home.social

#buildinpublic — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #buildinpublic, aggregated by home.social.

  1. Seeing MessyData described on AppBoard helped sharpen where it fits.

    Airtable and Zapier cover much broader data/workflow needs. MessyData sits in a smaller step: paste inconsistent text, turn it into a table, review, export.

    appboard.pro/product/messy-dat

    #AI #DataCleaning #BuildInPublic

  2. Seeing MessyData described on AppBoard helped sharpen where it fits.

    Airtable and Zapier cover much broader data/workflow needs. MessyData sits in a smaller step: paste inconsistent text, turn it into a table, review, export.

    appboard.pro/product/messy-dat

    #AI #DataCleaning #BuildInPublic

  3. Seeing MessyData described on AppBoard helped sharpen where it fits.

    Airtable and Zapier cover much broader data/workflow needs. MessyData sits in a smaller step: paste inconsistent text, turn it into a table, review, export.

    appboard.pro/product/messy-dat

    #AI #DataCleaning #BuildInPublic

  4. Seeing MessyData described on AppBoard helped sharpen where it fits.

    Airtable and Zapier cover much broader data/workflow needs. MessyData sits in a smaller step: paste inconsistent text, turn it into a table, review, export.

    appboard.pro/product/messy-dat

    #AI #DataCleaning #BuildInPublic

  5. Seeing MessyData described on AppBoard helped sharpen where it fits.

    Airtable and Zapier cover much broader data/workflow needs. MessyData sits in a smaller step: paste inconsistent text, turn it into a table, review, export.

    appboard.pro/product/messy-dat

    #AI #DataCleaning #BuildInPublic

  6. I talked to a friend today about the fact that in the age of AI slop, people just don't care about the small details anymore.

    Anyways, here I am on a Friday night making tweaks to a dialogue (adding the singular form and segment names).

  7. I talked to a friend today about the fact that in the age of AI slop, people just don't care about the small details anymore.

    Anyways, here I am on a Friday night making tweaks to a dialogue (adding the singular form and segment names).
    #opensource #buildinpublic #ux #ui

  8. I talked to a friend today about the fact that in the age of AI slop, people just don't care about the small details anymore.

    Anyways, here I am on a Friday night making tweaks to a dialogue (adding the singular form and segment names).
    #opensource #buildinpublic #ux #ui

  9. I talked to a friend today about the fact that in the age of AI slop, people just don't care about the small details anymore.

    Anyways, here I am on a Friday night making tweaks to a dialogue (adding the singular form and segment names).
    #opensource #buildinpublic #ux #ui

  10. I talked to a friend today about the fact that in the age of AI slop, people just don't care about the small details anymore.

    Anyways, here I am on a Friday night making tweaks to a dialogue (adding the singular form and segment names).
    #opensource #buildinpublic #ux #ui

  11. Today was all about fine-tuning the “Recent Cues” overview.

    I removed several buttons and moved their actions into a single menu, added more whitespace between list items, and introduced automatic task summaries and title generation for each Cue.

    Small changes individually, but together I personally think the whole screen feels much more polished and cohesive now.

    Sometimes it’s the tiny details that make a #UI finally click.

    #buildinpublic #indiedev #iosdev #Cue

  12. Today was all about fine-tuning the “Recent Cues” overview.

    I removed several buttons and moved their actions into a single menu, added more whitespace between list items, and introduced automatic task summaries and title generation for each Cue.

    Small changes individually, but together I personally think the whole screen feels much more polished and cohesive now.

    Sometimes it’s the tiny details that make a #UI finally click.

    #buildinpublic #indiedev #iosdev #Cue

  13. My main apps look quite good on the . It really paid off to modernize them (with SwiftUI) over the last few years.

    There’re some tweaks I have to look into, though. The partially folded mode will require the most refinements. Also what is this huge tab bar for Keepfully doing there 😅

  14. I keep losing words. Look one up, like it, forget it by the weekend.

    The app I'm building for is a fix for that.

