-product-okrs-measure-result-adoption/ 2026-07-05T00:00:00.000Z https://newruntime.com/signals/twenty-four-gigabytes-of-vram-becomes-a-practical-local-coding-tier/ 2026-07-04T00:00:00.000Z https://newruntime.com/signals/animation-vocabulary-turns-motion-references-into-an-agent-skill/ 2026-07-04T00:00:00.000Z https://newruntime.com/signals/frontier-labs-need-portfolio-discipline-for-compute-experiments/ 2026-07-04T00:00:00.000Z https://newruntime.com/signals/herdr-adds-agent-awareness-to-terminal-multiplexing/ 2026-07-04T00:00:00.000Z https://newruntime.com/signals/harvey-trains-legal-agent-with-applied-compute/ 2026-07-03T00:00:00.000Z https://newruntime.com/signals/codebase-memory-combines-search-with-a-repository-map/ 2026-07-03T00:00:00.000Z https://newruntime.com/signals/a-github-skill-can-resolve-review-comments-as-a-batch/ 2026-07-03T00:00:00.000Z https://newruntime.com/signals/the-future-interface-is-an-agent-manager-not-twenty-terminals/ 2026-07-03T00:00:00.000Z https://newruntime.com/signals/ai-reorganizes-marketing-around-search-and-orchestration/ 2026-07-02T00:00:00.000Z https://newruntime.com/signals/inference-gateway-makes-model-switching-operational/ 2026-07-02T00:00:00.000Z https://newruntime.com/signals/agent-memory-needs-its-own-review-loop/ 2026-07-02T00:00:00.000Z https://newruntime.com/signals/ai-moves-from-a-separate-app-into-the-work-environment/ 2026-07-02T00:00:00.000Z https://newruntime.com/signals/loop-engineering-applies-to-product-management-too/ 2026-07-02T00:00:00.000Z https://newruntime.com/signals/notion-html-blocks-turn-documents-into-interactive-outputs/ 2026-07-02T00:00:00.000Z https://newruntime.com/signals/ai-moves-the-bottleneck-across-the-whole-product-system/ 2026-07-02T00:00:00.000Z https://newruntime.com/signals/verifiability-is-an-ai-product-feature/ 2026-07-02T00:00:00.000Z https://newruntime.com/signals/linkedin-builds-semantic-search-for-a-hiring-agent-at-scale/ 2026-07-01T00:00:00.000Z https://newruntime.com/signals/reasoning-can-unlock-parametric-memory/ 2026-07-01T00:00:00.000Z https://newruntime.com/signals/google-agents-cli-connects-prompt-evals-and-deployment/ 2026-07-01T00:00:00.000Z https://newruntime.com/signals/deep-agents-plan-files-memory-subagents/ 2026-07-01T00:00:00.000Z https://newruntime.com/signals/agent-ready-saas-exposes-primitives/ 2026-07-01T00:00:00.000Z https://newruntime.com/signals/codex-can-import-an-existing-claude-code-setup/ 2026-07-01T00:00:00.000Z https://newruntime.com/signals/sonnet-moves-agent-capability-downmarket/ 2026-07-01T00:00:00.000Z https://newruntime.com/signals/warp-reframes-product-engineers-as-factory-engineers/ 2026-06-30T00:00:00.000Z https://newruntime.com/signals/firecrawl-indexes-arxiv-and-github-for-research-agents/ 2026-06-30T00:00:00.000Z https://newruntime.com/signals/an-ai-native-company-is-not-a-company-with-chatgpt/ 2026-06-30T00:00:00.000Z https://newruntime.com/signals/claude-tag-introduces-a-separate-agent-identity-model/ 2026-06-29T00:00:00.000Z https://newruntime.com/signals/prompt-debt-becomes-legacy-code/ 2026-06-29T00:00:00.000Z https://newruntime.com/signals/agentos-lightweight-runtime-for-coding-agents/ 2026-06-29T00:00:00.000Z https://newruntime.com/signals/openai-frames-codex-as-a-work-layer-not-a-chat-feature/ 2026-06-29T00:00:00.000Z https://newruntime.com/signals/economic-index-measures-agentic-work-cadence/ 2026-06-29T00:00:00.000Z https://newruntime.com/signals/deerflow-2-0-packages-an-open-runtime-for-autonomous-agents/ 2026-06-28T00:00:00.000Z https://newruntime.com/signals/role-confusion-explains-prompt-injection/ 2026-06-28T00:00:00.000Z https://newruntime.com/signals/pydantic-ai-capabilities-progressive-disclosure/ 2026-06-28T00:00:00.000Z