Ask HN: Do you have any AI agent success stories? | Hacker News Reader

Ask HN: Do you have any AI agent success stories?

3 pointsbaalimago2 comments

Firstly to clarify what I mean with AI agent: A script which utilizes an LLM is not an agent. It's automation, alternatively a "workflow" (according to Anthropic). An AI agent is a system which is handling complex semantic input by gathering information about the input via tooling + memory and then lastly process it into some "judgement based" response.

The shell script which writes a poem about the current weather in your city -> automation.

A chatbot for customer support -> agent. Codex/Claude Code -> agent.

Primary difference being that an agent build its own context depending on the task that it needs to solve.

I've heard a lot of buzz around AI agents, but I've yet to see that many success stories where they fit nicely and provide more value than what they cost to develop and maintain (exception being coding agents). So, please share your AI agent success stories!

I work for a fintech. We're currently building agents to manage basic human labor tasks that are time consuming (think: initial credit analysis, initial web research for AML, etc.). Chatbots are a waste of the actual power behind engineering with LLMs. With tool usage, and detailed instructions, we're easily able to direct the agents to do very useful work. While it has been possible to build these kinds of automations previously, the costs (time and opportunity) would have been astronomical to capture and encode the reasoning in a programming language. Now we can simply ask the robot in plain language to do the task. It won't reduce our headcount, but it will enable scaling the business with way less hands. And the cost to develop is very minimal. The first MVP for the credit analysis robot was vibe coded in an afternoon using an off-the-shelf lib. Doing the actual engineering is trivial context management and tool integration. The challenge is having the kinds of problems we do where these kinds of solutions make sense. In finance and insurance, there are tons of these manual human tasks that could benefit from the robots. I expect this space to explode in the next couple of years.

No i still don't really know how to create/use AI agents. I just use chatpgpt and roocode primarily.

Reply on news.ycombinator.com