Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

introducing diffmap: a new document format for planning and reviewing agent code. The idea behind diffmap is letting you review the important design changes, not massive line diffs. "Write a diffmap spec for the changes on this branch. Use I've been working and iterating on this skill for more...

50,674 Aufrufe • vor 5 Tagen •via X (Twitter)

35 Kommentare

Profilbild von Tanishq (tk)
Tanishq (tk)vor 5 Tagen

diffmap gives your agent a ton of interactive diagrams and widgets to help collaboratively plan and review with you. one example is a services diagram. it shows you different involved services, along with state changes and data flow over time

Profilbild von Tanishq (tk)
Tanishq (tk)vor 5 Tagen

other ones include mermaid diagram diffs and of course, callstack diffs. the skill includes guidance on when to use each diagram.

Profilbild von Tanishq (tk)
Tanishq (tk)vor 5 Tagen

the agent writes the plan in phases. Each phase is meant to be a single commit. after an agent completes a phase, it shows a commit widget, with the most important files ordered. Clicking on a file opens a diff panel (powered by @pierrecomputer ofc!)

Profilbild von Tanishq (tk)
Tanishq (tk)vor 5 Tagen

You're also able to add comments to the diffmap and copy it for your agent

Profilbild von Tanishq (tk)
Tanishq (tk)vor 5 Tagen

Diffmap is open-source and MIT licensed! Check it out

Profilbild von joel
joelvor 4 Tagen

looks interesting! a few thoughts on the video - we don’t find out what it actually is until about half way through. from the first frame i already knew what you were trying to address (by having skimmed the post). i would deliver the before and after payoff right away. the other alternative is to come up with a really good hook but then you have to keep attention for every second up to the reveal

Profilbild von Tanishq (tk)
Tanishq (tk)vor 4 Tagen

yeah i had the same thought, agreed! will have to show payoff faster

Profilbild von Jake Jillen
Jake Jillenvor 4 Tagen

Good stuff. The psuedo code with links to actual implementation is the best part I think. I used it immediately to try to understand the repo itself and it did a great job. Nicely done.

Profilbild von Tanishq (tk)
Tanishq (tk)vor 4 Tagen

glad to hear! Lmk if you have any feedback

Profilbild von Neesh 🥭
Neesh 🥭vor 5 Tagen

this is so sick

Profilbild von Morteza Hosseini
Morteza Hosseinivor 4 Tagen

Nice idea

Profilbild von Pierrick Bignet
Pierrick Bignetvor 4 Tagen

Excellent! Been using crit.md which has similar goal. Those tools are the key to unlock productivity.

Profilbild von José Miguel Arroyo
José Miguel Arroyovor 4 Tagen

Nice! I was wondering if you'd release it since last time I saw you talk about it. 👏

Profilbild von Tanishq (tk)
Tanishq (tk)vor 4 Tagen

yes it took a long time to dial in and until I was happy with it. Still a WIP honestly, but I use it every day so that was a good enough bar

Profilbild von Luke Igel
Luke Igelvor 4 Tagen

Amazing Tanisqh!

Profilbild von Rictus 🍥❁
Rictus 🍥❁vor 4 Tagen

Tried it on few PRs, great execution!

Profilbild von Antonio Bonet
Antonio Bonetvor 5 Tagen

This is really cool

Profilbild von Tanishq (tk)
Tanishq (tk)vor 5 Tagen

thanks! would love some feedback

Profilbild von Antonio Bonet
Antonio Bonetvor 5 Tagen

Will see about trying it soon

Profilbild von Arshith varma
Arshith varmavor 4 Tagen

This is crazy, I was working on the same idea and I was calling it replay.

Profilbild von Ivan Santos
Ivan Santosvor 4 Tagen

This is awesome!

Profilbild von Doug Tabuchi
Doug Tabuchivor 4 Tagen

@bot save to my vault to check out

Profilbild von Calvin Cheng
Calvin Chengvor 4 Tagen

can you view this on mobile?

