{"schema_version":"newruntime-topic-hub-v0.2","type":"topic_hub","stable_id":"topic_hub:agent-harness","slug":"agent-harness","title":"Agent Harness - New Runtime","description":"A New Runtime topic hub collecting signals, patterns, field notes, and public sources about agent harness.","retrieval_nugget":"A New Runtime topic hub collecting signals, patterns, field notes, and public sources about agent harness. Agent Harness is tracked here as an evidence-linked topic, not as a static glossary entry. The page connects raw observations to pattern hypotheses, longer analysis, and public sources. Use it as the canonical landing page before drilling into individual records.","answer":["Agent Harness is tracked here as an evidence-linked topic, not as a static glossary entry.","The page connects raw observations to pattern hypotheses, longer analysis, and public sources.","Use it as the canonical landing page before drilling into individual records."],"search_intents":["agent harness","agent harness AI agents","agent harness software"],"status":"featured","last_updated":"2026-08-03","record_date":"2026-08-03","date_kind":"last_updated","counts":{"total":121,"signals":104,"patterns":0,"posts":17,"atlas":0,"sources":193},"routes":{"html":"https://newruntime.com/topics/agent-harness/","markdown":"https://newruntime.com/topics/agent-harness.md","json":"https://newruntime.com/topics/agent-harness.json"},"source_urls":["https://addyosmani.com/blog/good-spec","https://agentation.com/","https://ai.google.dev/gemini-api/docs/gemini-3","https://aitmpl.com/component/hook/dangerous-command-blocker","https://alilleybrinker.com/mini/gas-town-decoded","https://americanbanker.com/news/citi-mandates-ai-prompt-training-for-most-employees","https://ando.so/","https://anthropic.com/engineering/AI-resistant-technical-evaluations","https://anthropic.com/engineering/claude-code-sandboxing","https://anthropic.com/engineering/effective-context-engineering-for-ai-agents","https://anthropic.com/engineering/managed-agents","https://anthropic.com/news/claude-code-on-the-web"],"top_sources":["https://addyosmani.com/blog/good-spec","https://agentation.com/","https://ai.google.dev/gemini-api/docs/gemini-3","https://aitmpl.com/component/hook/dangerous-command-blocker","https://alilleybrinker.com/mini/gas-town-decoded","https://americanbanker.com/news/citi-mandates-ai-prompt-training-for-most-employees","https://ando.so/","https://anthropic.com/engineering/AI-resistant-technical-evaluations","https://anthropic.com/engineering/claude-code-sandboxing","https://anthropic.com/engineering/effective-context-engineering-for-ai-agents","https://anthropic.com/engineering/managed-agents","https://anthropic.com/news/claude-code-on-the-web"],"evidence_records":[{"kind":"Field Note","stable_id":"post:agentic-sdlc-software-factory-loop","slug":"agentic-sdlc-software-factory-loop","title":"A Software Factory Connects Agents Through Verified Outcomes","date":"2026-08-03","record_date":"2026-08-03","date_kind":"updated_or_published_at","source_count":2,"url":"https://newruntime.com/posts/agentic-sdlc-software-factory-loop/"},{"kind":"Field Note","stable_id":"post:browserbase-search-fetch-browser-routing","slug":"browserbase-search-fetch-browser-routing","title":"Agents Should Search, Fetch, And Browse As Separate Operations","date":"2026-08-03","record_date":"2026-08-03","date_kind":"updated_or_published_at","source_count":1,"url":"https://newruntime.com/posts/browserbase-search-fetch-browser-routing/"},{"kind":"Field Note","stable_id":"post:chatgpt-agent-loop-efficiency-stack","slug":"chatgpt-agent-loop-efficiency-stack","title":"ChatGPT Cuts Repeated Work Across The Agent Stack","date":"2026-08-03","record_date":"2026-08-03","date_kind":"updated_or_published_at","source_count":1,"url":"https://newruntime.com/posts/chatgpt-agent-loop-efficiency-stack/"},{"kind":"Field Note","stable_id":"post:claude-code-auto-mode-action-gate","slug":"claude-code-auto-mode-action-gate","title":"Claude Code Auto Mode Gates Actions Instead Of Explanations","date":"2026-08-03","record_date":"2026-08-03","date_kind":"updated_or_published_at","source_count":1,"url":"https://newruntime.com/posts/claude-code-auto-mode-action-gate/"},{"kind":"Field Note","stable_id":"post:cline-hooks-agent-harness-guardrails","slug":"cline-hooks-agent-harness-guardrails","title":"Cline Hooks Put Deterministic Rules Inside The Agent Loop","date":"2026-08-03","record_date":"2026-08-03","date_kind":"updated_or_published_at","source_count":1,"url":"https://newruntime.com/posts/cline-hooks-agent-harness-guardrails/"},{"kind":"Field Note","stable_id":"post:anthropic-agent-containment-blast-radius","slug":"anthropic-agent-containment-blast-radius","title":"Containment Caps An Agent's Blast