{"slug": "augment", "name": "Augment", "category": "ai-coding", "category_name": "AI coding tools", "description": "", "recommenders": 3, "commenters": 6, "warners": 0, "score": 3.328, "rising": -0.98, "first": "2025-11-05", "latest": "2026-06-12", "why": "Augment kind of became impossible to avoid once we realized the new guy is outpacing the rest of us", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 3, "neutral": 3, "compare": 0, "warn": 0}, "spark": [0, 0, 1, 0, 2, 0, 0, 0, 0, 0, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "Augment kind of became impossible to avoid once we realized the new guy is outpacing the rest of us", "icon": true, "domain": null, "github_repo": null, "official_url": "https://www.augmentcode.com", "pricing": "", "aliases": ["Augment", "Augment Code"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 758654080, "item_id": 47415880, "url": "https://news.ycombinator.com/item?id=47415880", "by": "nassimm", "date": "2026-03-17", "stance": "recommend", "quote": "I use Augment and Intent with Opus 4.6", "excerpt": "It works well for me. I wouldn't have said that about 3 or 4 months ago but now it does work. How well it works seems to be highly project-dependant, my friends have much more trouble to get usable things out of LLMs. The projects I work on are relatively small, two frontend with about 30k loc and a middleware with about 50k loc. All project were started with no llms and were pretty clean. I use Augment and Intent wi", "context": "Frontend developer for 12 years, team of 2", "use_case": "AI-assisted coding", "switched_from": "", "story": "Ask HN: How is AI-assisted coding going for you professionally?"}, {"id": 758277808, "item_id": 47392363, "url": "https://news.ycombinator.com/item?id=47392363", "by": "parasti", "date": "2026-03-15", "stance": "recommend", "quote": "Augment kind of became impossible to avoid once we realized the new guy is outpacing the rest of us", "excerpt": "We're using Augment Code heavily on a \"full rewrite of legacy CRM with 30 years of business rules/data\" Laravel project with a team size of 4. Augment kind of became impossible to avoid once we realized the new guy is outpacing the rest of us while posessing almost no knowledge of code and working fully in the business requirements domain, extracting requirements from the customer and passing them to AI, which was en", "context": "team of 4 rewriting a legacy CRM", "use_case": "legacy CRM rewrite", "switched_from": "", "story": "Ask HN: How is AI-assisted coding going for you professionally?"}, {"id": 747204384, "item_id": 46700274, "url": "https://news.ycombinator.com/item?id=46700274", "by": "defatigable", "date": "2026-01-20", "stance": "recommend", "quote": "I use Augment with Claud Opus 4.5 every day at my job.", "excerpt": "I use Augment with Claud Opus 4.5 every day at my job. I barely ever write code by hand anymore. I don't blindly accept the code that it writes, I iterate with it. We review code at my work. I have absolutely found a lot of benefit from my tools. I've implemented several medium-scale projects that I anticipate would have taken 1-2 weeks manually, and took a day or so using agentic tools. A few very concrete advantage", "context": "", "use_case": "agentic coding at work", "switched_from": "", "story": "Ask HN: Do you have any evidence that agentic coding works?"}]}], "caveats": [], "who": [{"by": "nassimm", "context": "Frontend developer for 12 years, team of 2", "url": "https://news.ycombinator.com/item?id=47415880", "date": "2026-03-17"}, {"by": "parasti", "context": "team of 4 rewriting a legacy CRM", "url": "https://news.ycombinator.com/item?id=47392363", "date": "2026-03-15"}], "tags": [], "use_cases": ["ai coding", "porting notepad++ to macos", "ai-assisted coding", "legacy crm rewrite", "agentic coding at work"], "compared": [{"slug": "antigravity", "name": "Antigravity", "co": 2, "switched_from": 0, "switched_to": 1}, {"slug": "claude-opus", "name": "Claude Opus", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "claude-sonnet", "name": "Claude Sonnet", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "gpt-5", "name": "GPT-5", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=47388646", "title": "Ask HN: How is AI-assisted coding going for you professionally?", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=48496539", "title": "Show HN: FablePool \u2013 pool money behind a prompt, and Fable builds it in public", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=46691243", "title": "Ask HN: Do you have any evidence that agentic coding works?