ramoz

Pandoc might be able to do this, found this:

https://gist.github.com/plembo/409a8d7b1bae66622dbcd26337bbb...

Retro bowl (& goal) theme spotted

https://play.google.com/store/apps/details?id=com.newstargam...

https://play.google.com/store/apps/details?id=com.newstargam...

Okay, this is the one of the more useful thing sin my agentic engineering arsenal right now.

I mean, I didn't mean specifically every agent, and I also did not mean as a experiment. I see real at scale uses for this. Agents operating on their own networks, cross-team agents, my own agents on my own laptop, etc. Sharing context only gets more important the better these things get.

Ive been prototyping with Iroh for awhile.

I think this tech (modern p2p) represents what agent-to-agent (a2a) should be built on.

Every agent should be reachable to each other without hosting itself as an http server.

related prototypes

https://github.com/eqtylab/agentbeam

https://github.com/eqtylab/real-a2a

integrated agent review surfaces with https://github.com/backnotprop/plannotator

HTML/artifact canvases have a lot of potential

https://x.com/backnotprop/status/2064951065439834378?s=20

https://x.com/backnotprop/status/2065436433985474726?s=20

https://github.com/plannotator/effective-html

Shared context workspaces are important

https://plannotator.ai/workspaces/

https://github.com/plannotator/tot

I've been generating these types of interactive diagrams with Fable 5 and found success with this skill:

https://github.com/plannotator/effective-html

Claude Code, Codex, Pi clis all for varying levels of work. VS Code when needed.

I review agent messages, some specs/plans, and conduct local code reviews with Plannotator [1].

For skills, I have a bunch of custom ones for my own workflow. and for public skills I really only use the interrogate skill from cursor's lauren [2].

Key workflow stuff:

- Almost all work I do gets done in a git worktree.

- ghostty + Mac OS gives me all the organization I need for multi-agenting

- turn off all agent memory, this has only ever caused problems for me.

[1] https://plannotator.ai

[2] https://github.com/cursor/plugins/blob/main/pstack/skills/in...

I do think Cloudflare probably institutes a similar manual review process as well. I have a handful of fairly vocal and supportive engineers I stay in contact with around https://plannotator.ai (there is an integrated code review surface that creates a feedback loop with your local agent).

> agents do a good job of looping over PR comments

This is the easy part. Most harnesses enable some sort of integration now, so you can actually create a smooth local experience around this as well - better code before it ships to more costly review or bloats PR threads.

> guided, educational code review tool

This is a bit tougher, and I find the main harness chat tends to work best. I learn better when I'm more engaged and aware of what I'm asking. It's easy to stick a code tour type of thing on a screen. It's hard to really nail the right attention and learning mechanism around it.

The vast enterprise industry (non-technical) is now aware of Claude/Anthropic.

good feedback, thanks!

we're going to end up speaking past each other - but generally I do agree with you and am not denouncing the importance of formal verification methods. I do think abstractions are going to dominate the human ux above them

yes, am familiar with the "code is spec" trope.

Shame us all for moving away from something so perfect, precise, and that "doesn't have edge cases."

Hey - if you invent a programming language that can be used in such a way and create guaranteed deterministic behavior based on expressed desires as simple as natural language - ill pay a $200/m subscription for it.

> If I had to roll out such a development process today, I’d make a standardized Markdown specification the new unit of knowledge for the software project. Product owners and engineers could initially collaborate on this spec and on test cases to enforce business rules. Those should be checked into the project repositories along with the implementing code. There would need to be automated pull-request checks verifying not only that tests pass but that code conforms to the spec. This specification, and not the code that materializes it, is what the team would need to understand, review, and be held accountable for.

The constant urge I have today is for some sort of spec or simpler facts to be continuously verified at any point in the development process; Something agents would need to be aware of. I agree with the blog and think it's going to become a team sport to manage these requirements. I'm going to try this out by evolving my open source tool [1] (used to review specs and code) into a bit more of a collaborative & integrated plane for product specs/facts - https://plannotator.ai/workspaces/

[1] https://github.com/backnotprop/plannotator

I was about to comment: "HTML creates too much friction after doing all sorts of visual explainers" ... thanks for articulating it well.

As a layer of abstraction, it also creates more requirements: need a browser, likely need includes/cdn libs to avoid bloat, all sorts of other things. Markdown is consumable, diffable, shareable in raw form - and you can add enrichment layers on top without much effort.

He's already within the consulting sphere around hospitals in his area.

He's already in the whole consulting sphere around these hospitals in his area.

I don't have time for that. I just told him he needs to hire somebody

A non-technical friend of mine has just won some hospital contracts after vibecoding w/ Claude an inventory management solution for them. They gave him access to IT dept servers and he called me extremely lost on how to deploy (cant connect Claude to them) and also frustrated because the app has some sort of interesting data/state issues.

Yea that's fine and understandable.

But like I said, this is something for those users. I launch many review processes locally with `claude -p`

This is much of a something burger for users who actively use `claude -p` under their subscription. Users will have to do their own math, but that 200 could come and go quite fast and then you're hitting normal API rates versus what you had previously been hitting.

https://x.com/jeremyphoward/status/2054682882753597603?s=20

Happy to change the title if there is explicit clarity on what my `claude -p` usage costs me today & it not differing from what it'll cost me once the change is in effect.

I wasn't able to post the official links because it was already posted by simple reposters who didn't understand, and titled their HN posts as "you get credits" basically

this is the original thread https://x.com/ClaudeDevs/status/2054610152817619388?s=20

The wording in the press is very confusing. Not sure if deliberate.

If you're an active `claude -p` user, it will now cost you API rates vs being able to user your subscription.

UPDATE: https://x.com/lydiahallie/status/2054650920768807313?s=20

Still confused.

I’ve done a lot of exploration here.

Visual explainers certainly come in hand. You need to have both the extra time and cost of tokens accounted for when you ask for these. As well as maintainability - you lose things like vcs/diffs over plans that are much more readable as markdown.

The more interactivity on the surface, the better. Esp if they create feedback loops with the agent. Simple annotations to start.

Markdown still goes a long way. I’ve effectively been enriching plan rendering in Plannotator. Now supporting GFM, custom svgs, etc.

https://github.com/backnotprop/plannotator

For fun, I also enabled annotations on top of these type of svgs, see here https://x.com/plannotator/status/2052851731998941380?s=46

It never worked well for me. The only thing I really needed outside of the harnesses was a better plan review surface. https://github.com/backnotprop/plannotator

https://plannotator.ai/ now works for codex.

free & open source: https://github.com/backnotprop/plannotator

Codex actually feels severely lacking to me, trying to switch off Claude Code. I'm trying every day. The models honestly feel on par, but the Harness and the CLI are somewhat painful to work with.

Yeah, dude, stop being fucking weird. Im an adult, you're an adult that misinterpreted my gripe (with langchain mention, not the grammar)... If you want to get fussy, be better about it. Your fuss is annoying and unintuitive. Ask gen z for some advise.