Radius","date":"2026-08-03","record_date":"2026-08-03","date_kind":"updated_or_published_at","source_count":1,"url":"https://newruntime.com/posts/anthropic-agent-containment-blast-radius/"},{"kind":"Field Note","stable_id":"post:anthropic-tool-search-programmatic-calls","slug":"anthropic-tool-search-programmatic-calls","title":"Anthropic Moves Large Tool Libraries Out Of Context","date":"2026-08-01","record_date":"2026-08-01","date_kind":"updated_or_published_at","source_count":1,"url":"https://newruntime.com/posts/anthropic-tool-search-programmatic-calls/"},{"kind":"Field Note","stable_id":"post:arcee-open-model-science-post-training","slug":"arcee-open-model-science-post-training","title":"Arcee Turns Scientific Post-Training Into A Run Ledger","date":"2026-08-01","record_date":"2026-08-01","date_kind":"updated_or_published_at","source_count":1,"url":"https://newruntime.com/posts/arcee-open-model-science-post-training/"},{"kind":"Field Note","stable_id":"post:genkit-agent-skills-progressive-disclosure","slug":"genkit-agent-skills-progressive-disclosure","title":"Genkit Adds Progressive Disclosure For Agent Skills","date":"2026-08-01","record_date":"2026-08-01","date_kind":"updated_or_published_at","source_count":1,"url":"https://newruntime.com/posts/genkit-agent-skills-progressive-disclosure/"},{"kind":"Field Note","stable_id":"post:cline-recursive-self-improvement-coding-agent","slug":"cline-recursive-self-improvement-coding-agent","title":"Cline Turns Recursive Self-Improvement Into Harness Work","date":"2026-07-30","record_date":"2026-07-30","date_kind":"updated_or_published_at","source_count":2,"url":"https://newruntime.com/posts/cline-recursive-self-improvement-coding-agent/"},{"kind":"Field Note","stable_id":"post:openai-gpt-5-6-efficiency-stack","slug":"openai-gpt-5-6-efficiency-stack","title":"OpenAI Shows Efficiency Is a Full-Stack Agent Problem","date":"2026-07-30","record_date":"2026-07-30","date_kind":"updated_or_published_at","source_count":3,"url":"https://newruntime.com/posts/openai-gpt-5-6-efficiency-stack/"},{"kind":"Field Note","stable_id":"post:openai-arc-agi-settings-harness","slug":"openai-arc-agi-settings-harness","title":"OpenAI's ARC-AGI-3 Jump Was a Harness Result","date":"2026-07-30","record_date":"2026-07-30","date_kind":"updated_or_published_at","source_count":2,"url":"https://newruntime.com/posts/openai-arc-agi-settings-harness/"}],"patterns":[],"field_notes":[{"kind":"Field Note","stable_id":"post:agentic-sdlc-software-factory-loop","slug":"agentic-sdlc-software-factory-loop","title":"A Software Factory Connects Agents Through Verified Outcomes","description":"Augment and Warp describe team-level agent loops that move work from trigger and specification through implementation, verification, release, and measured improvement.","date":"2026-08-03","record_date":"2026-08-03","date_kind":"updated_or_published_at","topics":["agent-harness","coding-agents","evals","software-factories"],"source_count":2,"url":"https://newruntime.com/posts/agentic-sdlc-software-factory-loop/"},{"kind":"Field Note","stable_id":"post:browserbase-search-fetch-browser-routing","slug":"browserbase-search-fetch-browser-routing","title":"Agents Should Search, Fetch, And Browse As Separate Operations","description":"Browserbase separates discovery, content retrieval, and browser interaction so research agents do not launch a full browser merely to obtain a list of URLs.","date":"2026-08-03","record_date":"2026-08-03","date_kind":"updated_or_published_at","topics":["agent-harness","agents","browser-automation","web-research"],"source_count":1,"url":"https://newruntime.com/posts/browserbase-search-fetch-browser-routing/"},{"kind":"Field Note","stable_id":"post:chatgpt-agent-loop-efficiency-stack","slug":"chatgpt-agent-loop-efficiency-stack","title":"ChatGPT Cuts Repeated Work Across The Agent Stack","description":"ByteByteGo's OpenAI engineering walkthrough connects persistent sessions, stable prompt prefixes, deferred tools, delta tokenization, cache-aware routing, and split inference.","date":"2026-08-03","record_date":"2026-08-03","date_kind":"updated_or_published_at","topics":["agent-harness","context-engineering","inference","performance"],"source_count":1,"url":"https://newruntime.com/posts/chatgpt-agent-loop-efficiency-stack/"},{"kind":"Field Note","stable_id":"post:claude-code-auto-mode-action-gate","slug":"claude-code-auto-mode-action-gate","title":"Claude Code Auto Mode Gates Actions Instead Of Explanations","description":"Claude Code Auto Mode combines an input injection probe with a two-stage action classifier, preserving autonomy while exposing an honest residual miss rate.","date":"2026-08-03","record_date":"2026-08-03","date_kind":"updated_or_published_at","topics":["agent-harness","agent-security","coding-agents","evals"],"source_count":1,"url":"https://newruntime.com/posts/claude-code-auto-mode-action-gate/"},{"kind":"Field