• Home
  • Blog
  • Projects
  • Bookshelf
  • About
← Back to all posts

My AI Workflow - November 2026

Published ....
Last modified ....
From Boston, MA

Share this post on BlueskySee discussion on Bluesky


I’ve been experimenting a bit with my own agentic based development workflow as of late and I figured I should share a bit about it on my blog in the hopes that it maybe gives some ideas to others as well looking to try out something new with their own workflow.

I’ve finally been setting up some shared skills for things that I found myself repeating over and over again in various sessions, notably two skills that I honestly should probably combine into one:

  • $make-pr
    • A set of opinons on how an agent should create a pull request
    • Defaults to making a draft PR, with a fairly well structured PR description (or using a PR template if there is one in the local repo
  • $track-pr
    • For tracking the created PR in my current note taking application of choice (one that I’ve built for my own use cases that is honestly still pretty buggy - but thats for another future blog post)
    • I want to combine this with the above skill I think, not sure how others manage combining / allowing skills to be composed together yet

Those two cover the start of the PR making process but I also want to spend some time to figure out the lifecycle of the PR being managed by the agent, e.g. I want my agent to open and track the PR, and then also resolve comments as they come in and then go all the way through to merging the PR when its approved and then marking the PR as complete in my notes too.

Shoutout to Scott Kaye for pushing on me to start making skills and managing them in a repo also!

In addition to the above two skills, I also attempted to setup a skill based software factory workflow that I codenamed Codswallop. I experimented with this workflow for a bit, but it felt a bit clunky and honestly I think I want to instead pursue a code-based software factory implementation (I’ve been thinking about this a bit, I think it’ll take a deeper integration with my go-to agent harness/control plane which is T3 Code at the moment, but maybe Pi Durable is a good place to setup that integration as well).

One of the things that has also really stuck with my workflow is shifting from managing each task directly in its own thread and needing to juggle those threads myself / remembering which one I was last looking at or which one I should look at next, to now instead I interact mostly through a single pinned thread in T3 Code that I call my Orchestrator. It has an hourly scheduled task to look at Slack/GitHub/other T3 Code threads to keep up to date with things I need to manage and then funnels through updates from threads that I need to look at.


Tags:

AIAgentic EngineeringSoftware DevelopmentEngineering

Loading...

Related Posts

AI

Please try OpenAI models

....

OpenAI Enters the Agentic Knowledge Management Space

....

The Heat Death of Software

....

A few predictions about where software engineering is going, including some counter arguments as well

Your Job Is To Understand Systems

....

Parallel Computers

....

The Harness Isn't Your Problem, The Router Is

....

OpenBlank

....

ASD-STE100 Simplified Technical English

....

Performative Engineering

....

The act of making noise and delivering output instead of outcomes

The Agentic Engineering Scale

....

A brief outline of how I think of the scale of adoption of AI in software development

Onboarding Your New AI Teammate

....

Are we reinventing the wheel when it comes to onboarding new AI agents to a codebase, when we already have primitives available for onboarding humans?

Cursor and Obsidian

....

A quick look at combining Cursor with Obsidian to ask questions of your notes!

The AI Development Conundrum

....

Is it a good or a bad thing to offload writing code to AI agents and Large Language Models?

Offload Complexity, Don't Offload Learning

....

A rough mental model for how you should be leveraging AI as a tool for your own growth

My Current AI Stack

....

I've been using a variety of AI tools as of late, I figured I'd document the ones I'm primarily using!

Agentic Engineering

The Eventually Consistent Codebase

....

Outlining how I now approach software engineering/development thanks to AI agents

The Heat Death of Software

....

A few predictions about where software engineering is going, including some counter arguments as well

Your Job Is To Understand Systems

....

Software Development

The Eventually Consistent Codebase

....

Outlining how I now approach software engineering/development thanks to AI agents

The Heat Death of Software

....

A few predictions about where software engineering is going, including some counter arguments as well

Your Job Is To Understand Systems

....

Engineering

The Eventually Consistent Codebase

....

Outlining how I now approach software engineering/development thanks to AI agents

Performative Engineering

....

The act of making noise and delivering output instead of outcomes

The Agentic Engineering Scale

....

A brief outline of how I think of the scale of adoption of AI in software development

Parallel Computers

....

The Agentic Engineering Scale

....

A brief outline of how I think of the scale of adoption of AI in software development

Parallel Computers

....

The Harness Isn't Your Problem, The Router Is

....

Performative Engineering

....

The act of making noise and delivering output instead of outcomes

The Agentic Engineering Scale

....

A brief outline of how I think of the scale of adoption of AI in software development

Onboarding Your New AI Teammate

....

Are we reinventing the wheel when it comes to onboarding new AI agents to a codebase, when we already have primitives available for onboarding humans?

Polish is Important

....

You're Building Software Wrong

....

Slicing software: why vertical is better than horizontal.