How do you know it works?

Technologies

• Claude

  While I am working on replacing Claude Code with my own development system and harness specifically trained for my coding style for now I often use Claude Code.

  Claude is my main driver right now I do also use Codex for longer running tasks, particularly computer use tasks.

  The main portion of Claude's use is for my "fleet" see that page for more details about the fleet and how its decision system enables me to build faster.

• Effect

  Effect.ts is one of the main components of all my software. Effect ports a lot of ZIO from Scala to Typescript bringing many functional paridigms.

  In my opinion functional programming is one of the key enablers for effective LLM usage. For example, side Effects, a function making changes in an unrelated section of code, degrade LLM's performance even more than humans. Humans can remember many things from a long time in the past, while LLM's can only know whats in their context window. So the more disparate areas of the code that the model has to know means that it fills up its context window faster. This both reduces the size of the code that the LLM can work on it also degrades the LLM's prerformance. (see context rot) So the less you can fill the LLM's context window the better.

  This is where making small isolated composable functions reduces the amount the model needs in its context window.

  I also find that Effect.ts enables other benefits in very convenient ways, as the Effect.ts docs explain:

  When coding agents write a growing share of your software, the bottleneck moves from writing code to trusting it. Effect makes a program’s failure modes, dependencies, and lifecycle visible to the compiler, turning runtime surprises into precise feedback an agent can act on. And when the thing you are building is itself an AI application, flaky providers, retries, streaming, and rate limits are exactly the problems Effect solves out of the box. Effect Intro

  Further reading:

  • Parse, don't validate
  • Query Parameterization Cheat Sheet

• PostgreSQL

  While I reach for graph databases as my default there is a familiarity and simplicity that comes with a SQL database. I have settled on PostgreSQL as my SQL database of choice because of its resource efficiency and my own familiarity with it from previous jobs.

• Pulumi

  Throughout my career when I have been doing Infrastructure as Code I have continuously ran into the issue where I needed to either do some hacky solutions or combined IAC and a programming language when using something like Terraform. That is where for my own projects I selected Pulumi.

  While there are some other projects like CDK8s I found that Pulumi reflected best how I prefer to code and could work with my functional programming style. Pulumi isn't perfect and there are still object creation requiret, I am able to combine Effect.ts with some of the Pulumi to make my IAC even more robust and one coehesive style.

  Further reading:

  • Infrastructure As Code
  • OpenGitOps

• Python

  Python has been the single language that I have used the most throughout my career. While my recent projects are mostly Typescript I do still use python for my machine learning projects. I do find that my familiarity with Python matters less now that LLM's do the coding but for those rare bugs it is nice to go and read code that I am familiar enough with to easily scan.

  I used Python as my main language from 2015-2019 at Hewlett Packard Enterprise and Sumato Homes. Then from 2022-2025 at Chegg.

• Quint

  While I am less familiar with formal verification I am slowly learning as I have my agents create formal static analysis code in quint to verify that I won't reach deadlocks.

  My overall philosophy of making deterministic checks applies here as the closer I can make my quint match my code the more that I can feel safe to merge agent code without human review.

• TypeScript

  While my favorite language to code in by hand used to be Kotlin, I have shifted to typescript.

  I adore functional programming and find the advances in languages like Haskell facinating. However the interoperability and lack of widespread corporate deployment has prevented me from learning Haskell as much as I would like. That is where Effect.ts made typescript so enticing, I could use the wonderful ZIO system while also using a language that shows up all over the place.

  Further reading:

  • Designing with types: Making illegal states unrepresentable

Projects

• Agent fleet

  The organized fleet that enables me to code faster as I am only needed for key decisions

  Read the full write-up of Agent fleet

• Decision queue

  Every judgment call is a record.

  Read the full write-up of Decision queue

• Architecture checks

  Static checks for the architecture, not just the syntax.

  Read the full write-up of Architecture checks

• Workstation Config

  Consistent configuration for all workstations

  Read the full write-up of Workstation Config

• Dendrite

  Injection experiments on language models, scheduled across GPUs.

  Read the full write-up of Dendrite

• Application tracker

  A job-application tracker with a Firefox extension that fills in forms.

  Read the full write-up of Application tracker