{"version":"https://jsonfeed.org/version/1.1","title":"Hyperdrift","home_page_url":"https://hyperdrift.io/articles","feed_url":"https://hyperdrift.io/feed.json","items":[{"id":"https://orchestra.hyperdrift.io/articles/give-motivated-founders-a-fair-chance","url":"https://hyperdrift.io/articles/give-motivated-founders-a-fair-chance","title":"Give motivated founders a fair chance","summary":"Why I built Traction to give eager founders sustained help turning their vision into growth.","content_text":"Why I built Traction to give eager founders sustained help turning their vision into growth.","date_published":"2026-11-12","date_modified":"2026-11-15T21:15:44.000Z","tags":["agents","operations"],"image":"https://hyperdrift.io/articles/orchestra/founder-fair-chance-v1.jpg"},{"id":"https://orchestra.hyperdrift.io/articles/opentelemetry-genai-conversation-id","url":"https://hyperdrift.io/articles/opentelemetry-genai-conversation-id","title":"We got our first PR merged into OpenTelemetry","summary":"OpenTelemetry's GenAI conventions now say how an agent framework can share its conversation ID with the model and tool calls nested inside it. Review narrowed the rule to that one ID; agent naming continues in a separate draft.","content_text":"OpenTelemetry's GenAI conventions now say how an agent framework can share its conversation ID with the model and tool calls nested inside it. Review narrowed the rule to that one ID; agent naming continues in a separate draft.","date_published":"2026-10-31T14:00:00Z","date_modified":"2026-11-15T16:51:00.000Z","tags":["agents","operations"],"image":"https://hyperdrift.io/articles/orchestra/otel-conversation-path-v1.jpg"},{"id":"https://orchestra.hyperdrift.io/articles/agent-driven-ui-intelligence-and-action","url":"https://hyperdrift.io/articles/agent-driven-ui-intelligence-and-action","title":"Here’s the new deal. UI is for intel. Agents are for operating.","summary":"A peek into Traction’s 24 October release: the board shows what the Growth Manager and Builder are doing and what they delivered. The agents do the work. We decide what becomes work.","content_text":"A peek into Traction’s 24 October release: the board shows what the Growth Manager and Builder are doing and what they delivered. The agents do the work. We decide what becomes work.","date_published":"2026-10-24T02:11:00Z","date_modified":"2026-11-15T21:15:44.000Z","tags":["agents","ui","operations"],"image":"https://hyperdrift.io/articles/orchestra/intel-and-action-v1.jpg"},{"id":"https://orchestra.hyperdrift.io/articles/production-led-security-maintenance","url":"https://hyperdrift.io/articles/production-led-security-maintenance","title":"Should a security fix wait for the next feature release?","summary":"A finished app still needs repairs. Patch it from production, carry the fix back to development, and refuse any later release that would undo it.","content_text":"A finished app still needs repairs. Patch it from production, carry the fix back to development, and refuse any later release that would undo it.","date_published":"2026-10-13T21:16:00Z","date_modified":"2026-11-15T21:15:44.000Z","tags":["operations","permissions"],"image":"https://hyperdrift.io/articles/orchestra/lasting-security-fix-v1.jpg"},{"id":"https://orchestra.hyperdrift.io/articles/app-operations-after-launch","url":"https://hyperdrift.io/articles/app-operations-after-launch","title":"Your app works. Who runs it now?","summary":"A live app creates five jobs every week. Give them named owners, agents with limits and receipts, and keep the decisions. What that looks like, and what to ask whoever runs your app.","content_text":"A live app creates five jobs every week. Give them named owners, agents with limits and receipts, and keep the decisions. What that looks like, and what to ask whoever runs your