Viewing profile — aluzzardi

Thank you, appreciate it! Regarding scoping: In our case, the agent loop runs in the same way as our API server does (as in, it’s a multi tenant service running in a container some…

Author here. I should have made it more clear that the article is about agent / harness building (not about running third party agents). > I barely trust the harness more than the …

Author here. I’m worried about the same (models tuned for specific harnesses). We actually work around that by respecting the “contract”. For instance, our harness’ Bash signature …

Author here. This is an interesting and novel field, so I’m not pretending I know the answers, but this is what worked for us :) At the end of the day, and oversimplifying things: …

Author here. I think the confusion is that “agent” is used for two very different things: - building an agent - an “agent” product/runtime (Claude Code, etc) In the first case, the…

Author here. In my opinion, the main driver here is how fast models have evolved in the past 12 months. It makes the architecture of everything around them obsolete, very fast. We …

Author here. Because of parallelism and non determinism. This problem is quite common and not limited to memories. For instance, Claude Code will block write attempts and steer the…

Author here. My definition is: you take an agent, remove the model and you’re left with the harness. Tools, memories, sandboxing, steering, etc

Author here. Depending on how it’s designed, the harness itself doesn’t need any sandboxing. At the end of the day, it’s a “simple” loop that calls an external API (LLM) and receiv…

It started with Sonnet 4.0 as a single agent and now it’s a mix of Opus 4.6 and Haiku 4.5 agents. Opus plans the investigation and orchestrates the searches. Haiku is the one actua…

> it's not magic and you need to make the job of the agent easier by giving it good instructions, tools, and environments. This. We had much better success by letting the agent pul…

There are 2 layers of compression: - ZSTD (actual data compression) - De-duplication (i.e. what you're saying) Although AFAIK it's not "just point to it" but rather storing sorted …

Mendral co-founder and post author here. I agree with your statement and explained in a few other comments how we're doing this. tldr: - Something happens that needs investigating …

From our experience running this, we're seeing patterns like these: - Opus agent wakes up when we detect an incident (e.g. CI broke on main) - It looks at the big picture (e.g. whi…

> My experience with LLM generated SQL in OLTP and OLAP platforms has been a mixed bag Models are evolving fast . If your experience is older than a few months, I encourage you to …

We've actually started to gather metrics this week to write that exact post :) Coming soon!

Mendral co-founder here and author of the post. This is an interesting approach. I definitely agree with the problem statement: if the LLM has to filter by error/fatal because of c…

Post author here. Yes, it works really well. 1) The latest models are radically better at this. We noticed a massive improvement in quality starting with Sonnet 4.5 2) The context …