ClaireGz
Joined 3 years ago
Karma
93
Submissions
43
Member since
Jul 27
Recent submissions
Comment · 5 months ago
Yes exactly how I felt - I wanted to keep control on the tooling + on what's inside the context so Git felt like the most open tool to do this
Comment · 8 months ago
OpenAI recently shared how their internal data agent works: [https://openai.com/index/inside-our-in-house-data-agent/](https://openai.com/index/inside-our-in-house-data-agent/)
What interested me most wasn’t the model itself, but the surrounding system design: automated context retrieval, evaluation loops, and memory that improves the agent over time.
I’ve been experimenting with recreating a similar setup, but with a different goal: making the configuration more accessible for any company.
The result is an open-source YAML + Markdown framework where you define context sources, tools, and behavior explicitly instead of writing Python code. The idea is to make agent context easier to reason about, version, and iterate on, especially for data teams.
Repo: [https://github.com/getnao/nao](https://github.com/getnao/nao)
Would love feedback from people who have tried deploying analytics or data agents before.
Comment · 8 months ago
A lot of agent failures I’ve seen come from small details getting dropped when context is summarized or compressed.
How do you make sure the densification step doesn’t remove something that ends up being important for the task?
Comment · 8 months ago
Interesting direction.
One thing I keep seeing in practice is that “memory” problems are often less about storage and more about structure + retrieval strategy.
Vector search helps sometimes, but for a lot of agent workflows we’ve had better results with explicit context organization (files, metadata, rules) rather than semantic similarity alone.
Curious how you’re thinking about memory updates over time — append-only vs rewriting summaries?
Comment · 8 months ago
This is super helpful — most writeups skip over the actual communication steps, so seeing the All-to-All flow laid out makes it much clearer.
Curious from your experiments: at 1M+ context, does communication start dominating vs compute?
I keep seeing cases where bigger context windows are technically possible but don’t translate into better results unless the context is very structured, so I wonder where the real scaling limit ends up being in practice.