Fernando

linkedin.com/pulse/agents-m… via @LinkedIn

@hiiinternet We are looking for a design partner for story based telemetry if you guys are interested

if you're a product / ai engineer interested in working at Ramp hmu ✅

@Dimillian The ceo

who is monitoring the monitor of the orchestrator monitor?

@_dylanga @tryramp @modal We think this has a lot of value but can be hard for people to set up coherently. You should check out the story based telemetry and otel manifests we are working on to make this more accessible for all developers

The first thing I did at @tryramp was set up distributed tracing, structured logging, and metrics for Inspect, our background coding agent. We now have full visibility in to everything the system is doing: the browser, CF workers/DOs, @modal sandboxes, database calls, etc. Most importantly, Inspect now has visibility in to itself. It can self-triage runtime errors it encounters and create PRs to fix them. Every morning, it reviews the past 24 hours of its own @datadoghq dashboard, identifies systemic issues, new errors, and long tail latencies, and has a summary + PR waiting for me at 9am.

@McGrewSecurity screaming!!!!

@pusongqi this is a great adoption of the slack design

Each channel is a new worktree 🤠 Drag and drop your agents like this roro is prob the most fun way do work with agents

@dexhorthy we are bullish that story-based telemetry will replace a lot of this spec conversation

I wasn't gonna share this until AI Engineer miami but if you read this far, here have some alpha on what we've been working on the last few months hlyr.dev/qrspi-mlops

damn this is so good and encapsulates everything I've been seeing/saying in the last few months - a spec that is sufficiently detailed to generate code with a reliable degree of quality is roughly the same length and detail as the code itself - so don't review those things, just review the code at that point, if you care enough about that level of abstraction - unless you're vibing side projects or prototypes (yes, even zero-to-one software), you ABSOLUTELY SHOULD care about the code at that level of abstraction - you need to find SOME way to get more leverage over coding agents though, because just reading all that code is a pain, esp when a lot of it is slop - the default/dare-i-say-decel way is to go back to "i own the execution, and give little things to the agent, check it along the way" - the accel-but-safe-way is to find something - NOT A SPEC (the word "spec" is broken anyway) - NOT 3 INVOCATIONS OF AskUserQuestion - that lets you resteer the model *before* it slops out N-thousand LOC

@YoavCodes you know the algorithm is robust lol, probably 5

@Principal_ADE How many mandarin puns per day is too many?

@theo Cards for repositories?

Probably going live in an hour. What should I talk about today?

@theo @yiliush

So I've been using a new terminal...

@dani_avila7 made you this card to celebrate

23,000+ stars on GitHub! Thanks to everyone in the community who keeps contributing Components to aitmpl.com You’re awesome! 👏

@iamlukethedev I think story-based telemtry is going to look really great here

QA is one of the most underrated jobs in tech. So I added a QA room to the OpenClaw 3D office. Whenever agents run tests or verify behavior, they move into the QA room to work. You can see: • QA workflows • Test pipelines • Live logs • Verification results Everything needed to run a reliable AI engineering team. PS: Where are my QA engineers at? 👀

@aidenybai 🤦‍♂️

here goes nothing...

@brandonin @RayFernando1337 @NVIDIAGTC @nvidia 🤣

@RayFernando1337 @NVIDIAGTC @nvidia Come meet daddy Jensen with me.

Excited to go to @NVIDIAGTC as the golden ticket winner! Got exclusive seating for Jensen’s talk! @nvidia

@StatisticsFTW made you this card for your repo

github.com/barnum-circus/… And check out the repository!

Introducing Barnum, or... how I ship hundreds of PRs per week, burn through backlogs, and automatically fact-check documentation. LLMs are incredibly powerful tools. But when we try to use them to drive more complicated refactors or more intricate workflows, their shortcomings are quickly revealed. When their context gets full, they get forgetful, and they can't be relied upon to necessarily do the steps that you ask. They often cut corners. Put simply, having an inherently probabilistic process perform what should be deterministic work necessarily comes at the cost of reliability. And you can't build a complicated workflow off of unreliable foundations. That's where Barnum comes in. Barnum is the missing workflow engine for agents. Rather than having agents be responsible for upholding guarantees (e.g., always lint and commit your changes atomically), agents instead do just what they're good at: reading text and reasoning. Everything else is done deterministically, on the outside, by Barnum. This means that you can build bigger, more involved workflows without sacrificing reliability. Because you can intersperse bash scripts, you save on token usage. The agents performing a micro-task only receive the instructions for that specific task, meaning that context does not get overwhelmed and they don't get forgetful. And because all inputs, outputs, and transitions are validated, the agents can't wriggle out of doing the work. This workflow is essentially a state machine described in a config file. And the best part? The configuration has a JSON schema, so agents are actually really good at writing the workflow! It's already been used to ship hundreds of PRs, run automated refactors, burn through various backlogs, fact-check every statement in documentation, and build a deep-research clone! The attached image is a representation of the workflow that I use to identify and implement automated refactors. I follow this up with a separate workflow that splits each commit into a separate PR, judges the refactor, and potentially completes the refactoring (for example, by modifying call sites if the refactor changed some public API). So go on, give it a try. Check out barnum-circus.github.io, star the repository, and join the Discord! I can't wait to see what you build with it! And I'd love for you to get involved!

@Dimillian @rohanvarma I used to care so much about these, and then the bot was the only one who read them and it definitely helped, but I never see them unless it’s in passing

@rohanvarma I think I can count in months the last time I edited more than a line now, this is insane

I can’t remember the last time I named a variable 😬 I think I used to be quite good at it

@steveruizok I learned a lot from this tweet, wish I could like it twice

In these troubled times, a react performance tweet to restore you

@iamlukethedev Happy to help!

@Principal_ADE I need you :)

The community asked. The decision has been made. The OpenClaw 3D office will be open-sourced. Step 1 ✅ Domain secured: claw3d.ai Step 2 🚧 Looking for builders and collaborators to join the project. Step 3 ⏳ GitHub repo coming soon. If you want to help build the AI workplace, reply “CLAWS” and I’ll reach out.