Antony MarcanoWhat if you could develop your SKILL . md files in a test-driven way, just like your code? That was the question I asked myself, and the result was Test-Driven Agentic Behaviours (TDAB)...
Let me show you โ https://youtu.be/i3g9ZXiaqh0
YouTube
jo.vaneyckSoftware engineer and drowning in hourly slack pings from colleagues and linkedin slop trying to find what matters for the job going forward?
1 newsletter per week, 100% free, fresh and hand-curated. You're very welcome.
In this video we'll quickly go over the awesome "AI augmented coding patterns" by Lada Kesseler and others, the most comprehensive resource on how to actually get stuff done with AI coding assistants.
We'll be performing a typical backend engineering task using an AI coding assistant along with some these patterns.
Are you a cyborg or a centaur? Watch the video and find out!
AI coding patterns (that actually work)
Felix NeumannAsync AI coding agents, and how to make good use of them. Very interesting experience report, matching my own expectations.
"We use async agents heavily. The key is to have proper validation loops, tests and strong/well phrased system prompts, so the agent can quickly see if something is broken or it broke convention.
...
Now for most of the tickets we just assign them to agents ... . I can focus on bigger, more complex things, while the agents fix bugs, handle small features, do refactorings and so on in the background. It's very liberating.
I am convinced that most companies/environments will end up with a similar setup and this becomes the norm. There really isn't a reason why not to use async agents."
"Time to take another serious look at LLM's!" I shouted from the rooftops last week. With one big disclaimer: SECURITY ๐
That's what this week's video is all about:
https://youtu.be/Y34JF4piEBI
#llm #claudecode #githubcopilot #n8nio #agenticai #security #aiaugmentedcoding