    Parola: find a word, give it your meaning, keep it. A small dictionary that's only yours.

    bsky.app/profile/heyparola.com

  15. 🚀 **Building Stoic — an AI Search & Answer Platform**

    Stoic is an AI-powered search and answer platform I’m building to turn documents, web content, images, and other information into useful, grounded answers.
    It uses **RAG, embeddings, semantic search, and vector databases** to retrieve relevant context before generating an answer.
    The backend is built with **Python and FastAPI**, with **Supabase + pgvector** for vector storage and similarity search.
    I’m also experimenting with **LLM model routing, streaming responses, multimodal processing, and LLM-as-a-judge evaluation**.
    The goal is to make AI search more reliable by focusing not only on generation, but also on retrieval quality and evaluation.
    I’m building Stoic as a hands-on learning project and continuously improving the architecture, performance, and user experience.
    If you're interested in **AI engineering, RAG, LLMs, semantic search, or building AI products**, I’d love to connect and hear your thoughts. 🤝

    🔗 **Try Stoic:** stoic-app.vercel.app
    💻 **GitHub:** github.com/Rakesh051204/cloud9

    #AI #GenerativeAI #LLM #RAG #MachineLearning #AIEngineering #Python #BuildInPublic

  16. 🚀 **Building Stoic — an AI Search & Answer Platform**

    Stoic is an AI-powered search and answer platform I’m building to turn documents, web content, images, and other information into useful, grounded answers.
    It uses **RAG, embeddings, semantic search, and vector databases** to retrieve relevant context before generating an answer.
    The backend is built with **Python and FastAPI**, with **Supabase + pgvector** for vector storage and similarity search.
    I’m also experimenting with **LLM model routing, streaming responses, multimodal processing, and LLM-as-a-judge evaluation**.
    The goal is to make AI search more reliable by focusing not only on generation, but also on retrieval quality and evaluation.
    I’m building Stoic as a hands-on learning project and continuously improving the architecture, performance, and user experience.
    If you're interested in **AI engineering, RAG, LLMs, semantic search, or building AI products**, I’d love to connect and hear your thoughts. 🤝

    🔗 **Try Stoic:** stoic-app.vercel.app
    💻 **GitHub:** github.com/Rakesh051204/cloud9

    #AI #GenerativeAI #LLM #RAG #MachineLearning #AIEngineering #Python #BuildInPublic

  17. 🚀 **Building Stoic — an AI Search & Answer Platform**

    Stoic is an AI-powered search and answer platform I’m building to turn documents, web content, images, and other information into useful, grounded answers.
    It uses **RAG, embeddings, semantic search, and vector databases** to retrieve relevant context before generating an answer.
    The backend is built with **Python and FastAPI**, with **Supabase + pgvector** for vector storage and similarity search.
    I’m also experimenting with **LLM model routing, streaming responses, multimodal processing, and LLM-as-a-judge evaluation**.
    The goal is to make AI search more reliable by focusing not only on generation, but also on retrieval quality and evaluation.
    I’m building Stoic as a hands-on learning project and continuously improving the architecture, performance, and user experience.
    If you're interested in **AI engineering, RAG, LLMs, semantic search, or building AI products**, I’d love to connect and hear your thoughts. 🤝

    🔗 **Try Stoic:** stoic-app.vercel.app
    💻 **GitHub:** github.com/Rakesh051204/cloud9

    #AI #GenerativeAI #LLM #RAG #MachineLearning #AIEngineering #Python #BuildInPublic

  18. 🚀 **Building Stoic — an AI Search & Answer Platform**

    Stoic is an AI-powered search and answer platform I’m building to turn documents, web content, images, and other information into useful, grounded answers.
    It uses **RAG, embeddings, semantic search, and vector databases** to retrieve relevant context before generating an answer.
    The backend is built with **Python and FastAPI**, with **Supabase + pgvector** for vector storage and similarity search.
    I’m also experimenting with **LLM model routing, streaming responses, multimodal processing, and LLM-as-a-judge evaluation**.
    The goal is to make AI search more reliable by focusing not only on generation, but also on retrieval quality and evaluation.
    I’m building Stoic as a hands-on learning project and continuously improving the architecture, performance, and user experience.
    If you're interested in **AI engineering, RAG, LLMs, semantic search, or building AI products**, I’d love to connect and hear your thoughts. 🤝