Note","stable_id":"post:cline-hooks-agent-harness-guardrails","slug":"cline-hooks-agent-harness-guardrails","title":"Cline Hooks Put Deterministic Rules Inside The Agent Loop","description":"Cline's plugin hooks show how an agent harness can journal every run and block dangerous tool calls without waiting for the model to choose a guardrail.","date":"2026-08-03","record_date":"2026-08-03","date_kind":"updated_or_published_at","topics":["agent-harness","coding-agents","mcp","observability"],"source_count":1,"url":"https://newruntime.com/posts/cline-hooks-agent-harness-guardrails/"},{"kind":"Field Note","stable_id":"post:anthropic-agent-containment-blast-radius","slug":"anthropic-agent-containment-blast-radius","title":"Containment Caps An Agent's Blast Radius","description":"Anthropic's three runtime patterns show why hard filesystem, network, credential, and trust boundaries carry more security weight than repeated approval prompts.","date":"2026-08-03","record_date":"2026-08-03","date_kind":"updated_or_published_at","topics":["agent-harness","agent-security","governance","runtime-isolation"],"source_count":1,"url":"https://newruntime.com/posts/anthropic-agent-containment-blast-radius/"},{"kind":"Field Note","stable_id":"post:anthropic-tool-search-programmatic-calls","slug":"anthropic-tool-search-programmatic-calls","title":"Anthropic Moves Large Tool Libraries Out Of Context","description":"Anthropic's Tool Search Tool, Programmatic Tool Calling, and Tool Use Examples separate discovery, orchestration, and usage guidance for agents with large tool libraries.","date":"2026-08-01","record_date":"2026-08-01","date_kind":"updated_or_published_at","topics":["agent-harness","context-engineering","mcp","tools"],"source_count":1,"url":"https://newruntime.com/posts/anthropic-tool-search-programmatic-calls/"},{"kind":"Field Note","stable_id":"post:arcee-open-model-science-post-training","slug":"arcee-open-model-science-post-training","title":"Arcee Turns Scientific Post-Training Into A Run Ledger","description":"Arcee's open-model science write-up shows a 21-run post-training loop around Trinity Mini, held-out scientific environments, trace review, and a promoted specialist adapter.","date":"2026-08-01","record_date":"2026-08-01","date_kind":"updated_or_published_at","topics":["agent-harness","open-models","post-training","scientific-ai"],"source_count":1,"url":"https://newruntime.com/posts/arcee-open-model-science-post-training/"},{"kind":"Field Note","stable_id":"post:genkit-agent-skills-progressive-disclosure","slug":"genkit-agent-skills-progressive-disclosure","title":"Genkit Adds Progressive Disclosure For Agent Skills","description":"Genkit now loads Agent Skills through middleware that discovers SKILL.md metadata first and activates full instructions, references, and scripts only when needed.","date":"2026-08-01","record_date":"2026-08-01","date_kind":"updated_or_published_at","topics":["agent-harness","context-engineering","genkit","skills"],"source_count":1,"url":"https://newruntime.com/posts/genkit-agent-skills-progressive-disclosure/"},{"kind":"Field Note","stable_id":"post:cline-recursive-self-improvement-coding-agent","slug":"cline-recursive-self-improvement-coding-agent","title":"Cline Turns Recursive Self-Improvement Into Harness Work","description":"Cline's Terminal-Bench run is not a singularity story; it is a concrete loop where an agent reads traces, patches the harness, reruns evals, and hands a PR to humans.","date":"2026-07-30","record_date":"2026-07-30","date_kind":"updated_or_published_at","topics":["agent-economics","agent-harness","coding-agents","evals","open-source"],"source_count":2,"url":"https://newruntime.com/posts/cline-recursive-self-improvement-coding-agent/"},{"kind":"Field Note","stable_id":"post:openai-gpt-5-6-efficiency-stack","slug":"openai-gpt-5-6-efficiency-stack","title":"OpenAI Shows Efficiency Is a Full-Stack Agent Problem","description":"OpenAI's GPT-5.6 efficiency write-up connects model training, inference optimization, and the Codex/ChatGPT Work harness into one compounding cost-performance loop.","date":"2026-07-30","record_date":"2026-07-30","date_kind":"updated_or_published_at","topics":["agent-economics","agent-harness","context-engineering","inference","models"],"source_count":3,"url":"https://newruntime.com/posts/openai-gpt-5-6-efficiency-stack/"},{"kind":"Field Note","stable_id":"post:openai-arc-agi-settings-harness","slug":"openai-arc-agi-settings-harness","title":"OpenAI's ARC-AGI-3 Jump Was a Harness Result","description":"OpenAI's ARC-AGI-3 write-up shows why agent benchmarks measure the model plus the runtime harness: retained reasoning and compaction changed both score and token