
Improving communication using product thinking and machine learning. Prev @NotivHQ @bugcrowd. Purveyor of bad dad jokes! #peoplefirst
San Francisco, CA
Joined December 2008
- Tweets4.7K
- Following1K
- Followers2.6K
- Likes10.2K
Chris Raethke retweeted
people are all trying to figure out what i mean by this
Its quite simple:
There is a bunch of whatever work that goes on (hey move this button here), yeah its easy to make a bunch of small changes
But this is a problem, you never take a step back and deeply think about what you are building and thus we get slop constantly. You don't take the time and figure out what is the best path forward, you just fix the next thing in front of you while having 10 of them going at once.
Take a moment, think about what you are doing.
Wow, what a sad day, @sentry are shutting down Seer Code Review, there is a discount to move to Code Rabbit, but sentry's code review was so much better, both results and also experience.
2
3
260
I love that @antiburn_ai helps me cut so close to my usage limits. Have now swapped fable 5.1 medium for opus 5 high until the morning. #Tokenomics
1
3
300
Anyone else have a mispent weekend burning tokens?
github.com/codesoda/openjev-… #jev
1
6
342
Every person / team should own their harness, whether that’s optimizing a vendor one or rolling their own. The better you understand the internals, the better you’ll be at driving it.
I dream for a future in our industry where good/great engineers, rock into a hiring pipeline, and when they respond to the “what AI tool they use” question, the response is….
“I use my own. Wanna see it? Let’s nerd!”
2
366
Everyone is freaking out about @claudeai Fable using up their allowances. You're doing it wrong!
Replying to @Shpigford
The solution is you don't use fable for everything, set a haiku co-ordinator, sonnet/opus for planning/review and fable ONLY for the implementation. The sonnet/opus can review it, then get fable to update implementation if required. Haiku then pushes and creates PR, fixes CI 🏁
1
89
Dropped a project today: Discuss CLI
No more reviewing agent plans in the terminal.
Discuss CLI turns any Markdown file into a browser review surface with PR-style comments — and your coding agent can join, read the exact text, and reply in the margins.
github.com/codesoda/discuss-…
I kept manually asking my coding agent to verify database state and click through flows after every change.
So I built Bugatti.dev.
"Submit the signup form and verify the user appears in the database" — that's your test. Your agent runs it, you get pass/fail.
Building a new thing tonight, would love your feedback.
Plain-English local QA, powered by your coding agent. Describe the flow in TOML, Bugatti clicks the buttons.
github.com/codesoda/bugatti-…
1
1
157
Building a new thing tonight, would love your feedback.
Plain-English local QA, powered by your coding agent. Describe the flow in TOML, Bugatti clicks the buttons.
github.com/codesoda/bugatti-…
Your coding agent accumulates patterns you never notice. Skillable mines your session transcripts to find repeating workflows and turn them into skills.
Works with Claude Code, Codex, OpenCode + 9 more.
github.com/codesoda/skillabl…
2
128
Currently ralping a new thing
AI first bookmarking - What's interesting is not so much in what it is, but how it's coming into fruition.
github.com/codesoda/agentmar…
1
2
78
I worked with GPT 5.4 to brainstorm, then codex and I wrote a PRD (see tasks). That was then strategically broken up into detailed specs using my auto-ralph skill, which I reviewed meticulously. Now auto-ralph is [planning, buidling, reviewing]+ through each spec to build it out.
1
1
94
I love that I can just follow along as it builds it out.
github.com/codesoda/agentmar…
42
You know what would be nice, different permission profiles inside a @claudeai project, e.g. I'm in dev profile, so that has a bunch of skills, tools, etc., enabled. I'm in the AWS/DevOps profile, so I enable all the default things for that. But in general, it's locked down.
87