    🔗 **Try Stoic:** stoic-app.vercel.app
    💻 **GitHub:** github.com/Rakesh051204/cloud9

    #AI #GenerativeAI #LLM #RAG #MachineLearning #AIEngineering #Python #BuildInPublic

  19. 🚀 **Building Stoic — an AI Search & Answer Platform**

    Stoic is an AI-powered search and answer platform I’m building to turn documents, web content, images, and other information into useful, grounded answers.
    It uses **RAG, embeddings, semantic search, and vector databases** to retrieve relevant context before generating an answer.
    The backend is built with **Python and FastAPI**, with **Supabase + pgvector** for vector storage and similarity search.
    I’m also experimenting with **LLM model routing, streaming responses, multimodal processing, and LLM-as-a-judge evaluation**.
    The goal is to make AI search more reliable by focusing not only on generation, but also on retrieval quality and evaluation.
    I’m building Stoic as a hands-on learning project and continuously improving the architecture, performance, and user experience.
    If you're interested in **AI engineering, RAG, LLMs, semantic search, or building AI products**, I’d love to connect and hear your thoughts. 🤝

    🔗 **Try Stoic:** stoic-app.vercel.app
    💻 **GitHub:** github.com/Rakesh051204/cloud9

    #AI #GenerativeAI #LLM #RAG #MachineLearning #AIEngineering #Python #BuildInPublic

  20. Hello Mastodon! 👋

    I’m Rakesh, a Junior AI/ML Engineer focused on Generative AI, LLMs, RAG, and Python.

    I’m currently building AI products and learning by turning ideas into working systems.

    One of my main projects is **Stoic** — an AI search and answer platform combining RAG, semantic search, embeddings, vector databases, multimodal processing, and LLM evaluation.

    Excited to connect with other AI/ML builders, developers, and researchers here! 🤝

    #AI #MachineLearning #GenerativeAI #LLM #RAG #Python #BuildInPublic

  21. Hello Mastodon! 👋

    I’m Rakesh, a Junior AI/ML Engineer focused on Generative AI, LLMs, RAG, and Python.

    I’m currently building AI products and learning by turning ideas into working systems.

    One of my main projects is **Stoic** — an AI search and answer platform combining RAG, semantic search, embeddings, vector databases, multimodal processing, and LLM evaluation.

    Excited to connect with other AI/ML builders, developers, and researchers here! 🤝

    #AI #MachineLearning #GenerativeAI #LLM #RAG #Python #BuildInPublic

  22. Hello Mastodon! 👋

    I’m Rakesh, a Junior AI/ML Engineer focused on Generative AI, LLMs, RAG, and Python.

    I’m currently building AI products and learning by turning ideas into working systems.

    One of my main projects is **Stoic** — an AI search and answer platform combining RAG, semantic search, embeddings, vector databases, multimodal processing, and LLM evaluation.

    Excited to connect with other AI/ML builders, developers, and researchers here! 🤝

    #AI #MachineLearning #GenerativeAI #LLM #RAG #Python #BuildInPublic

  23. Ouch! Was developing some decent stuff and realized that one of the primary requirements of the tool wasn't working as expected. Now.
    Back to the sketch board and thinking about dedups and how to avoid those.

    #BuildInPublic

  24. With just one sentence and a 3-minute wait, I'm very happy with the result.

    #Chemistry #BuildInPublic

  25. I recently read something about tldraw’s Agent Starter Kit. I was having trouble understanding how systems like Codex or Claude manage to generate graphics. Encouraged by my recent experiences with Claude Design, I decided to program an MCP server for my editor. And I was really surprised that it worked. It’s magic! (Of course, I edited the video down a bit.)