https://newruntime.com/signals/loop-library-packages-fifteen-repeatable-coding-agent-cycles/ 2026-06-28T00:00:00.000Z https://newruntime.com/signals/agents-md-can-become-an-instruction-injection-surface/ 2026-06-28T00:00:00.000Z https://newruntime.com/signals/coinbase-reports-lower-ai-spend-as-token-use-rises/ 2026-06-28T00:00:00.000Z https://newruntime.com/signals/github-copilot-app-becomes-an-operating-layer-for-routines/ 2026-06-28T00:00:00.000Z https://newruntime.com/signals/shopify-treats-code-as-output-and-guardrails-as-engineering/ 2026-06-28T00:00:00.000Z https://newruntime.com/signals/parallel-agent-workflow-needs-operator-stack/ 2026-06-27T00:00:00.000Z https://newruntime.com/signals/cursor-is-expanding-from-ide-to-agent-factory/ 2026-06-27T00:00:00.000Z https://newruntime.com/signals/glm-5-2-changes-the-economics-of-claude-code-workflows/ 2026-06-27T00:00:00.000Z https://newruntime.com/signals/ai-spend-measured-per-successful-task/ 2026-06-27T00:00:00.000Z https://newruntime.com/signals/creative-ideation-becomes-a-routable-agent-skill/ 2026-06-27T00:00:00.000Z https://newruntime.com/signals/ai-sdk-7-grows-into-an-agent-runtime/ 2026-06-27T00:00:00.000Z https://newruntime.com/signals/claude-design-closes-the-loop-between-brand-and-daily-output/ 2026-06-26T00:00:00.000Z https://newruntime.com/signals/sakana-fugu-presents-multiple-agents-as-one-model-endpoint/ 2026-06-25T00:00:00.000Z https://newruntime.com/signals/agentic-resource-discovery-indexes-skills-mcp-and-agents/ 2026-06-24T00:00:00.000Z https://newruntime.com/signals/hermes-turns-solved-tasks-into-new-skills/ 2026-06-24T00:00:00.000Z https://newruntime.com/signals/preply-uses-each-lesson-as-context-for-the-next/ 2026-06-24T00:00:00.000Z https://newruntime.com/signals/doordash-memory-is-versioned-personalization-layer/ 2026-06-24T00:00:00.000Z https://newruntime.com/signals/claude-tag-gives-the-agent-a-native-slack-identity/ 2026-06-24T00:00:00.000Z https://newruntime.com/signals/doordash-assistant-builds-the-cart-instead-of-giving-advice/ 2026-06-24T00:00:00.000Z https://newruntime.com/signals/cloudflare-gives-agents-temporary-accounts/ 2026-06-23T00:00:00.000Z https://newruntime.com/signals/domain-expertise-becomes-an-interface-to-coding-agents/ 2026-06-23T00:00:00.000Z https://newruntime.com/signals/claude-md-shrinks-as-skills-hooks-and-subagents-mature/ 2026-06-23T00:00:00.000Z https://newruntime.com/signals/ai-compresses-coding-not-whole-sdlc/ 2026-06-23T00:00:00.000Z https://newruntime.com/signals/openai-built-a-data-agent-across-ninety-thousand-tables/ 2026-06-23T00:00:00.000Z https://newruntime.com/signals/workspace-agents-gain-api-triggers/ 2026-06-22T00:00:00.000Z https://newruntime.com/signals/agent-loops-can-generate-their-own-follow-up-work/ 2026-06-22T00:00:00.000Z https://newruntime.com/signals/cursor-converts-a-text-workflow-into-an-automation/ 2026-06-22T00:00:00.000Z https://newruntime.com/signals/codex-turns-a-recorded-mac-workflow-into-a-reusable-skill/ 2026-06-22T00:00:00.000Z https://newruntime.com/signals/claude-code-artifacts-as-collaboration-layer/ 2026-06-22T00:00:00.000Z https://newruntime.com/signals/anthropic-shows-when-architecture-beats-more-prompt-tuning/ 2026-06-22T00:00:00.000Z https://newruntime.com/signals/fapo-optimizes-the-whole-llm-pipeline-not-only-the-prompt/ 2026-06-22T00:00:00.000Z https://newruntime.com/signals/coinbase-creates-a-distinct-entry-point-for-ai-agents/ 2026-06-21T00:00:00.000Z https://newruntime.com/signals/claude-managed-agents-productize-the-production-runtime/ 2026-06-21T00:00:00.000Z https://newruntime.com/signals/visual-plans-become-a-shared-interface-for-coding-agents/ 2026-06-20T00:00:00.000Z https://newruntime.com/signals/agents-render-bounded-ui-during-work/ 