I run a chunk of my commercial follow-up through agents now, and the wall I keep hitting isn't the writing — it's that the agent doesn't know where the relationship actually stands. Who owes whom a reply, whether we're warm or stalled, what the last real signal was. So I either hold all of that in my head (and I become the bottleneck), or I dump the whole thread history into context and the message comes back generic and expensive. For those of you running outreach or follow-up through agents: how do you represent relationship state as something structured the agent reads and acts on — a status field, a per-contact context file, a "next best touch" the system proposes? And just as important, how do you keep the output from feeling automated on the other end? I'm after the structural fix, not a better prompt. What actually lives in your setup, and what did you try that quietly failed?

Hi All, this is little different than the normal community post, but I trust the folks who have made it here because you don’t want BS sales pitch but something that works, ie the fundamentals… So my question is related to SEO and web traffic and how AI is changing that (I have zero experience in this area btw). I see a few different approaches to this such as refining content or making pages more ‘custom’ for users. But I also see people talking about having information accessible for the models themselves so that search results are pulling into the chats that people are using to get results rather than actually scrolling google search results pages. And then the wild card in my opinion is how MCP and those visual components can be inserted into chat windows now, continuing the ‘customization’ for the user (my guess is that UI will become even more user specific much like the text results we get back from the models currently). Not sure if all of that makes sense or is as connected as I think it is or will be. So my question: what are yall seeing and where can I start to double down on knowledge, much like Jake is doing here in the community. Thanks!

Ornith-1.0: the open-source coding LLM that matches Claude Opus 4.7 — and runs on your laptop. This open-weights agentic-coding model hits 77.5 on Terminal-Bench and 82.4 on SWE-bench Verified, beating Claude Opus on both, then ships a 9B size you can `ollama run` locally. MIT licensed, four sizes, and it taught itself the harness.