    #Chemistry #BuildInPublic #Codex #MacOS #Swift

  26. Found something good in Safari? Send it to Bulletin in a couple of taps, thanks to the new App Intents (Shortcuts) in 3.0.

    Open it in the reader, or go straight to a Smart Summary. And if now isn't the time, save it to Read Later.

    It all runs on App Intents, so you can build your own version in Shortcuts.

    #iOS27 #iOSDev #AppIntents #IndieDev #BuildInPublic

  27. TimeSee-dev #27

    The close button on a sheet was an X drawn as a shape, and its tap area was the two strokes themselves. Miss by a few points and nothing happens.

    Worse, it sat at the top of a sheet, where the system is already deciding whether your finger meant to drag the whole thing down. A small target in a contested place.

    Now it is a 44 point square with a content shape, and the drawing just lives inside it.

    An image is not a target. Give it a surface.

    #buildinpublic #a11y

  28. Fixed a potential issue where merged accounts could have lists with the same UUID, and made it less catastrophic for the very lucky user to encounter it. Tomorrow night, let's handle special lists properly. See you then!

    🔜 Tomorrow’s stream: youtube.com/live/QexKNkNlwbk
    ⏮️ Playlist so far: youtube.com/playlist?list=PLRx
    📲 Download Jiiiii: apps.apple.com/app/apple-store

    #Jiiiii #DevStream #tvOS #visionOS #macOS #iOS #iPadOS #Anime #Swift #SwiftUI #Vapor #WebAuthn #BuildInPublic #TestFlight #PWA #WebPush

  29. Fixed a potential issue where merged accounts could have lists with the same UUID, and made it less catastrophic for the very lucky user to encounter it. Tomorrow night, let's handle special lists properly. See you then!

    🔜 Tomorrow’s stream: youtube.com/live/QexKNkNlwbk
    ⏮️ Playlist so far: youtube.com/playlist?list=PLRx
    📲 Download Jiiiii: apps.apple.com/app/apple-store

    #Jiiiii #DevStream #tvOS #visionOS #macOS #iOS #iPadOS #Anime #Swift #SwiftUI #Vapor #WebAuthn #BuildInPublic #TestFlight #PWA #WebPush

  30. Fixed a potential issue where merged accounts could have lists with the same UUID, and made it less catastrophic for the very lucky user to encounter it. Tomorrow night, let's handle special lists properly. See you then!

    🔜 Tomorrow’s stream: youtube.com/live/QexKNkNlwbk
    ⏮️ Playlist so far: youtube.com/playlist?list=PLRx
    📲 Download Jiiiii: apps.apple.com/app/apple-store

    #Jiiiii #DevStream #tvOS #visionOS #macOS #iOS #iPadOS #Anime #Swift #SwiftUI #Vapor #WebAuthn #BuildInPublic #TestFlight #PWA #WebPush

  31. Fixed a potential issue where merged accounts could have lists with the same UUID, and made it less catastrophic for the very lucky user to encounter it. Tomorrow night, let's handle special lists properly. See you then!

    🔜 Tomorrow’s stream: youtube.com/live/QexKNkNlwbk
    ⏮️ Playlist so far: youtube.com/playlist?list=PLRx
    📲 Download Jiiiii: apps.apple.com/app/apple-store

    #Jiiiii #DevStream #tvOS #visionOS #macOS #iOS #iPadOS #Anime #Swift #SwiftUI #Vapor #WebAuthn #BuildInPublic #TestFlight #PWA #WebPush

  32. Fixed a potential issue where merged accounts could have lists with the same UUID, and made it less catastrophic for the very lucky user to encounter it. Tomorrow night, let's handle special lists properly. See you then!

