Steve Gordon
@stevejgordon.bsky.social
Microsoft MVP | Pluralsight Author | Eng. Elastic APM Agents | Blogger | Speaker | YouTuber | He/Him
Last week we launched my latest course on @pluralsight.bsky.social - "Applying Dependency Injection & Middleware in ASP․NET Core 10" Please check it out at www.pluralsight.com/courses/appl... #dotnet #aspnetcore
Applying Dependency Injection & Middleware in ASP.NET Core 10
pluralsight.com
Helpful, thanks @visualstudio.com. What is "s"! Had to kill the process. I feel it may be punishing me for opening it less now I'm mosting in AI terminals and VS Code! #visualstudio
At the gate and soon on my way to NDC Copenhagen hosted by @ndcconferences.com. Hope to see a few familiar faces and meet many new ones while I'm there!
NDC Copenhagen is almost here, and we couldn't be more excited! If you haven't grabbed your ticket yet, there's still time. Come join us next week for world-class talks, brilliant speakers, and great company. See you there! 🇩🇰 Tickets -> ndccopenhagen.com #NDCCPH
So GitHub Actions is down (again) and blocking me! Great!
Pretty staggered to find that resource constraints in Azure mean I can't deploy a side project requiring SQL to any UK region currently. The promise of the cloud model is somewhat failing at this point and I have to assume that AI is crippling the availability of compute.
Sonnet 4.6 is annoying me! Gave it a clear openspec with 8 deliverables. Asked it to implement deliverables 1 to 3 (more token efficient) but it implements randomly tasks from all deliverables, but not all tasks for all deliverables, burning a huge chunk of my #claudecode pro 5 hour window!
One of the things I enjoy about AI agents is the brainstorming phase. I have CEO, Requirements Analyst, PM and Solution Architect personas that I use to take a feature idea and have them challenge me on the functionality and technical aspects. I ask them to be 95% confident my intent is understood.
Codex has got me back to productive on my side project this morning. Churning through deliverables on my next feature around preparing the children to head out to a local zoo with the occasional prompt. Claude usage was 77% 5hr after the first small change. Codex is on its 10th with 65% remaining.
I'm trying out Codex CLI and the pro subscription this morning. Claude Code seems to have become unusable with the whole token usage fiasco. I've removed most of my helpful infrastructure to save tokens but even plain openspec apply tasks are burning my usage and the changes are slow too.
Another example of AI acting like a lazy developer (and yes, humans do this too). Here @github #copilot decided to ignore common file separation and use "a shortcut" by just throwing them into an existing test file. Overall it saved me time on a chore, but I still have to watch closely.
I'm continuing to experiment with subagents and an automated ochestrated workflow for feature implementation, with QA and code review. It's kinda working, but it burns tokens and several steps just fail and the ochestrator (main session) end up doing the work again. Needs more investigation!
Steve Gordon@stevejgordon.bsky.social · 6mo agoThis morning I am playing with #ClaudeCode subagents and building a test workflow.
One of the reasons I'm spending time learning about #ClaudeCode subagents is that while my workflow has been quite productive, I'm becoming the slowest part of the process, manually orchestrating various sessions. Keeping track became hard and tiresome so I ended up with notes to keep track!
This morning I am playing with #ClaudeCode subagents and building a test workflow.
Yuk! Caught Claude Code using AsyncLocal to work around a pooled EF DbContext rather the recommended pattern of scoped factory. Code reviews are still important people! The challenge is that I find reviewing/reading code I haven't written quite slow as I need to build up the context. #dotnet
One unhealthy habit introduced with my personal Claude Pro subscription is wanting to maximise my usage. I now find myself starting as session as soon as I wake to maximum the number of 5 hour windows I get. Also juggling prompts to get the maximum 5hr and weekly token usage.
At a motorway services on our way home from 11 days in Wales. It's been a nice break with lots of activities and outings for the girls. Had a surprise extra cost of £313 yesterday after bursting a tire in a nasty hidden pothole. Glad we could get it replaced rather than limp home on the spare!
I've been refining this workflow and its now quite efficient. Agents log at the end of a session and include a handover (if needed) to another persona. I can then quickly bring a new session up with the correct role and point it at the handover to continue the next steps.
Steve Gordon@stevejgordon.bsky.social · 6mo agoAfter a bit of an infuriating time bouncing between #claudecode sessions in a dev and then qa persona, looping until it finally does things reasonably well, I've started experimenting with a devlog skill to summarise what is done, left over in each session and provide a handover the next agent.
In a side project experiment with AI, mostly #claudecode, I've been reviewing the code its written before committing but I was kinda ignoring the tests. Now having reviewed some of them, they need some major work to remove brittle asserts and teach it about parameterised TUnit tests!!
After a bit of an infuriating time bouncing between #claudecode sessions in a dev and then qa persona, looping until it finally does things reasonably well, I've started experimenting with a devlog skill to summarise what is done, left over in each session and provide a handover the next agent.
It's Claude Time again! Today @rendle.dev and I are joined by @richcampbell.bsky.social - let's see if Claude Code can build user interfaces? Can it understand sketches and scribbles? Tune in: twitch.tv/dylanbeattie (or youtube.com/dylanbeattie if Twitch isn't your jam)
Twitch
Twitch is the world
twitch.tv
My current frustration with my AI agent workflow experiment, specifically Claude Code is how quickly I burn my 5-hr usage on basically one small feature. I run in a #dotnet engineer persona to apply the OpenSpec change, then switch to a QA persona to review. 1/4
Steve Gordon@stevejgordon.bsky.social · 6mo agoI'm currently on holiday and I've been experimenting with using a multi-agent workflow, in part based on the great ideas presented by @rendle.dev on their stream with @dylanbeatt.ie to build out an idea without eating into family time.
I'm currently on holiday and I've been experimenting with using a multi-agent workflow, in part based on the great ideas presented by @rendle.dev on their stream with @dylanbeatt.ie to build out an idea without eating into family time.
Yet more Claude talk and experimentation and such www.youtube.com/watch?v=c2rQ...
Claude Code Part 5: Let's Take A Moment And Talk About All This
YouTube video by rendle
youtube.com
Seems like @rendle.dev and my ad-hoc "wtf is Claude Code" series is getting some traction, which is heartening. We'll be on Wed + Thu + Fri this week, starting around 2pm UK time, live on Twitch (twitch.tv/dylanbeattie) and on YouTube (youtube.com/dylanbeattie). Tune in and chat - or catch up later.
Twitch
Twitch is the world
twitch.tv
Steve Gordon@stevejgordon.bsky.social · 7mo agoWatched both recordings so far and it's been great. I'm at that point of, I need to learn this stuff and make more use of the tools now, so having guidance from two people whose opinions I respect and trust is very helpful! Looking forward to part 3.
Today was infusion day for me, which comes once every three weeks. I get to top myself up with fresh new antibodies. It requires turning my bedroom temporarily into a hospital! I've gotten used to the process after 6 months of doing it. A bit sore tonight and exhausted. #immunocompromised #cvid
As someone who was cautious and skeptical of AI coding agents, I'm starting to accept that these tools are hugely improved compared to where they were even 6 months ago. I made good progress on some changes fully in @github.com Copilot CLI yesterday. Next week I plan to try Claude Code.
