anthony

demo of the agent orchestrator Ive been building for the last couple of weeks. It's node based so you drop agents on a canvas, wire them together, and each one gets its own model, prompt, tools, skills, sub agents and cost limits. my theory is that some agent harnesses fail by trying to cram everything into one all purpose prompt. a "senior engineer" persona that researches, implements, tests and reviews in a single context window does all of those things worse than a chain of narrowly specialized small context window agents with shared state memory. so instead a software workflow here might be seven nodes (understand -> research -> design -> implement -> test -> review -> deploy) augmented with routers, checkpoints and logic gates with each node permission restricted so no part of the processes has more access than it needed for the job. lastly, loop zones work by allowing any agent to send its output back to any earlier node(s). instead of failing a run entirely the reviewer agent might directly critique the implementer, who then picks the work back up with warm context instead of starting fresh. this demo is the simplest possible run. one agent, a manual trigger, some tools, and a fork.

WIP: recursive self improvement but for agent workflows. the pipeline reads it previous executions and traces and rewrites itself based on your configuration and objectives. open sourcing soon. @LangChain calling all graph nerds

how many of the ai startups you saw pitched this year are essentially selling a single workflow in this app? this is my builder agent creating a multi agent workflow from a few paragraphs. nodes, tools, shared state, review loop, done.

building a node based agent orchestrator where every agent node gets its own skills, tools and sub agents and I wildly underestimated skills. the wiring was pretty easy but getting the agents to actually use skills reliably has eaten more of my time than any other feature so Im summoning the skills wizard himself @mattpocockuk for a bit of a sanity check. after a lot of runs I keep seeing two different failure modes. the first being invisible, where the agent should activate a specific skill at a specific step and just never realizes it applies. there's no error or way to trace and the run just continues on until you realize at the end that the output is worse than it should be. partly patched this with nudges, where the harness looks for keywords and concepts and drops a hint like "there's a skill that might fit here" which helped but feels like treating the symptom. the second is the skill activating and failing anyways. sometimes it's outdated or wrong, sometimes it assumes tools that node doesnt have access to and sometimes the skill is fine in principle but the agent still fails to properly execute the steps, which I think is mostly a context problem. I also suspect my nudges are quietly creating a third issue, where skills fire when they shouldn't does this match your experience with skills, and how do you actually alleviate each issue? the invisible one especially since its the only one I cant instrument my way out of.

people who are serious about software forge their own GPUs in a backyard foundry and etch the transistors with a homemade EUV laser

all of this @AnthropicAI watermarks talk makes me feel like every gibberish opus 5 output was entirely intentional. "this lifts identity out of the traversal, which means ordering survives the collapse instead of being re-derived from whatever the caller happened to be holding"

ok the new @AnthropicAI watermarks are getting a bit out of hand

natural language is too alive to ever completely hide its fingerprints. If the text needs to be readable and high quality then there are always going to be massive architectural weakness built into it. eu wasting everyone's time. someone will reverse engineer it in no time.