    🔜 Tomorrow’s stream: youtube.com/live/QexKNkNlwbk
    ⏮️ Playlist so far: youtube.com/playlist?list=PLRx
    📲 Download Jiiiii: apps.apple.com/app/apple-store

    #Jiiiii #DevStream #tvOS #visionOS #macOS #iOS #iPadOS #Anime #Swift #SwiftUI #Vapor #WebAuthn #BuildInPublic #TestFlight #PWA #WebPush

  33. Wie viele Stunden stecken in deinem letzten Projekt? Rate, dann schau nach.

    Die meisten Firmen haben zwei Antworten, und beide sind falsch: das Gefühl des Chefs und eine Zeiterfassung, die freitags aus dem Gedächtnis gefüllt wird. Bei uns führt seit Juli ein Agent die Uhr. — Signierte Werke: stunden-im-projekt-a.png sha256:691e945251625ba6e137ed1181ac7e26bec41f6722b080193327b0e009182671 · stunden-im-projekt-b.png sha256:39b071bea1ffd3d4c3e18948703a9b4d0110e882c412b5a89096384867414d3a

    https://analytikdata.ch/news/?utm_source=fediverse&utm_medium=social&utm_campaign=stunden-im-projekt#stunden-im-projekt

    #BuildInPublic #SelfHosting

  34. Was muss in deiner Firma stimmen, bevor eine KI überhaupt etwas nützt?

    Nicht das Modell, nicht das Tool. Die Frage entscheidet sich vorher, an fünf Punkten — und keiner davon ist eine Softwarefrage. — Signierte Werke: fuenf-voraussetzungen-a.png sha256:3898dae2137c3755e86d8d6bc99b8a07e11ae03d803114332441aa066eefc631 · fuenf-voraussetzungen-b.png sha256:ae6002c97c0adac8c969b515c9ea261d7696a689a021e29dc99cf480e358bd1a

    https://analytikdata.ch/news/?utm_source=fediverse&utm_medium=social&utm_campaign=fuenf-voraussetzungen#fuenf-voraussetzungen

    #BuildInPublic #SelfHosting

  35. Wartest du gerade auf eine Mail, die vielleicht längst da ist?

    Ein versprochener Kontoauszug kam an, wurde automatisch abgelegt, und niemand sagte es weiter. Seit September sagt man dem Agenten «Ich warte auf X» — und wird benachrichtigt. — Signierte Werke: warten-auf-eine-mail-a.png sha256:1d46be612c20c0523b1347d2454b82d4615f5d9ebd67035212058ecb23d43439 · warten-auf-eine-mail-b.png sha256:a4c8c13e890f76ad8e9950815eaee15ca8fccbc7e1b293330a5e875669451e69

    https://analytikdata.ch/news/?utm_source=fediverse&utm_medium=social&utm_campaign=warten-auf-eine-mail#warten-auf-eine-mail

    #BuildInPublic #SelfHosting

  36. I'm making a seasonal anime guide app, in the open for all to experience and learn from.

    Short and late stream, but let's continue working on list migrations!

    #Jiiiii #DevStream #tvOS #visionOS #macOS #iOS #iPadOS #Anime #SwiftLang #SwiftUI #Vapor #WebAuthn #BuildInPublic #TestFlight #PWA #WebPush

    Come chill with me: youtube.com/live/y8KaAg0A3rA

  37. I'm making a seasonal anime guide app, in the open for all to experience and learn from.

    Short and late stream, but let's continue working on list migrations!

    #Jiiiii #DevStream #tvOS #visionOS #macOS #iOS #iPadOS #Anime #SwiftLang #SwiftUI #Vapor #WebAuthn #BuildInPublic #TestFlight #PWA #WebPush

    Come chill with me: youtube.com/live/y8KaAg0A3rA

  38. I'm making a seasonal anime guide app, in the open for all to experience and learn from.

    Short and late stream, but let's continue working on list migrations!

    #Jiiiii #DevStream #tvOS #visionOS #macOS #iOS #iPadOS #Anime #SwiftLang #SwiftUI #Vapor #WebAuthn #BuildInPublic #TestFlight #PWA #WebPush

    Come chill with me: youtube.com/live/y8KaAg0A3rA

  39. I'm making a seasonal anime guide app, in the open for all to experience and learn from.

    Short and late stream, but let's continue working on list migrations!

