--- title: Terminal or Terminate? | daily.dev description: Agents work 'subsurface' with APIs and CLIs, while humans need a 'surface' level for seeing, comparing and deciding, the author argues. He uses a hospital... canonical: https://daily.dev/posts/terminal-or-terminate--i3d4bsopr twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Terminal or Terminate? | daily.dev og:description: Agents work 'subsurface' with APIs and CLIs, while humans need a 'surface' level for seeing, comparing and deciding, the author argues. He uses a hospital... og:url: https://daily.dev/posts/terminal-or-terminate--i3d4bsopr og:image: https://api.daily.dev/og/posts/i3d4BSoPR.png og:image:alt: Terminal or Terminate? og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Terminal or Terminate? **[Telerik](https://daily.dev/sources/telerik)** · 5 min read · 0 upvotes · 0 comments ## Summary Agents work 'subsurface' with APIs and CLIs, while humans need a 'surface' level for seeing, comparing and deciding, the author argues. He uses a hospital scenario where a new med-tech app lets a doctor talk to twice as many patients but removes her patient chart, so she has two conversations at once. In the first quarter of 2026, six repositories wrapping GUIs in agent-friendly CLIs each crossed 4,000 stars within days. Software without an API, MCP server or CLI becomes 'effectively invisible' to agents. The piece compares chatbots unfavorably to automatic transmissions, which took nearly two decades to become the main type of transmission. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### Why do chatbots feel confusing even though they seem powerful at first glance Chatbots often fail to indicate what they can do, unlike a car's P/R/N/D shifter which shows exactly what the system will do. Without that clarity, users end up negotiating with the machine for several sessions about what they actually meant, often needing prompt training or MCP know-how before the tool behaves as intended. _Developers designing agent interfaces compare approaches to visible system states on daily.dev._ ### What happened when six repositories added agent-friendly CLI wrappers to existing GUIs in early 2026 Six major repositories launched ways to wrap an existing GUI in a structured CLI that agents can use, and all six crossed 4,000 GitHub stars within days. This reflects a broader shift where software without a proper API, MCP server, or CLI becomes effectively invisible in agentic workflows. _Teams deciding whether to add an agent-facing CLI follow adoption signals like this on daily.dev._ ## Similar posts on daily.dev - [Agentic Terminal - How Your Terminal Comes Alive with CLI Agents](https://daily.dev/posts/agentic-terminal---how-your-terminal-comes-alive-with-cli-agents-ygueyoqlj) · InfoQ · 1 upvotes · 0 comments - [I stopped using GUI tools after switching to CLI agents, and I’m not going back](https://daily.dev/posts/i-stopped-using-gui-tools-after-switching-to-cli-agents-and-i-m-not-going-back-ugjsoyxzd) · XDA Developers · 1 upvotes · 0 comments - [AI has made the CLI more important and powerful](https://daily.dev/posts/ai-has-made-the-cli-more-important-and-powerful-ecb25bhyr) · The Register · 1 upvotes · 0 comments - [The IDE Is Losing to the Terminal — Coding Agents Made the Difference](https://daily.dev/posts/the-ide-is-losing-to-the-terminal-coding-agents-made-the-difference-4wqtpmdct) · Medium · 3 upvotes · 0 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#ux](https://daily.dev/tags/ux), [#cli](https://daily.dev/tags/cli), [#mcp](https://daily.dev/tags/mcp), [#human-computer-interaction](https://daily.dev/tags/human-computer-interaction) [View this post on daily.dev](https://daily.dev/posts/terminal-or-terminate--i3d4bsopr) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Terminal or Terminate?","url":"https://daily.dev/posts/terminal-or-terminate--i3d4bsopr","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/terminal-or-terminate--i3d4bsopr"},"datePublished":"2026-10-27T15:33:23.269Z","dateModified":"2026-10-27T15:35:21.241Z","description":"Agents work 'subsurface' with APIs and CLIs, while humans need a 'surface' level for seeing, comparing and deciding, the author argues. He uses a hospital...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/78015fefe65dd0fecae9b04599d6353f?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/78015fefe65dd0fecae9b04599d6353f?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Telerik","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Telerik","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/5ee6d4bef8ac4f84886d06f5881963e7","url":"https://daily.dev/sources/telerik"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/terminal-or-terminate--i3d4bsopr","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,ux,cli,mcp,human-computer-interaction","timeRequired":"PT5M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Telerik","item":"https://daily.dev/sources/telerik"},{"@type":"ListItem","position":3,"name":"Terminal or Terminate?"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/terminal-or-terminate--i3d4bsopr#faq","mainEntity":[{"@type":"Question","name":"Why do chatbots feel confusing even though they seem powerful at first glance","acceptedAnswer":{"@type":"Answer","text":"Chatbots often fail to indicate what they can do, unlike a car's P/R/N/D shifter which shows exactly what the system will do. Without that clarity, users end up negotiating with the machine for several sessions about what they actually meant, often needing prompt training or MCP know-how before the tool behaves as intended. Developers designing agent interfaces compare approaches to visible system states on daily.dev."}},{"@type":"Question","name":"What happened when six repositories added agent-friendly CLI wrappers to existing GUIs in early 2026","acceptedAnswer":{"@type":"Answer","text":"Six major repositories launched ways to wrap an existing GUI in a structured CLI that agents can use, and all six crossed 4,000 GitHub stars within days. This reflects a broader shift where software without a proper API, MCP server, or CLI becomes effectively invisible in agentic workflows. Teams deciding whether to add an agent-facing CLI follow adoption signals like this on daily.dev."}}]} ```