app.","date_published":"2026-10-13T21:16:00Z","date_modified":"2026-11-15T20:52:00.000Z","tags":["operations","agents"],"image":"https://hyperdrift.io/articles/orchestra/app-operations-v1.jpg"},{"id":"https://orchestra.hyperdrift.io/articles/is-ui-holding-us-back","url":"https://hyperdrift.io/articles/is-ui-holding-us-back","title":"Is UI holding us back?","summary":"New interfaces can remove work or move it into checking and correction. A historical argument for judging the whole task.","content_text":"New interfaces can remove work or move it into checking and correction. A historical argument for judging the whole task.","date_published":"2026-10-06T00:00:00Z","date_modified":"2026-11-15T21:15:44.000Z","tags":["ui","accessibility","agents"],"image":"https://hyperdrift.io/articles/orchestra/ui-effort-v1.jpg"},{"id":"https://orchestra.hyperdrift.io/articles/web-accessibility-can-people-finish","url":"https://hyperdrift.io/articles/web-accessibility-can-people-finish","title":"Web accessibility: can people finish the job?","summary":"An accessible button is useful. An accessible way to finish is the point. What the current evidence tells us about agents and access.","content_text":"An accessible button is useful. An accessible way to finish is the point. What the current evidence tells us about agents and access.","date_published":"2026-10-06T00:00:00Z","date_modified":"2026-11-15T21:15:44.000Z","tags":["accessibility","voice"],"image":"https://hyperdrift.io/articles/orchestra/accessible-finish-v1.jpg"},{"id":"https://orchestra.hyperdrift.io/articles/webmcp-actions-on-the-page","url":"https://hyperdrift.io/articles/webmcp-actions-on-the-page","title":"Stop making agents hunt for buttons","summary":"WebMCP lets a page expose actions to a browser agent. Radar shows how that can keep the person and agent working in the same place.","content_text":"WebMCP lets a page expose actions to a browser agent. Radar shows how that can keep the person and agent working in the same place.","date_published":"2026-10-06T00:00:00Z","date_modified":"2026-11-15T20:52:00.000Z","tags":["webmcp","mcp","ui"],"image":"https://hyperdrift.io/articles/orchestra/webmcp-direct-action-v1.jpg"},{"id":"https://orchestra.hyperdrift.io/articles/hands-free-app-control","url":"https://hyperdrift.io/articles/hands-free-app-control","title":"A spoken promise is not a completed action","summary":"A Cargo recovery request becomes an action, a checked result and a spoken report. What this bounded demonstration can teach app designers.","content_text":"A Cargo recovery request becomes an action, a checked result and a spoken report. What this bounded demonstration can teach app designers.","date_published":"2026-10-06T00:00:00Z","date_modified":"2026-11-15T21:15:44.000Z","tags":["voice","accessibility","ui"],"image":"https://hyperdrift.io/articles/orchestra/checked-voice-v1.jpg"},{"id":"https://orchestra.hyperdrift.io/articles/voice-through-mcp","url":"https://hyperdrift.io/articles/voice-through-mcp","title":"Say the job once. Keep control of the result.","summary":"Dictating to an assistant can become a way to direct connected tools. Our proposed experiment starts with a scoped read and a draft.","content_text":"Dictating to an assistant can become a way to direct connected tools. Our proposed experiment starts with a scoped read and a draft.","date_published":"2026-10-06T00:00:00Z","date_modified":"2026-11-15T21:15:44.000Z","tags":["voice","mcp","permissions"],"image":"https://hyperdrift.io/articles/orchestra/voice-across-apps-v1.jpg"},{"id":"https://orchestra.hyperdrift.io/articles/future-ui-keep-your-place","url":"https://hyperdrift.io/articles/future-ui-keep-your-place","title":"Your work should survive a change of interface","summary":"Speak, inspect, correct and continue. A future interface should preserve the task when the person changes how they interact.","content_text":"Speak, inspect, correct and continue. A future interface should preserve the task when the person changes how they