2026-06-20T00:00:00.000Z https://newruntime.com/signals/taste-lab-uses-a-design-system-as-a-reasoning-brief/ 2026-06-19T00:00:00.000Z https://newruntime.com/signals/the-computer-becomes-a-runtime-assigned-to-the-agent/ 2026-06-19T00:00:00.000Z https://newruntime.com/signals/astro-and-next-js-expose-different-surfaces-to-ai-agents/ 2026-06-19T00:00:00.000Z https://newruntime.com/signals/tokens-stay-the-cost-while-runtime-becomes-the-product/ 2026-06-18T00:00:00.000Z https://newruntime.com/signals/chatgpt-uses-offline-consolidation-to-improve-memory/ 2026-06-18T00:00:00.000Z https://newruntime.com/signals/anthropic-redesigns-engineering-around-cheap-code/ 2026-06-18T00:00:00.000Z https://newruntime.com/signals/hermes-adds-purchases-and-api-payments-to-agent-workflows/ 2026-06-18T00:00:00.000Z https://newruntime.com/signals/last30days-packages-social-research-as-an-agent-skill/ 2026-06-18T00:00:00.000Z https://newruntime.com/signals/google-makes-rag-search-again-before-it-answers/ 2026-06-18T00:00:00.000Z https://newruntime.com/signals/claude-code-can-build-a-task-specific-harness-before-coding/ 2026-06-18T00:00:00.000Z https://newruntime.com/signals/vercel-drop-turns-a-folder-into-a-public-site/ 2026-06-17T00:00:00.000Z https://newruntime.com/signals/fusion-api-uses-multiple-models-and-a-judge-for-one-answer/ 2026-06-17T00:00:00.000Z https://newruntime.com/signals/ponytail-adds-a-senior-cleanup-pass-to-agent-generated-code/ 2026-06-17T00:00:00.000Z https://newruntime.com/signals/worktrunk-makes-git-worktrees-operational-for-parallel-agents/ 2026-06-16T00:00:00.000Z https://newruntime.com/signals/anthropic-shows-two-async-orchestration-patterns/ 2026-06-16T00:00:00.000Z https://newruntime.com/signals/codex-can-run-as-a-maintainer-loop/ 2026-06-16T00:00:00.000Z https://newruntime.com/signals/the-agent-becomes-a-separate-hosting-layer/ 2026-06-16T00:00:00.000Z https://newruntime.com/signals/production-ai-engineering-is-the-system-around-the-model/ 2026-06-16T00:00:00.000Z https://newruntime.com/signals/the-learning-loop-is-more-durable-than-the-model/ 2026-06-16T00:00:00.000Z https://newruntime.com/signals/openai-documents-the-harness-behind-an-autonomous-coding-agent/ 2026-06-02T00:00:00.000Z https://newruntime.com/signals/skillspector-adds-a-security-gate-for-agent-skills/ 2026-06-02T00:00:00.000Z https://newruntime.com/signals/openhuman-builds-a-personal-harness-around-local-memory/ 2026-05-24T00:00:00.000Z https://newruntime.com/signals/codex-subagents-reduce-context-pollution/ 2026-05-24T00:00:00.000Z https://newruntime.com/signals/agent-evals-become-a-discipline-separate-from-model-evals/ 2026-05-21T00:00:00.000Z https://newruntime.com/signals/claude-for-legal-packages-a-legal-team-as-plugins/ 2026-05-20T00:00:00.000Z https://newruntime.com/signals/stitch-evolves-from-screen-generator-into-an-ai-design-environment/ 2026-05-20T00:00:00.000Z https://newruntime.com/signals/google-search-adds-agentic-action-to-discovery/ 2026-05-20T00:00:00.000Z https://newruntime.com/signals/chrome-turns-web-development-into-a-verifiable-agent-loop/ 2026-05-20T00:00:00.000Z https://newruntime.com/signals/shadcn-run-treats-a-design-system-as-an-agent-registry/ 2026-05-19T00:00:00.000Z https://newruntime.com/signals/agentmemory-shares-state-across-codex-claude-code-and-cursor/ 2026-05-19T00:00:00.000Z https://newruntime.com/signals/vercel-treats-production-ai-as-multi-model-infrastructure/ 2026-05-15T00:00:00.000Z https://newruntime.com/signals/cline-sdk-exposes-an-open-harness-for-coding-agents/ 2026-05-14T00:00:00.000Z https://newruntime.com/signals/the-rule-of-12-makes-claude-md-a-behavioral-contract/ 2026-05-14T00:00:00.000Z