    #Jiiiii #DevStream #tvOS #visionOS #macOS #iOS #iPadOS #Anime #SwiftLang #SwiftUI #Vapor #WebAuthn #BuildInPublic #TestFlight #PWA #WebPush

    Come chill with me: youtube.com/live/y8KaAg0A3rA

  40. I'm making a seasonal anime guide app, in the open for all to experience and learn from.

    Short and late stream, but let's continue working on list migrations!

    #Jiiiii #DevStream #tvOS #visionOS #macOS #iOS #iPadOS #Anime #SwiftLang #SwiftUI #Vapor #WebAuthn #BuildInPublic #TestFlight #PWA #WebPush

    Come chill with me: youtube.com/live/y8KaAg0A3rA

  41. Another live experiment in the Lab is PhysioTracker: a simple way to log physio exercises and build up a record over time.

    I kept it deliberately local-only. No account or cloud sync; the data stays in the browser unless you export it.

    physiotracker.app

    #ai #buildinpublic #indiedev

  42. I'm really proud of this one. Pocket Jam is soon getting a Song Analysis feature. It will figure out key, tempo and song sections. This makes it even easier to practice and loop specific parts of a song.
    It even comes with a nice sections editor in case the analysis doesn't come out 100% perfect.

    #indiedev #buildinpublic #music #musicians #apple #macos27

  43. Every privacy app tells you it can't read your notes. Mine tells you that as well, which on its own is worth nothing.

    The Catchlight iOS source is public under Apache-2.0, encryption and all. You don't have to read it, and I don't expect you to. Somebody with more patience than me can, and that possibility is the part that counts rather than whether anyone ever does.

    Apache-2.0 means you can reuse it, which I'd prefer to it sitting there being admired.

    #BuildInPublic #OpenSource #Privacy

  44. Coming soon: A full email editor for Double-Opt-In and Welcome emails. Another step towards full automation support!

  45. Another Edorena milestone 🚀

    Share Snapshot is live.

    Rule engine → shipped.

    Semantic understanding → shipped.

    Snapshot sharing → shipped.

    We're moving from building the foundation to learning from real users.

    That's the phase I've been waiting for.

    #buildinpublic #AI #SaaS #Startup #Productivity #edorena

  46. Another Edorena milestone 🚀

    Share Snapshot is live.

    Rule engine → shipped.

    Semantic understanding → shipped.

    Snapshot sharing → shipped.

    We're moving from building the foundation to learning from real users.

    That's the phase I've been waiting for.

    #buildinpublic #AI #SaaS #Startup #Productivity #edorena

  47. Another Edorena milestone 🚀

    Share Snapshot is live.

    Rule engine → shipped.

    Semantic understanding → shipped.

    Snapshot sharing → shipped.

    We're moving from building the foundation to learning from real users.

    That's the phase I've been waiting for.

    #buildinpublic #AI #SaaS #Startup #Productivity #edorena

  48. Another Edorena milestone 🚀

    Share Snapshot is live.

    Rule engine → shipped.

    Semantic understanding → shipped.

    Snapshot sharing → shipped.

    We're moving from building the foundation to learning from real users.

    That's the phase I've been waiting for.

    #buildinpublic #AI #SaaS #Startup #Productivity #edorena

  49. Another Edorena milestone 🚀

    Share Snapshot is live.

    Rule engine → shipped.

    Semantic understanding → shipped.

    Snapshot sharing → shipped.

    We're moving from building the foundation to learning from real users.

    That's the phase I've been waiting for.

    #buildinpublic #AI #SaaS #Startup #Productivity #edorena

  50. I’ve started fetching data from the API and reworked the lyrics view (thanks @TheDaver for the feedback). It was mostly simple because I already had a regex to find timestamps to strip them out from the old lyrics view.

    Here’s a little sneak peak at what’s coming. Shout out to my fellow Hades 2 fans!

    #BuildInPublic #swiftui