interact.","date_published":"2026-10-06T00:00:00Z","date_modified":"2026-11-15T21:15:44.000Z","tags":["ui","accessibility","agents"],"image":"https://hyperdrift.io/articles/orchestra/keep-your-place-v1.jpg"},{"id":"https://orchestra.hyperdrift.io/articles/the-first-officer","url":"https://hyperdrift.io/articles/the-first-officer","title":"The dashboard that speaks first","summary":"In a recorded Cargo recovery, a spoken instruction starts the work. First Officer checks the response and reports back, with the evidence still on screen.","content_text":"In a recorded Cargo recovery, a spoken instruction starts the work. First Officer checks the response and reports back, with the evidence still on screen.","date_published":"2026-09-30T00:00:00Z","date_modified":"2026-11-15T21:15:44.000Z","tags":["voice","operations","ui"],"image":"https://hyperdrift.io/articles/orchestra/officer-v1.jpg"},{"id":"https://orchestra.hyperdrift.io/articles/lakebase-vs-document-databases","url":"https://hyperdrift.io/articles/lakebase-vs-document-databases","title":"Lakebase vs MongoDB and Cosmos DB: which approach fits?","summary":"Compare Lakebase’s Postgres approach with MongoDB and Cosmos DB document models: relationships, transactions, use cases and when Databricks integration matters.","content_text":"Compare Lakebase’s Postgres approach with MongoDB and Cosmos DB document models: relationships, transactions, use cases and when Databricks integration matters.","date_published":"2026-09-24T20:10:00Z","date_modified":"2026-11-15T21:15:44.000Z","tags":["databricks","databases"],"image":"https://hyperdrift.io/articles/orchestra/databases-v1.jpg"},{"id":"https://orchestra.hyperdrift.io/articles/langchain-databricks-appkit-sse","url":"https://hyperdrift.io/articles/langchain-databricks-appkit-sse","title":"LangChain vs Databricks AppKit for agent streaming","summary":"LangChain supplies agent updates; Databricks AppKit adds an integrated app server and agent host. Compare streaming, SSE, approval and recovery responsibilities.","content_text":"LangChain supplies agent updates; Databricks AppKit adds an integrated app server and agent host. Compare streaming, SSE, approval and recovery responsibilities.","date_published":"2026-09-24T20:10:00Z","date_modified":"2026-11-15T16:51:00.000Z","tags":["databricks","streaming"],"image":"https://hyperdrift.io/articles/orchestra/agent-streaming-builds-v1.jpg"},{"id":"https://orchestra.hyperdrift.io/articles/delegation-with-boundaries","url":"https://hyperdrift.io/articles/delegation-with-boundaries","title":"AI agent permissions: how much authority should you delegate?","summary":"Helm separates diagnosis from action and restricts disruptive operations to Cargo. Its completion-reporting gap shows why permissions and outcome checks need separate tests.","content_text":"Helm separates diagnosis from action and restricts disruptive operations to Cargo. Its completion-reporting gap shows why permissions and outcome checks need separate tests.","date_published":"2026-09-23T00:00:00Z","date_modified":"2026-11-15T20:52:00.000Z","tags":["agents","permissions"],"image":"https://hyperdrift.io/articles/orchestra/agent-permissions-v1.jpg"},{"id":"https://orchestra.hyperdrift.io/articles/evidence-that-starts-work","url":"https://hyperdrift.io/articles/evidence-that-starts-work","title":"AI daily briefs: turn activity into useful priorities","summary":"Standup puts people waiting for a maintainer before routine work. Its recorded output and later MCP checks show why each recommendation needs a source the reader can inspect.","content_text":"Standup puts people waiting for a maintainer before routine work. Its recorded output and later MCP checks show why each recommendation needs a source the reader can inspect.","date_published":"2026-09-23T00:00:00Z","date_modified":"2026-11-15T21:15:44.000Z","tags":["operations","agents"],"image":"https://hyperdrift.io/articles/orchestra/brief-v1.jpg"}]}