use.","date":"2026-07-30","record_date":"2026-07-30","date_kind":"updated_or_published_at","topics":["agent-harness","api-design","context-engineering","evals","models"],"source_count":2,"url":"https://newruntime.com/posts/openai-arc-agi-settings-harness/"},{"kind":"Field Note","stable_id":"post:claude-opus-5-prompt-contracts","slug":"claude-opus-5-prompt-contracts","title":"Claude Opus 5 Makes Prompting a Runtime Contract","description":"Anthropic's Opus 5 prompting guide shows that stronger models can make old harness defaults wrong: verbosity, effort, verification, delegation, and thinking mode all become runtime controls.","date":"2026-07-28","record_date":"2026-07-28","date_kind":"updated_or_published_at","topics":["agent-harness","claude","prompting"],"source_count":1,"url":"https://newruntime.com/posts/claude-opus-5-prompt-contracts/"},{"kind":"Field Note","stable_id":"post:langchain-deep-agents-lean-harness","slug":"langchain-deep-agents-lean-harness","title":"LangChain Deep Agents Shrink the Harness Instead of Adding More Prompt","description":"Deep Agents v0.7.0b2 cuts default-agent input tokens by 65% and tool-description tokens by 43%, turning harness efficiency into a first-class agent metric.","date":"2026-07-27","record_date":"2026-07-27","date_kind":"updated_or_published_at","topics":["agent-harness","agents","developer-tools","evals"],"source_count":2,"url":"https://newruntime.com/posts/langchain-deep-agents-lean-harness/"},{"kind":"Field Note","stable_id":"post:open-secure-ai-alliance-open-defense-stack","slug":"open-secure-ai-alliance-open-defense-stack","title":"Open Secure AI Alliance Turns the AI-Safety Fight Into a Stack Question","description":"NVIDIA's Open Secure AI Alliance reframes open models, harnesses, identity, safe formats, scanners, and disclosure as shared defensive infrastructure for AI agents.","date":"2026-07-27","record_date":"2026-07-27","date_kind":"updated_or_published_at","topics":["agent-harness","ai-security","governance","open-models"],"source_count":6,"url":"https://newruntime.com/posts/open-secure-ai-alliance-open-defense-stack/"},{"kind":"Field Note","stable_id":"post:agent-harness-optimization-outer-loop","slug":"agent-harness-optimization-outer-loop","title":"Agent Harness Optimization Is Becoming an Outer-Loop Discipline","description":"The next useful automation target is not another agent response. It is the controlled loop that changes prompts, tools, context, and routing, then keeps only improvements that survive evaluation.","date":"2026-07-24","record_date":"2026-07-24","date_kind":"updated_or_published_at","topics":["agent-harness","autoresearch","evals","optimization"],"source_count":5,"url":"https://newruntime.com/posts/agent-harness-optimization-outer-loop/"},{"kind":"Field Note","stable_id":"post:coding-agents-multi-model-harness","slug":"coding-agents-multi-model-harness","title":"The Coding Harness Is Becoming Independent From the Model","description":"Practitioners are routing different models through coding-agent workflows, while production systems increasingly choose model and effort per role instead of per product.","date":"2026-07-24","record_date":"2026-07-24","date_kind":"updated_or_published_at","topics":["agent-harness","coding-agents","model-routing"],"source_count":5,"url":"https://newruntime.com/posts/coding-agents-multi-model-harness/"}],"raw_signals":[{"kind":"Raw Signal","stable_id":"signal:claude-opus-5-prompt-contracts","slug":"claude-opus-5-prompt-contracts","title":"Claude Opus 5 Turns Prompting Into Harness Calibration","description":"Anthropic's Opus 5 prompting guide shows model upgrades changing the harness contract: verbosity, progress updates, scope, subagents, verification, and thinking mode all need retuning.","date":"2026-07-28","record_date":"2026-07-28","date_kind":"observed_at","topics":["agent-harness","claude","prompting"],"source_count":1,"metric":"structural","url":"https://newruntime.com/signals/claude-opus-5-prompt-contracts/"},{"kind":"Raw Signal","stable_id":"signal:anthropic-goal-scoped-agent-loops","slug":"anthropic-goal-scoped-agent-loops","title":"Anthropic: Goal-Scoped Agent Loops","description":"The archive captures X source as a dated public record from X source. It documents long-running work gaining explicit goals, state, stopping rules, and recovery and is retained as pressure-testing evidence for the goal-scoped agent loops trend.","date":"2026-06-26","record_date":"2026-06-26","date_kind":"observed_at","topics":["agent-harness","agent-loops","agents","automation","coding-agents","orchestration","skills"],"source_count":1,"metric":"notable","url":"https://newruntime.com/signals/anthropic-goal-scoped-agent-loops/"},{"kind":"Raw Signal","stable_id":"signal:claude-code-verification-bandwidth","slug":"claude-code-verification-bandwidth","title":"Claude