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=46528389", "title": "Google Got Its Groove Back and Edged Ahead of OpenAI", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=45749833", "title": "Developers are choosing older AI models", "mentions": 1}], "sentiment_by_month": {"2025-11": {"neutral": 1}, "2025-12": {}, "2026-01": {"neutral": 1, "recommend": 1}, "2026-02": {}, "2026-03": {"recommend": 2}, "2026-04": {}, "2026-05": {}, "2026-06": {"neutral": 1}, "2026-07": {}, "2026-08": {}, "2026-09": {}, "2026-10": {}}, "quotes": [{"id": 776160192, "item_id": 48510012, "url": "https://news.ycombinator.com/item?id=48510012", "by": "philluminati", "date": "2026-06-12", "stance": "neutral", "quote": "I copy and pasted your prompt into Augment (Opus 4.7) and told it to do everything you wanted", "excerpt": "Whoever posted the request for Notepad++ on MacOS... ... I was feeling generous, so here you go! https://github.com/PhillipTaylor/notepad_plus_plus_mac_os I copy and pasted your prompt into Augment (Opus 4.7) and told it to do everything you wanted, then I told it to keeping going afterwards. I think there are a few missing pieces as it's quite a open-ended piece of work. This took 59,000 tokens.", "context": "", "use_case": "porting Notepad++ to macOS", "switched_from": "", "story": "Show HN: FablePool \u2013 pool money behind a prompt, and Fable builds it in public"}, {"id": 758654080, "item_id": 47415880, "url": "https://news.ycombinator.com/item?id=47415880", "by": "nassimm", "date": "2026-03-17", "stance": "recommend", "quote": "I use Augment and Intent with Opus 4.6", "excerpt": "It works well for me. I wouldn't have said that about 3 or 4 months ago but now it does work. How well it works seems to be highly project-dependant, my friends have much more trouble to get usable things out of LLMs. The projects I work on are relatively small, two frontend with about 30k loc and a middleware with about 50k loc. All project were started with no llms and were pretty clean. I use Augment and Intent wi", "context": "Frontend developer for 12 years, team of 2", "use_case": "AI-assisted coding", "switched_from": "", "story": "Ask HN: How is AI-assisted coding going for you professionally?"}, {"id": 758277808, "item_id": 47392363, "url": "https://news.ycombinator.com/item?id=47392363", "by": "parasti", "date": "2026-03-15", "stance": "recommend", "quote": "Augment kind of became impossible to avoid once we realized the new guy is outpacing the rest of us", "excerpt": "We're using Augment Code heavily on a \"full rewrite of legacy CRM with 30 years of business rules/data\" Laravel project with a team size of 4. Augment kind of became impossible to avoid once we realized the new guy is outpacing the rest of us while posessing almost no knowledge of code and working fully in the business requirements domain, extracting requirements from the customer and passing them to AI, which was en", "context": "team of 4 rewriting a legacy CRM", "use_case": "legacy CRM rewrite", "switched_from": "", "story": "Ask HN: How is AI-assisted coding going for you professionally?"}, {"id": 747204384, "item_id": 46700274, "url": "https://news.ycombinator.com/item?id=46700274", "by": "defatigable", "date": "2026-01-20", "stance": "recommend", "quote": "I use Augment with Claud Opus 4.5 every day at my job.", "excerpt": "I use Augment with Claud Opus 4.5 every day at my job. I barely ever write code by hand anymore. I don't blindly accept the code that it writes, I iterate with it. We review code at my work. I have absolutely found a lot of benefit from my tools. I've implemented several medium-scale projects that I anticipate would have taken 1-2 weeks manually, and took a day or so using agentic tools. A few very concrete advantage", "context": "", "use_case": "agentic coding at work", "switched_from": "", "story": "Ask HN: Do you have any evidence that agentic coding works?"}, {"id": 744604515, "item_id": 46537782, "url": "https://news.ycombinator.com/item?id=46537782", "by": "mythz", "date": "2026-01-07", "stance": "neutral", "quote": "after leaving Augment Code", "excerpt": "Gemini CLI is too slow to be useful, kind of surprised it was even offered and marketed given how painful it is to use. I thought it'd have to be damaging to the Gemini brand to get people to try it out, suffer painful UX then immediately stop using it. (Using it from Australia may also contribute to its slow perf) Antigravity was also painful to use at launch where more queries failed then succeeded, however they've", "context": "", "use_case": "AI coding", "switched_from": "", "story": "Google Got Its Groove Back and Edged Ahead of OpenAI"}, {"id": 733159442, "item_id": 45822465, "url": "https://news.ycombinator.com/item?id=45822465", "by": "feintruled", "date": "2025-11-05", "stance": "neutral", "quote": "Augment code has recently switched to a per-token instead of per-message pricing model. This hasn't gone down particularly well", "excerpt": "Some missing context (pun intended) is that Augment code has recently switched to a per-token instead of per-message pricing model. This hasn't gone down particularly well, but that's another story. But it may well be that users drop back to older models in the expectation it will use less tokens. Personally, I stopped using GPT-5 as it would just be tool call after tool call without ever stopping to tell you what th", "context": "", "use_case": "AI coding", "switched_from": "", "story": "Developers are choosing older AI models"}]}