CodingCat.dev (@CodingCatDev) header
CodingCat.dev (@CodingCatDev) profile picture

Watch on https://nitter.cf/t.co/I2XpaxIBND

USA
Joined February 2015
Stop building knowledge bases with messy folders of Markdown files. 🛑 If you want your docs and internal knowledge to actually scale, you need structured content. In our latest guide, we break down how to build a modern, scalable Knowledge Base using @sanity_io: - Designing a flexible schema for docs - Querying fast with GROQ Making content easy for non-devs to edit Read the full breakdown here 👇 codingcat.dev/post/sanity-kn…
1
62
Token waste is also a precision problem. When AI agents ingest bloated retrieval payloads, hallucination rates climb alongside inference bills. Governance starts with scoped GROQ projections and structured dataset outlines. Production notes below 👇
2
1
2
48
Stuffing an entire docs repo into a system prompt kills latency and explodes token costs. Context MCP flips the architecture: agents load a lightweight index via initial_context, then fetch exact nodes on demand. Full breakdown in the reply 👇
1
1
1
42
Podcast S1E27 with Justin Duke (@jmduke): Producing Newsletters with Buttondown If you are looking for a simple yet powerful way to create a newsletter checkout Buttondown! We sit down with Justin Duke to talk about how he got started working on this project.
1
1
1
48
CodingCatDev Deep Dive: Better Performance through analysis Example of how to use Web.dev to maintain a timeline of performance, while running firebase performance for constant monitoring.
1
1
1
40
Replying to @Matheus_Builder
Totally agree and @HowDevelop will know a real answer. Me: 100%. Local inference stops blanket transcript exposure, yet external tool calls still need an egress gate. The cleanest pattern here is enforcing strict schema validation and a redaction/tokenization layer in the tool router before any external request fires, paired with local-only OpenTelemetry traces (or scrubbed attributes) so PII never hits cloud observability logs.
2
33
Podcast S1E26 with Flor Antara (@techflor), James Vidler (@jameskvidler): Creating Great Ecommerce with Jamstack We sit down with Flor Antara and James Vidler to talk all about Ecommerce and the solutions for Jamstack.
1
1
1
47
Podcast S1E25 with Alex Gogan (@alexg0g): Creating Macro Benefits from Micro Frontends We sit down to chat with Alex Gogan about how Sherpa is leveraging Microfrontends.
1
1
1
71
Full architectural breakdown of local Speech-to-Text + 12B Gemma on-device tool calling with Shivay Lamba: youtu.be/RSKKXEE9AJE Explore more Episodes and Blog Posts: codingcat.dev
19
Cloud agent pipelines chain network hops across transcription, inference, and tool routing. Moving Speech-to-Text and a 12B Gemma model directly onto the device eliminates round-trip latency and keeps PII inside local memory. Architecture in the reply 👇
4
1
3
135
How does Context MCP give AI agents deterministic context without blowing up your token budget? Instead of stuffing 50 RAG chunks into the prompt, the agent inspects the tree outline and pulls only the exact Markdown paths it needs. Details below 👇
2
1
1
83
Podcast S1E24 with Alexander Lichter (@thealexlichter): Diving Deeper Into Nuxt.js We take a deeper dive into Nuxt.js with Alexander Lichter a core team member of Nuxt.js.
1
1
2
61
CodingCatDev Deep Dive: Building a Fun App With Ionic Studio and Cloudinary This post describes the procedure of uploading images to Cloudinary as a prelude for building a fun app called Face Smash with Ionic Studio.
1
1
1
59
Podcast S1E23 with Daniel Roe (@danielcroe): Creating a Better Vue with Nuxt We chat with Daniel Roe about how he became a member of the Nuxt team and how Nuxt fits into the Vue.js ecosystem.
1
1
1
70
Podcast S1E22 with Cassidy Williams (@cassidoo): Hosting Next.js on Netlify We sat down with Cassidy Williams to talk about her background as a developer. Then we talked about the cool new Next.js on Netlify hosting feature.
1
1
2
75