Code: Verification Bandwidth","description":"The archive captures Claude Code as a dated public record from Claude Code. It documents evaluation, review, and observability becoming the bottleneck after generation accelerates and is retained as pressure-testing evidence for the verification bandwidth trend.","date":"2026-06-02","record_date":"2026-06-02","date_kind":"observed_at","topics":["agent-harness","claude","coding-agents","evals","observability","skills","verification"],"source_count":1,"metric":"notable","url":"https://newruntime.com/signals/claude-code-verification-bandwidth/"},{"kind":"Raw Signal","stable_id":"signal:github-cursor-plugins-verification-bandwidth","slug":"github-cursor-plugins-verification-bandwidth","title":"GitHub / cursor/plugins: Verification Bandwidth","description":"The archive captures GitHub / cursor/plugins as a dated public record from GitHub / cursor/plugins. It documents evaluation, review, and observability becoming the bottleneck after generation accelerates and is retained as pressure-testing evidence for the verification bandwidth trend.","date":"2026-06-02","record_date":"2026-06-02","date_kind":"observed_at","topics":["agent-harness","coding-agents","cursor","evals","observability","skills","verification"],"source_count":1,"metric":"notable","url":"https://newruntime.com/signals/github-cursor-plugins-verification-bandwidth/"},{"kind":"Raw Signal","stable_id":"signal:asteroid-task-specific-ai-interfaces","slug":"asteroid-task-specific-ai-interfaces","title":"Asteroid: Task-Specific Ai Interfaces","description":"The archive captures Asteroid as a dated public record from Asteroid. It documents model output moving from plain answers into generated task interfaces and actions and is retained as supporting evidence for the task-specific AI interfaces trend.","date":"2026-05-21","record_date":"2026-05-21","date_kind":"observed_at","topics":["agent-harness","agent-interfaces","agent-runtime","agent-tools","agents","computer-use","generative-ui"],"source_count":1,"metric":"notable","url":"https://newruntime.com/signals/asteroid-task-specific-ai-interfaces/"},{"kind":"Raw Signal","stable_id":"signal:walkinglabs-learn-harness-engineering-verification-bandwidth","slug":"walkinglabs-learn-harness-engineering-verification-bandwidth","title":"Walkinglabs / Learn Harness Engineering: Verification Bandwidth","description":"The archive captures Walkinglabs / Learn Harness Engineering as a dated public record from Walkinglabs / Learn Harness Engineering. It documents evaluation, review, and observability becoming the bottleneck after generation accelerates and is retained as pressure-testing evidence for the verification bandwidth trend.","date":"2026-05-21","record_date":"2026-05-21","date_kind":"observed_at","topics":["agent-harness","coding-agents","evals","harness-engineering","observability","skills","verification"],"source_count":1,"metric":"notable","url":"https://newruntime.com/signals/walkinglabs-learn-harness-engineering-verification-bandwidth/"},{"kind":"Raw Signal","stable_id":"signal:google-gemini-models-agent-ready-software","slug":"google-gemini-models-agent-ready-software","title":"Google / Gemini Models: Agent-Ready Software","description":"The archive captures Google / Gemini Models as a dated public record from Google / Gemini Models. It documents software exposing explicit capabilities, permissions, and machine-readable actions and is retained as supporting evidence for the agent-ready software trend.","date":"2026-05-20","record_date":"2026-05-20","date_kind":"observed_at","topics":["agent-harness","agent-interfaces","agent-runtime","agent-tools","agents","computer-use","generative-ui"],"source_count":2,"metric":"notable","url":"https://newruntime.com/signals/google-gemini-models-agent-ready-software/"},{"kind":"Raw Signal","stable_id":"signal:claude-goal-scoped-agent-loops-2307","slug":"claude-goal-scoped-agent-loops-2307","title":"Claude: Goal-Scoped Agent Loops","description":"The archive captures YouTube source as a dated public record from YouTube source. It documents long-running work gaining explicit goals, state, stopping rules, and recovery and is retained as supporting evidence for the goal-scoped agent loops trend.","date":"2026-05-07","record_date":"2026-05-07","date_kind":"observed_at","topics":["agent-harness","agent-loops","agents","automation","coding-agents","orchestration","skills"],"source_count":1,"metric":"notable","url":"https://newruntime.com/signals/claude-goal-scoped-agent-loops-2307/"},{"kind":"Raw Signal","stable_id":"signal:skill-md-acts-as-a-behavior-loader-not-a-better-prompt","slug":"skill-md-acts-as-a-behavior-loader-not-a-better-prompt","title":"SKILL.md Acts as a Behavior Loader, Not a Better Prompt","description":"Skills