@backnotprop

Cofounder, AI @EQTYLab / prev dc - complex systems / veteran / For fun: @plannotator

 NYC
backnotprop.com/
Joined March 2024
  • Tweets1.9K
  • Following978
  • Followers2.2K
227Media
Anthropic code review this, clanker review that ... why don't you shut up and review+annotate your own code.... (yes im a loser who still manually reviews code) Originally inspired by a bunch of feature requests and then seeing @dillon_mulroy tweet a similar cool ux. @plannotator for reviewing plans (primary focus) and code, fully oss. OpenCode, @badlogicgames 's pi.dev, and Claude Code and other clankers
18
17
10
319
76,290
Many of the novel sandbox/agent-vm providers are not providing any substantial difference or advantage over an EC2 box
2
147
State Machines for your Software Factories Needed to burn my claude limits before reset and built this out. Feels like a strong concept for anyone already using skills to dictate agent workflows. Sound on 🔈
4
12
367
github.com/backnotprop/machi…

GitHub - backnotprop/machine: State machines for coding agents.

State machines for coding agents. Contribute to backnotprop/machine development by creating an account on GitHub.

github.com
4
55
This is the way for me personally as well. Not just personal wiki, but every major project at this point is a massive context/project polyrepo. Im not sure what a third party could really offer at this point that beats filesystem net performance here - for memory, context, etc. Typical memory products dont fit well here. Context aggregators I do not think are right either... it all needs to live together with the code. The possible contenders in the space are Code-forge providers. IDE/ADE, Cloudflare Artifacts, Cursor Origin could all better innovate here. backnotprop.com/blog/context…

Context Monorepos

Own your context. A context monorepo is a structured repo of docs, examples, and agent guidelines that makes launching agents across real codebases actually work.

backnotprop.com
Matt Pocock
@mattpocockukOct 19
3 months on, and my personal wiki has become critical infrastructure for my business. Hugely enriches my courses and makes "agents that run my business" actually viable. Very, very glad that I built this myself. Relying on a vendor for memory feels like a recipe for lock-in.
4
1
39
2,805
Claude Code Mods, Pi Extensions, OpenCode Plugins > MCP
3
19
1,572
/fire-subagent "fire the subagent that just produced that slop. Start up a new one and tell it be better than its predecessor"
3
23
981
not the most groundbreaking thing but love "Big Pics, Little Words" type of skills
2
1
1
33
1,298
e.g. github.com/backnotprop/bro/b…

bro/skills/big-pics-little-words/SKILL.md at main · backnotprop/bro

Useful skills. Contribute to backnotprop/bro development by creating an account on GitHub.

github.com
1
6
224
Michael Ramos retweeted
dex
@dexhorthyOct 14
hanging out during AIE New York riffing agentic coding, plans, inboxes, and a whole lot more with the ur boy @backnotprop creator of @plannotator and more importantly the /bro skill
2
32
4,385
Telling you guys AI code review, esp 3rd party, is going to die. You’re not going to pay an extra $1/PR when your company is pumping thousands of PRs a day. Instead, better models and stronger codebase verification systems means implementation agents achieve correctness more efficiently and on their own during development. Everything we did in CI will move upstream for efficiency.
William Zhang
@wzhangOct 13
if you're consistently paying $1 for a code review you're not doing it right, let alone $5-20 💀 our internal code reviewer running 6.1 sol xhigh btw
27
6
1
185
12,637
Doesnt mean Greptile fails btw. If their data is as valuable as they claim then labs would eat it up. And they’re in good position to move into and compete in mundane operational and QA automation.
1
7
610
Guided Reviews went viral a bunch last week. FYI, there is an open-source version and also the ability to send portable guided reviews as html files. github.com/backnotprop/plann…
plannotator
@plannotatorAug 19

Portable guided code reviews

Article · @plannotator
5
5
1
83
8,537
examples: guides.show/g/gs0M7zgI_zYeuq… guides.show/g/Q-ECuRlzn6I2U4…

Guided Review

A Plannotator Guided Review. The guide is end-to-end encrypted; the key travels in the link.

guides.show
2
382
Michael Ramos retweeted
brian flynn
@FlynnjammOct 9
yeah, we're definitely going back to managing an inbox
plannotator
@plannotatorOct 9
Introducing Plannotator Inbox. Making decisions is the new bottleneck, while your agents work on many things across many threads over longer periods of time. Inbox is how you stay in-the-loop, organized, alongside the agent harnesses you already prefer to use. Try today, free, local, open source.
20
2
31
2,185
Decision making is becoming the bottleneck with agent coding. Basically all I do all day is answer questions, review prototype variants, and decide if i like outputs, etc. The chat interface is meaningless at this point - terrible surface for staying in the loop. I give the agent an instruction and they go off and do 1000 things. It throws random questions and review artifacts at me all day and those are where my focus lands. E.g. Two hours into the session says, oh yeah, I still need your decision on X, Y, or Z, which who knows where in the chat those were. So I ask for a html or markdown to review with context. The more AI can do, the more it covers across systems and integration and we're just not yet at a point where I think you can be loosely blind to that stuff. It's getting harder the more they can do. Still fun.
36
6
3
159
7,775
One solution might look like an email inbox xitter.cf/plannotator/status/210…
plannotator
@plannotatorOct 9
Introducing Plannotator Inbox. Making decisions is the new bottleneck, while your agents work on many things across many threads over longer periods of time. Inbox is how you stay in-the-loop, organized, alongside the agent harnesses you already prefer to use. Try today, free, local, open source.
2
87
Shipping something today
Artem Zhutov@ArtemXTechOct 9
The new @plannotator inbox feature is a great experiment. I'm liking it so far. Finally, some innovation in the way we interact with agents. I'm so tired of Claude sending those messages: "Two decisions from you yesterday are still yours." I have zero context about what it is
2
28
1,074
xitter.cf/plannotator/status/210…
plannotator
@plannotatorOct 9
Introducing Plannotator Inbox. Making decisions is the new bottleneck, while your agents work on many things across many threads over longer periods of time. Inbox is how you stay in-the-loop, organized, alongside the agent harnesses you already prefer to use. Try today, free, local, open source.
1
3
153
Michael Ramos retweeted
plannotator
@plannotatorOct 9
Introducing Plannotator Inbox. Making decisions is the new bottleneck, while your agents work on many things across many threads over longer periods of time. Inbox is how you stay in-the-loop, organized, alongside the agent harnesses you already prefer to use. Try today, free, local, open source.
32
19
15
311
20,751
Load more