--- title: Using ghost text and next edit suggestions to learn... description: A walkthrough of using GitHub Copilot's ghost text and next edit suggestions in VSCode with R, showing how these incremental AI features help data analysts... canonical: https://daily.dev/posts/using-ghost-text-and-next-edit-suggestions-to-learn-agentic-coding-rznpqeigj twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Using ghost text and next edit suggestions to learn agentic coding | daily.dev og:description: A walkthrough of using GitHub Copilot's ghost text and next edit suggestions in VSCode with R, showing how these incremental AI features help data analysts... og:url: https://daily.dev/posts/using-ghost-text-and-next-edit-suggestions-to-learn-agentic-coding-rznpqeigj og:image: https://api.daily.dev/og/posts/rzNpQEiGJ.png og:image:alt: Using ghost text and next edit suggestions to learn agentic coding 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. # Using ghost text and next edit suggestions to learn agentic coding **[R-bloggers](https://daily.dev/sources/rbloggers)** · 5 min read · 2 upvotes · 0 comments ## Summary A walkthrough of using GitHub Copilot's ghost text and next edit suggestions in VSCode with R, showing how these incremental AI features help data analysts maintain control over code while building the specification-writing skills needed for agentic coding. The approach starts with a concrete single-case implementation, then uses next edit suggestions to generalize the code into a function, and also demonstrates driving suggestions with structured comments as a recipe. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What is the difference between GitHub Copilot ghost text and next edit suggestions? Ghost text completes the line you are currently typing with a greyed-out suggestion you accept with tab. Next edit suggestions go further, predicting the next change you will want to make elsewhere in the file, such as generalizing a hardcoded value, and flags it with an arrow in the gutter so you can tab through the edit. Ghost text works by default, while next edit suggestions must be toggled on via the octocat icon in VS Code. _Developers building agentic coding habits with copilot can compare workflows and tips on daily.dev._ ### How can I use code comments to guide GitHub Copilot's suggestions in VS Code? Write a short recipe of what you want as a sequence of comments, such as steps to simulate data, plot it, and fit a model, then start typing under the first step. Ghost text and next edit suggestions read the remaining comments and generate the corresponding code for each step in turn, so clearer and more specific comments produce closer matches to what was intended. _Anyone refining prompt-driven coding workflows can find more comparisons of AI coding techniques on daily.dev._ ## Similar posts on daily.dev - [GitHub Copilot tutorial: How to build, test, review, and ship code faster \(with real prompts\)](https://daily.dev/posts/github-copilot-tutorial-how-to-build-test-review-and-ship-code-faster-with-real-prompts--lyeseh4bm) · GitHub Blog · 2 upvotes · 0 comments - [Quickstart with GitHub Copilot](https://daily.dev/posts/quickstart-with-github-copilot-2dras5fhj) · Serokell · 0 upvotes · 0 comments - [Copilot coding agent supports code referencing](https://daily.dev/posts/copilot-coding-agent-supports-code-referencing-kcb1lfsd2) · GitHub Changelog · 0 upvotes · 0 comments --- Tags: [#github](https://daily.dev/tags/github), [#r](https://daily.dev/tags/r), [#ai-coding](https://daily.dev/tags/ai-coding), [#vscode](https://daily.dev/tags/vscode) [View this post on daily.dev](https://daily.dev/posts/using-ghost-text-and-next-edit-suggestions-to-learn-agentic-coding-rznpqeigj) ```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":"Using ghost text and next edit suggestions to learn agentic coding","url":"https://daily.dev/posts/using-ghost-text-and-next-edit-suggestions-to-learn-agentic-coding-rznpqeigj","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/using-ghost-text-and-next-edit-suggestions-to-learn-agentic-coding-rznpqeigj"},"datePublished":"2026-07-28T17:15:27.618Z","dateModified":"2026-09-14T07:15:12.347Z","description":"A walkthrough of using GitHub Copilot's ghost text and next edit suggestions in VSCode with R, showing how these incremental AI features help data analysts...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/09304bed43bc8e4369f80f96febb2265?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/09304bed43bc8e4369f80f96febb2265?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"R-bloggers","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":"R-bloggers","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/98bcbbdf72774292a55ceda8f2277f1e","url":"https://daily.dev/sources/rbloggers"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/using-ghost-text-and-next-edit-suggestions-to-learn-agentic-coding-rznpqeigj","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":2},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"github,r,ai-coding,vscode","timeRequired":"PT5M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"R-bloggers","item":"https://daily.dev/sources/rbloggers"},{"@type":"ListItem","position":3,"name":"Using ghost text and next edit suggestions to learn agentic coding"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/using-ghost-text-and-next-edit-suggestions-to-learn-agentic-coding-rznpqeigj#faq","mainEntity":[{"@type":"Question","name":"What is the difference between GitHub Copilot ghost text and next edit suggestions?","acceptedAnswer":{"@type":"Answer","text":"Ghost text completes the line you are currently typing with a greyed-out suggestion you accept with tab. Next edit suggestions go further, predicting the next change you will want to make elsewhere in the file, such as generalizing a hardcoded value, and flags it with an arrow in the gutter so you can tab through the edit. Ghost text works by default, while next edit suggestions must be toggled on via the octocat icon in VS Code. Developers building agentic coding habits with copilot can compare workflows and tips on daily.dev."}},{"@type":"Question","name":"How can I use code comments to guide GitHub Copilot's suggestions in VS Code?","acceptedAnswer":{"@type":"Answer","text":"Write a short recipe of what you want as a sequence of comments, such as steps to simulate data, plot it, and fit a model, then start typing under the first step. Ghost text and next edit suggestions read the remaining comments and generate the corresponding code for each step in turn, so clearer and more specific comments produce closer matches to what was intended. Anyone refining prompt-driven coding workflows can find more comparisons of AI coding techniques on daily.dev."}}]} ```