package procedures, tools, and progressive context so an agent can load behavior only when the task requires it.","date":"2026-05-07","record_date":"2026-05-07","date_kind":"observed_at","topics":["agent-harness","context-engineering","skills"],"source_count":3,"metric":"notable","url":"https://newruntime.com/signals/skill-md-acts-as-a-behavior-loader-not-a-better-prompt/"},{"kind":"Raw Signal","stable_id":"signal:claude-goal-scoped-agent-loops","slug":"claude-goal-scoped-agent-loops","title":"Claude: Goal-Scoped Agent Loops","description":"The archive captures X source as a dated public record from X source. It documents long-running work gaining explicit goals, state, stopping rules, and recovery and is retained as pressure-testing evidence for the goal-scoped agent loops trend.","date":"2026-05-06","record_date":"2026-05-06","date_kind":"observed_at","topics":["agent-harness","agent-loops","agents","automation","coding-agents","orchestration","skills"],"source_count":1,"metric":"notable","url":"https://newruntime.com/signals/claude-goal-scoped-agent-loops/"},{"kind":"Raw Signal","stable_id":"signal:stripe-built-protodash-around-its-own-design-system","slug":"stripe-built-protodash-around-its-own-design-system","title":"Stripe Built ProtoDash Around Its Own Design System","description":"Stripe's internal prototyping harness combines product rules, components, sandboxes, and review feedback instead of generating generic mockups.","date":"2026-05-06","record_date":"2026-05-06","date_kind":"observed_at","topics":["agent-harness","design-systems","prototyping"],"source_count":1,"metric":"notable","url":"https://newruntime.com/signals/stripe-built-protodash-around-its-own-design-system/"},{"kind":"Raw Signal","stable_id":"signal:github-nousresearch-hermes-agent-generative-media-infrastructure","slug":"github-nousresearch-hermes-agent-generative-media-infrastructure","title":"GitHub / NousResearch/hermes-agent: Generative Media Infrastructure","description":"The archive captures GitHub / NousResearch/hermes-agent as a dated public record from GitHub / NousResearch/hermes-agent. It documents image, video, audio, and multimodal generation becoming application infrastructure and is retained as branch-opening evidence for the generative media infrastructure trend.","date":"2026-04-30","record_date":"2026-04-30","date_kind":"observed_at","topics":["agent-harness","coding-agents","comfyui","generative-media","media-infrastructure","multimodal","skills"],"source_count":1,"metric":"structural","url":"https://newruntime.com/signals/github-nousresearch-hermes-agent-generative-media-infrastructure/"},{"kind":"Raw Signal","stable_id":"signal:github-stripe-link-cli-task-specific-ai-interfaces","slug":"github-stripe-link-cli-task-specific-ai-interfaces","title":"GitHub / stripe/link-cli: Task-Specific Ai Interfaces","description":"The archive captures GitHub / stripe/link-cli as a dated public record from GitHub / stripe/link-cli. It documents model output moving from plain answers into generated task interfaces and actions and is retained as supporting evidence for the task-specific AI interfaces trend.","date":"2026-04-30","record_date":"2026-04-30","date_kind":"observed_at","topics":["agent-harness","agent-interfaces","agents","coding-agents","computer-use","generative-ui","skills"],"source_count":2,"metric":"notable","url":"https://newruntime.com/signals/github-stripe-link-cli-task-specific-ai-interfaces/"},{"kind":"Raw Signal","stable_id":"signal:ando-ai-native-operating-models","slug":"ando-ai-native-operating-models","title":"Ando: Ai-Native Operating Models","description":"The archive captures Ando as a dated public record from Ando. It documents AI adoption shifting jobs, coordination, review, and organizational capacity and is retained as supporting evidence for the AI-native operating models trend.","date":"2026-04-24","record_date":"2026-04-24","date_kind":"observed_at","topics":["agent-harness","agent-interfaces","ai-adoption","computer-use","future-of-work","generative-ui","org-design"],"source_count":3,"metric":"notable","url":"https://newruntime.com/signals/ando-ai-native-operating-models/"},{"kind":"Raw Signal","stable_id":"signal:google-cloud-gemini-enterprise-agent-platform-ai-native-operating-models","slug":"google-cloud-gemini-enterprise-agent-platform-ai-native-operating-models","title":"Google Cloud / Gemini Enterprise Agent Platform: Ai-Native Operating Models","description":"The archive captures Google Cloud / Gemini Enterprise Agent Platform as a dated public record from Google Cloud / Gemini Enterprise Agent Platform. It documents AI adoption shifting jobs, coordination, review, and organizational capacity and is retained as pressure-testing evidence for the AI-native operating models