Profilbild von male manipulator (reformed)
male manipulator (reformed)vor 4 Tagen

What do you use to make sure the map lines up with what’s in the code? Programmatic tools that check some of the mapping between the two would make it a lot easier to trust the info. (As long as it’s clear what precisely is verified by the tools, and what we’re taking on trust)

Profilbild von Tanishq (tk)
Tanishq (tk)vor 4 Tagen

the diff panels are real code lines. everything else is written by the agent. the agent can reference the code lines in the diagrams, so you can audit whats in the diagram matches up with whats in the code, but realistically that’s not an issue

Profilbild von Mathew Chan
Mathew Chanvor 4 Tagen

This is sweet! gonna try this.

Profilbild von Tanishq (tk)
Tanishq (tk)vor 4 Tagen

lmk if you try it and have feedback!

Profilbild von Asmir
Asmirvor 4 Tagen

this would be so good with a validator that checks every callstack node points at an actual changed hunk and flags files in the diff that no node covers lol

Profilbild von Tanishq (tk)
Tanishq (tk)vor 4 Tagen

yes have thought about this! decided it was easier product ux to show a commit summary when implemented. but very interesting concept, just didnt know how to surface cleanly

Profilbild von Mark Maglana
Mark Maglanavor 4 Tagen

Is the sharing feature being implemented via github gist a temporary thing? Would feel safer if it was something more restrictive.

Profilbild von Tanishq (tk)
Tanishq (tk)vor 4 Tagen

agreed! yeah its temporary, ill implement something better if more people want it

Profilbild von Daniel Lenton
Daniel Lentonvor 5 Tagen

Does the ✅ version of a phase usually look much like the plan? That gap feels like the bit most worth reviewing

Profilbild von Tanishq (tk)
Tanishq (tk)vor 4 Tagen

basically, the plan is composed of phases (commit-length work). You review the plan, and (my preferred way of working) is going phase by phase, but you can also just decide to build the whole thing in one shot

Profilbild von Ricardo Vázquez
Ricardo Vázquezvor 4 Tagen

cc @karrisaarinen ☝️

Profilbild von Tanishq (tk)
Tanishq (tk)vor 4 Tagen

@karrisaarinen oh yeah saw their recent launch! Need to dig into it more

Ähnliche Videos

Introducing /visual-plan - a skill to generate rich, visual plans for Claude Code and Codex. Plan mode in Claude Code is incredible. But I always find my eyes glazing over when it gives me this huge markdown essay in my terminal. I found I can make much better visual plans with reusable components. So I made a skill called `/visual-plan`. It generates plans as MDX with visual, interactive components. Diagrams, interactive API specs, schema design changes, annotated code, and even pan and zoomable wireframes. So for any UI work, you can look at a wireframe first, comment on it, iterate, and then have the agent work. I’ve found this to be a much more intuitive interface for reasoning about what the agent is doing. It’s somewhat inspired by that popular post about how HTML is better than Markdown. But HTML can be slow and verbose to write. And it doesn’t look good checked into a repo. This has really made me feel like humans and engineering are entering a new abstraction phase, where we reason about things at the plan level. As long as the plan is good, agents are getting more and more reliable at executing on it. Almost to the degree that we trust the C compiler to compile to assembly reliably. Plans are the new intermediate representation. I also made a skill for the reverse of this, called `/visual-recap`. After the agent works, it gives you a recap of everything it did. Same idea: wireframes, interactive API specs and diffs, schemas, annotated code, etc. So now when you’re reviewing what the agent did for you, or looking at a pull request of somebody else’s code, you can see a visual recap instead of just reading a wall of text. It’s all free and open source. You can find it on my GitHub. Will link to it in the reply because we all know how dumb these algorithms are with links.

Steve (Builder.io)

126,758 Aufrufe • vor 4 Monaten