A Better Workflow for AI-Assisted Coding: Lessons from Matt Pocock
I recently watched Matt Pocock's workshop, Full Walkthrough: Workflow for AI Coding . The main takeaway: Good AI-assisted coding is not about writin…
Team Management
⚑ Report a ProblemLatest Team Management news from Tech News
All topics
Culture
agents
ai
api
architecture
automation
beginners
career
devchallenge
devops
discuss
javascript
learning
llm
machinelearning
mcp
opensource
productivity
programming
python
react
saas
security
showdev
softwareengineering
startup
testing
tutorial
typescript
webdev
Switching AI coding tools? Keep the conversation with a local handoff
Hi! Switching between AI coding tools is useful until you have to explain the same task all over again. The next agent needs more than the original…
I built the world's fastest AI gateway in Rust
TL;DR I built Antirion , an open-source (Apache-2.0) AI gateway written in Rust: one binary between your apps and LLM providers, with routing, fallb…
Building GoRoute: An Ultra-Lightweight (<15MB RAM) LLM Gateway in Go
Most developers using terminal coding agents like Claude Code , OpenCode , Codex , or Cursor end up running an LLM router in the background to handl…
Write your agent as functions first, add a framework later
Plenty of agent tutorials open with a framework import. I'd start with ordinary functions that call a model, return structured data, and invoke tool…
Building a Distributed GPU Cluster for LLM Inference on Idle Apple Silicon Macs
A single M2 Max Mac Studio can serve 8‑token‑per‑second Llama‑2‑7B inference, yet most developers leave that compute idle overnight. ## Inventory an…
Japan's devs on Claude Code: nerve, not capability
Originally published in TL;JP , a weekly, fact-checked read on what Japanese AI and tech practitioners are saying on X. This is the Oct 6-12, 2026 i…
How to use Cognee with Hermes
TL;DR - Hermes ships with built-in memory, but it forgets the shape of things - how facts connect, not just the facts themselves. Cognee doesn't. Fo…
Why I Stopped Predefining Agent Roles — and Built a Runtime That Grows Its Own Team
Most multi-agent frameworks ask you to design the team before you know the task. You define roles (researcher, writer, reviewer), wire up a workflow…
Building Better RAG
Most RAG systems that disappoint in production fail at retrieval, not generation: the model answers well from the wrong context, or from none at all…
Can Jev beat Polymarket? I asked it about 26,174 resolved markets
Can Jev beat the Polymarket price? Not from the question text, no. I sent Jev the question and resolution rules of 26,174 resolved Polymarket market…
The cached-prefix crossover: when the cheaper LLM becomes the expensive one
Most LLM cost comparisons collapse a model to one number: $X per million input tokens . That number is the price of a cache miss . Once prompt cachi…
How I Switched Between 5 LLM Providers Without Changing My Code
Last Tuesday, I was debugging a production issue at 2pm when I got a 503 error from my LLM provider. Again. This was the third time that week. My ap…
Your AI Dashboard Is Green. Your Delivery Isn't.
A diagnostic companion to DORA and DX metrics for SDMs and Directors Faros AI looked at telemetry from about 10,000 developers and found that teams…
Shipping practices from five AI engineering episodes
A demo is cheap. Shipping it means you can say what you reviewed, what you designed, what you measured, and who owns production when the model is wr…
Multi-Reward RL, Part 2: Benchmarking GRPO, DAPO, and CISPO on Unseen Tasks
Follow-up: Part 3 scales the CISPO + REPO-R recipe to Qwen3.8-27B and 600 steps , with a one-change-per-run holdout ladder and an advantage-floor fa…
LLM gateway on-call: the 4 incidents that actually happen
An LLM gateway is a small system with a big trust load. It's small enough for one on-call to own, and it holds your org's model credentials, its spe…
Screenshot APIs all send your page content to their servers — built a self-hosted one, looking for feedback
Ran into this building an agent that needed to look at web pages. Every screenshot API is SaaS, which is fine, until you notice the page-understandi…
What Is Jev? I Tested TypeSafe's Decision Model on My Comments and Email
In September 2026 a company called TypeSafe released Jev, and it isn't a chatbot. It never writes a sentence. You give it some text and a question w…
MTP on an RTX 3090: Faster Tokens, but What About Coding Quality?
Originally published on my blog . Enabling MTP on this RTX 3090 raised generation throughput from 36.0 to 56.2 tokens/s, about 56% faster . The two…
How to Build a Zero-Downtime Multi-Model AI Router in n8n (Claude 3.5 + GPT-4o + DeepSeek Failover)
How to Build a Zero-Downtime Multi-Model AI Router in n8n (Claude 3.5 + GPT-4o + DeepSeek Failover) If you run production AI workflows, you have fel…
LangSmith: Essential Observability for LLM Applications in 2026
LangSmith: The Essential Observability Platform for LLM Applications Introduction Building reliable LLM applications is fundamentally different from…
LangSmith: The Essential Observability Platform for LLM Applications
LangSmith: The Essential Observability Platform for LLM Applications Introduction Building reliable LLM applications is fundamentally different from…
The MCP Load & Resilience Checklist: What This Covers, and What It Deliberately Doesn't
A few weeks back I wrote about rate-limiting and backoff patterns for MCP servers under load. The feedback that came back wasn't "give me more backo…
how we evaluate our AI Gen message for apply messsage
how we evaluate our AI cover letter we built a feature: when a pro (service provider on our platform) gets a request from a client, LLM writes the f…
An MCP server for Swiss household employment, with a source for every number
Employing a cleaner or a nanny in Switzerland means 26 sets of rules. Every canton has its own compensation office and form, its own family allowanc…
Cutting 70% of RAG context tokens and keeping the answers identical (measured)
Your RAG pipeline retrieves 12 chunks because the retrieval score said "maybe". Your LLM reads all of them. You pay for all of them. And the answer…
Open WebUI: Admin Configuration Options in a Nutshell
Open WebUI is a universal chat interface with connectivity to local or remote LLM providers, custom files, documents, and a knowledge base, with ful…
VEKTOR v1.9.8 is live: an LLM library that builds itself, a converter for nearly every file, and security you can actually see
Local-first memory for AI agents, now with your books, your documents and a much harder look at what your AI reads. We shipped more in the last mont…
My drift board learned to say "I don't know". Here is what it still cannot say.
Archival copy of record, committed before this post: https://github.com/Tania-coder/SEISMOGRAPH/blob/main/docs/reports/2026-09-22-weather-report-02.…