trend.","date":"2026-04-24","record_date":"2026-04-24","date_kind":"observed_at","topics":["agent-harness","agent-runtime","agent-tools","agents","ai-adoption","future-of-work","org-design"],"source_count":1,"metric":"notable","url":"https://newruntime.com/signals/google-cloud-gemini-enterprise-agent-platform-ai-native-operating-models/"},{"kind":"Raw Signal","stable_id":"signal:image-generation-prompting-guide","slug":"image-generation-prompting-guide","title":"Image generation prompting Guide","description":"The archive captures Image generation prompting Guide as a dated public record from OpenAI Developers / Image Gen Models Prompting. It documents image, video, audio, and multimodal generation becoming application infrastructure and is retained as branch-opening evidence for the generative media infrastructure trend.","date":"2026-04-24","record_date":"2026-04-24","date_kind":"observed_at","topics":["agent-context","agent-harness","design-systems","frontend","generative-media","media-infrastructure","multimodal"],"source_count":1,"metric":"structural","url":"https://newruntime.com/signals/image-generation-prompting-guide/"},{"kind":"Raw Signal","stable_id":"signal:microsoft-new-hosted-agents-in-foundry-agent-service-verification-bandwidth","slug":"microsoft-new-hosted-agents-in-foundry-agent-service-verification-bandwidth","title":"Microsoft / New Hosted Agents In Foundry Agent Service: Verification Bandwidth","description":"The archive captures Microsoft / New Hosted Agents In Foundry Agent Service as a dated public record from Microsoft / New Hosted Agents In Foundry Agent Service. It documents evaluation, review, and observability becoming the bottleneck after generation accelerates and is retained as pressure-testing evidence for the verification bandwidth trend.","date":"2026-04-24","record_date":"2026-04-24","date_kind":"observed_at","topics":["agent-harness","agent-runtime","agent-tools","agents","evals","observability","verification"],"source_count":1,"metric":"notable","url":"https://newruntime.com/signals/microsoft-new-hosted-agents-in-foundry-agent-service-verification-bandwidth/"},{"kind":"Raw Signal","stable_id":"signal:anthropic-81k-economics-verification-bandwidth","slug":"anthropic-81k-economics-verification-bandwidth","title":"Anthropic / 81k Economics: Verification Bandwidth","description":"The archive captures Anthropic / 81k Economics as a dated public record from Anthropic / 81k Economics. It documents evaluation, review, and observability becoming the bottleneck after generation accelerates and is retained as pressure-testing evidence for the verification bandwidth trend.","date":"2026-04-23","record_date":"2026-04-23","date_kind":"observed_at","topics":["agent-harness","ai-adoption","evals","future-of-work","observability","org-design","verification"],"source_count":1,"metric":"notable","url":"https://newruntime.com/signals/anthropic-81k-economics-verification-bandwidth/"},{"kind":"Raw Signal","stable_id":"signal:github-tencentcloud-cubesandbox-agent-security-runtime-boundaries","slug":"github-tencentcloud-cubesandbox-agent-security-runtime-boundaries","title":"GitHub / TencentCloud/CubeSandbox: Agent Security Runtime Boundaries","description":"The archive captures GitHub / TencentCloud/CubeSandbox as a dated public record from GitHub / TencentCloud/CubeSandbox. It documents agent security expanding from prompt policy into memory, tools, sandboxes, and execution boundaries and is retained as branch-opening evidence for the agent security runtime boundaries trend.","date":"2026-04-23","record_date":"2026-04-23","date_kind":"observed_at","topics":["agent-harness","agent-security","agents","coding-agents","prompt-injection","sandbox","skills"],"source_count":1,"metric":"structural","url":"https://newruntime.com/signals/github-tencentcloud-cubesandbox-agent-security-runtime-boundaries/"},{"kind":"Raw Signal","stable_id":"signal:claude-agent-security-runtime-boundaries","slug":"claude-agent-security-runtime-boundaries","title":"Claude: Agent Security Runtime Boundaries","description":"The archive captures YouTube source as a dated public record from YouTube source. It documents agent security expanding from prompt policy into memory, tools, sandboxes, and execution boundaries and is retained as branch-opening evidence for the agent security runtime boundaries trend.","date":"2026-04-22","record_date":"2026-04-22","date_kind":"observed_at","topics":["agent-harness","agent-security","coding-agents","model-routing","prompt-injection","sandbox","skills"],"source_count":1,"metric":"structural","url":"https://newruntime.com/signals/claude-agent-security-runtime-boundaries/"},{"kind":"Raw Signal","stable_id":"signal:google-ai-mode-chrome-task-specific-ai-interfaces","slug":"google-ai-mode-chrome-task-specific-ai-interfaces","title":"Google / Ai Mode Chrome: Task-Specific Ai Interfaces","description":"The archive captures Google / Ai Mode Chrome as a dated public record from Google / Ai Mode Chrome. It documents model output moving from plain answers into generated task interfaces and actions and is retained as supporting evidence for the task-specific AI interfaces trend.","date":"2026-04-20","record_date":"2026-04-20","date_kind":"observed_at","topics":["agent-harness","agent-interfaces","agent-runtime","agent-tools","agents","computer-use","generative-ui"],"source_count":1,"metric":"notable","url":"https://newruntime.com/signals/google-ai-mode-chrome-task-specific-ai-interfaces/"},{"kind":"Raw Signal","stable_id":"signal:github-heygen-com-hyperframes-generative-media-infrastructure","slug":"github-heygen-com-hyperframes-generative-media-infrastructure","title":"GitHub / heygen-com/hyperframes: Generative Media Infrastructure","description":"The archive captures GitHub / heygen-com/hyperframes as a dated public record from GitHub / heygen-com/hyperframes. It documents image, video, audio, and multimodal generation becoming application infrastructure and is retained as branch-opening evidence for the generative media infrastructure trend.","date":"2026-04-19","record_date":"2026-04-19","date_kind":"observed_at","topics":["agent-context","agent-harness","design-systems","frontend","generative-media","media-infrastructure","multimodal"],"source_count":1,"metric":"structural","url":"https://newruntime.com/signals/github-heygen-com-hyperframes-generative-media-infrastructure/"},{"kind":"Raw Signal","stable_id":"signal:openai-next-evolution-of-agents-sdk-agent-ready-software","slug":"openai-next-evolution-of-agents-sdk-agent-ready-software","title":"OpenAI / Next Evolution Of Agents Sdk: Agent-Ready Software","description":"The archive captures OpenAI / Next Evolution Of Agents Sdk as a dated public record from OpenAI / Next Evolution Of Agents Sdk. It documents software exposing explicit capabilities, permissions, and machine-readable actions and is retained as pressure-testing evidence for the agent-ready software trend.","date":"2026-04-16","record_date":"2026-04-16","date_kind":"observed_at","topics":["agent-harness","agent-protocols","agent-runtime","agent-tools","agents","interoperability","mcp"],"source_count":1,"metric":"notable","url":"https://newruntime.com/signals/openai-next-evolution-of-agents-sdk-agent-ready-software/"},{"kind":"Raw Signal","stable_id":"signal:github-farzaa-clicky-task-specific-ai-interfaces","slug":"github-farzaa-clicky-task-specific-ai-interfaces","title":"GitHub / farzaa/clicky: Task-Specific Ai Interfaces","description":"The archive captures GitHub / farzaa/clicky as a dated public record from GitHub / farzaa/clicky. It documents model output moving from plain answers into generated task interfaces and actions and is retained as supporting evidence for the task-specific AI interfaces trend.","date":"2026-04-13","record_date":"2026-04-13","date_kind":"observed_at","topics":["agent-harness","agent-interfaces","agent-runtime","agent-tools","agents","computer-use","generative-ui"],"source_count":3,"metric":"notable","url":"https://newruntime.com/signals/github-farzaa-clicky-task-specific-ai-interfaces/"}],"atlas_records":[],"next_reads":[{"type":"related_material","path":"/posts/agentic-sdlc-software-factory-loop/","reason":"Continue through the Agent Harness topic.","url":"https://newruntime.com/posts/agentic-sdlc-software-factory-loop/","title":"A Software Factory Connects Agents Through Verified Outcomes","media_type":"text/html"},{"type":"related_material","path":"/posts/browserbase-search-fetch-browser-routing/","reason":"Continue through the Agent Harness topic.","url":"https://newruntime.com/posts/browserbase-search-fetch-browser-routing/","title":"Agents Should Search, Fetch, And Browse As Separate Operations","media_type":"text/html"},{"type":"related_material","path":"/posts/chatgpt-agent-loop-efficiency-stack/","reason":"Continue through the Agent Harness topic.","url":"https://newruntime.com/posts/chatgpt-agent-loop-efficiency-stack/","title":"ChatGPT Cuts Repeated Work Across The Agent Stack","media_type":"text/html"},{"type":"related_material","path":"/posts/claude-code-auto-mode-action-gate/","reason":"Continue through the Agent Harness topic.","url":"https://newruntime.com/posts/claude-code-auto-mode-action-gate/","title":"Claude Code Auto Mode Gates Actions Instead Of Explanations","media_type":"text/html"},{"type":"related_material","path":"/posts/cline-hooks-agent-harness-guardrails/","reason":"Continue through the Agent Harness topic.","url":"https://newruntime.com/posts/cline-hooks-agent-harness-guardrails/","title":"Cline Hooks Put Deterministic Rules Inside The Agent Loop","media_type":"text/html"}]}