https://newruntime.com/signals/agent-view-makes-parallel-work-a-first-class-interface/ 2026-05-14T00:00:00.000Z https://newruntime.com/signals/claude-code-goals-turn-completion-into-a-verifiable-contract/ 2026-05-14T00:00:00.000Z https://newruntime.com/signals/github-treats-agent-tokens-as-an-operational-cloud-bill/ 2026-05-09T00:00:00.000Z https://newruntime.com/signals/voice-agents-move-from-conversation-to-tool-using-work/ 2026-05-09T00:00:00.000Z https://newruntime.com/signals/a-personal-agent-os-emerges-from-small-cli-tools/ 2026-05-09T00:00:00.000Z https://newruntime.com/signals/skill-md-acts-as-a-behavior-loader-not-a-better-prompt/ 2026-05-07T00:00:00.000Z https://newruntime.com/signals/openai-shows-memory-compaction-for-long-running-agents/ 2026-05-07T00:00:00.000Z https://newruntime.com/signals/anthropic-packages-financial-work-as-domain-agent-modules/ 2026-05-07T00:00:00.000Z https://newruntime.com/signals/claude-managed-agents-add-outcomes-and-multi-agent-orchestration/ 2026-05-07T00:00:00.000Z https://newruntime.com/signals/hermes-profiles-need-a-shared-work-layer-to-become-a-crew/ 2026-05-07T00:00:00.000Z https://newruntime.com/signals/open-slide-moves-presentation-authoring-into-a-react-runtime/ 2026-05-06T00:00:00.000Z https://newruntime.com/signals/refero-turns-visual-references-into-design-md-files/ 2026-05-06T00:00:00.000Z https://newruntime.com/signals/cursor-ships-its-development-procedures-as-agent-skills/ 2026-05-06T00:00:00.000Z https://newruntime.com/signals/stripe-built-protodash-around-its-own-design-system/ 2026-05-06T00:00:00.000Z https://newruntime.com/signals/cocoindex-keeps-agent-context-fresh-without-full-reindexing/ 2026-05-06T00:00:00.000Z https://newruntime.com/patterns/agent-ready-software-exposes-capabilities/ 2026-07-16T00:00:00.000Z https://newruntime.com/patterns/ai-native-orgs-move-to-review-and-orchestration/ 2026-07-16T00:00:00.000Z https://newruntime.com/patterns/company-memory-needs-write-loops/ 2026-07-16T00:00:00.000Z https://newruntime.com/patterns/harness-architecture-outlives-model-choice/ 2026-07-16T00:00:00.000Z https://newruntime.com/patterns/model-answers-become-task-interfaces/ 2026-07-16T00:00:00.000Z https://newruntime.com/patterns/skills-become-portable-capability-layer/ 2026-07-16T00:00:00.000Z https://newruntime.com/patterns/verification-bandwidth-is-the-scarce-resource/ 2026-07-16T00:00:00.000Z https://newruntime.com/patterns/agent-economics-moves-to-completed-work/ 2026-07-15T00:00:00.000Z https://newruntime.com/patterns/goal-scoped-loops-replace-manual-continuation/ 2026-07-07T00:00:00.000Z https://newruntime.com/patterns/design-systems-become-agent-context/ 2026-06-26T00:00:00.000Z https://newruntime.com/shifts/generated-interface-from-answer/ 2026-07-21T00:00:00.000Z https://newruntime.com/shifts/shared-context-infrastructure/ 2026-07-21T00:00:00.000Z https://newruntime.com/shifts/goal-scoped-agent-loops/ 2026-07-21T00:00:00.000Z https://newruntime.com/shifts/compute-backed-ai-contracts/ 2026-07-21T00:00:00.000Z https://newruntime.com/deltas/agent-first-api-contracts/ 2026-07-21T00:00:00.000Z https://newruntime.com/deltas/attacker-first-remediation-loop/ 2026-07-21T00:00:00.000Z https://newruntime.com/deltas/shared-context-portability/ 2026-07-21T00:00:00.000Z https://newruntime.com/graveyard/manual-context-handoff/ 2026-07-22T00:00:00.000Z https://newruntime.com/graveyard/changelog-bullet-reading/ 2026-07-22T00:00:00.000Z https://newruntime.com/projects/coding-agent-cost-controls/ 2026-07-21T00:00:00.000Z https://newruntime.com/projects/verifiable-ai-coding-workflow/ 2026-07-21T00:00:00.000Z https://newruntime.com/systems/hermes/ 2026-07-21T00:00:00.000Z https://newruntime.com/systems/openclaw/ 2026-07-21T00:00:00.000Z