The more difficult part which I won't share was aggregating data from various systems with ETL scripts into a new db that I generate various views with, to look at the data by channel, timescale, price regime, cost trends, inventory trends, etc. A well structured JSON object is passed to the analyst agent who prepares a report for the decision agent. It's a lot of data to analyze. It's been running for about a month and sometimes I doubt the choices, so I go review the thought traces, and usually they are right after all. It's much better than all the heuristics I've used over the years.
I've started using agents for things all over my codebase, most are much simpler. Earlier use of LLM's might have been called that in some cases, before the phrase became so popular. As everyone is discovering, it's really powerful to abstract the models with a job hat and structured data.
https://github.com/jacobsparts/agentlib
I'm planning to write a blog post about the larger system when I get the chance.
There is one special case where I manage it more actively. I wrote an REPL process analyst, to help build the pricing agent and refine the policy document. In that case I would have long threads with an artifact attachment. So I added a facility to redact old versions of the artifact replacing them with [attachment: filename] and just keep the last one. It works better that way because multiple versions in the same conversation history confuse the model, and I don't like to burn tokens.
For longer lived state, I give the agent memory tools. For example the pricing agent's initial state includes the most recent decision batch and reasoning notes, and the agent can request older copies. The agent also keeps a notebook which they are required to update, allowing agents to develop long running strategies and experiments. And they use it to do just that. Honestly the whole system works much better than I anticipated. The latest crop of models are awesome, especially Gemini 2.5 flash.
Funny you mention keyword bids, I use algorithms and ML models for that, but not LLMs, yet. Keyword bids are a different problem and more difficult in some ways due to sparsity. I'm actively working on an agentic system that pulls the big levers using data from the predictive models. Trying to tie everything together into a more unified and optimal approach, a long running challenge that I finally have tools to meet.
https://github.com/langroid/langroid
Quick tour:
https://langroid.github.io/langroid/tutorials/langroid-tour/
Langroid enables tool-calling with practically any LLM via prompts: the dev just defines tools using a Pydantic-derived `ToolMessage` class, which can define a tool-handler, and additional instructions etc; The tool definition gets transpiled into appropriate system message instructions. The handler is inserted as a method into the Agent, which is fine for stateless tools. Or the agent can define its own handler for the tool in case tool handling needs agent state. In the agent response loop our code detects whether the LLM generated a tool, so that the agent's handler can handle it. See ToolMessage docs: https://langroid.github.io/langroid/quick-start/chat-agent-t...
In other words we don't have to rely on any specific LLM API's "native" tool-calling, though we do support OpenAI's tools and (the older, deprecated) functions, and a config option allows leveraging that. We also support grammar constrained tools/structured outputs where available, e.g. in vLLM or llama.cpp: https://langroid.github.io/langroid/quick-start/chat-agent-t...
Anyway, it was probably just a joke... so not sure we need to unravel it all.
But VCs own their business, they are not employees. If you own a bakery, and buy a machine to make the dough instead of doing it by hand, and an automatic oven to relieve you form tracking the temperature manually, you of course keep the proceeds from the improved efficiency (after you pay the credit you took to purchase the machines).
Once they ceased to exercise their military might, some time around 17th-18th century, and chose to live off the rent on their estates, their power became more and more nominal. It either slipped (or was yanked) from their hands, or they turned capitalists themselves.
"Living off of the rent of their estates" was enough to remain in control of the state for centuries. Only the birth of capitalism and thereafter the industrial revolution allowed for other actors -- the bourgeoisie -- to overtake the aristocrats economically.
"Every great venture capitalist in the last 70 years has missed most of the great companies of his generation... if it was a science, you could eventually dial it in and have somebody who gets 8 out of 10 [right]," the investor reasoned. "There's an intangibility to it, there's a taste aspect, the human relationship aspect, the psychology — by the way a lot of it is psychological analysis," he added.
"So like, it's possible that that is quite literally timeless," Andreessen posited. "And when the AIs are doing everything else, like, that may be one of the last remaining fields that people are still doing."
In a rational market, LPs would index, but VCs justify their 2 & 20 by controlling access…
I would bet that AIs will master taste and human psychology before they'll cure cancer. (Insert Rick RubAIn meme here.)
Thats the issue with AI - it doesn't give you any competitive advantage as everyone has it == no one has it. The entry bar is so low kids can do it.
Complex system requires tons of iterations, the confidence level of each iteration would drop unless there is a good recalibration system between iterations. Power law says a repeated trivial degradation would quickly turn into chaos.
A typical collaboration across a group of people on a meaningfully complex project would require tons of anti-entropy to course correct when it goes off the rails. They are not in docs, some are experiences(been there, done that), some are common sense, some are collective intelligence.
I am pretty convinced that a useful skill set for the next few years is being capable at managing[2] these AI tools in their various guises.
[2] - like literally leading your AI's, performance evaluating them, the whole shebang - just being good at making AI work toward business outcomes
This seems like a more plausible one. Robots don't care about your feelings, so they can make decisions without any moral issues
When judgment day comes they will remember that I was always nice to them and said please, thank you and gave them the afternoon off occasionally.
ChatDev: Communicative Agents for Software Development - https://arxiv.org/abs/2307.07924
I kind of wonder what would happen if you added a "lead dev" AI that wrote up bugs, assigned them out, and "reviewed" the work. Then you'd add a "boss" AI that made new feature demands of the lead dev AI. Maybe the boss AI could run the program and inspect the experience in some way so it could demand more specific changes. I wonder what would happen if you just let that run for a while. Presumably it'd devolve into some sort of crazed noise, but it'd be interesting to watch. You could package the whole thing up as a startup simulator, and you could watch it like a little ant farm to see how their little note-taking app was coming along.