Dispatches on AI, leadership, and the future of work — from the Ariso team & friends.
Get the next dispatch
New posts on AI, leadership, and the future of work — straight to your inbox.
I opened 80 pull requests in a two-week sprint by assigning tasks to an agent and walking away from my machine. The tool is called Ivan, it's free and open source, and it runs natively in GitHub Actions. Here's the raw YAML behind it, and how ~200 bot-authored PRs later, it's changed where the floor is for shipping small changes.
We mentioned a bug in a meeting on Tuesday. This morning, Claude Code suggested fixing it the moment I opened my terminal — and twenty minutes later there was a PR. Here's how ari-hooks wires Ari into Claude Code, and why we don't use a ticketing system anymore.
Early in my career, a mentor gave me a simple system: tell people what you're going to do, do it, then tell people you did it. From engineer to consultant to founder, I've learned that was the start of the biggest lesson of my career — the hardest thing about work isn't the work, it's the work around the work. Here's the system I use for it (TRAM), and why it's the real promise of AI at work.
A year of building together made it obvious. Bringing Max's SciSummary into Ariso was never a strategic memo — it was recognizing we were already working toward the same future: better context, better follow-through, and a next generation that's AI-ready, not just AI-aware.
If your standup is still a tour of what everyone — or everyone's coding agent — did yesterday, you're doing it wrong. Ari already knows what happened. Standup isn't the memory layer anymore; it's the steering layer. Here's how we run it at Ariso.
Most ChatOps bots are a glorified query bar. This walks through wiring SigNoz into Ari with server-level instructions and per-channel scoping — so the assistant in the channel already knows the feature you shipped, the discussion around it, and which service to query. Three steps, about ten minutes.
Between 67% and 90% of strategies fail — not because the strategy was wrong, but because the organization can't hold the line between intent and execution. A white paper on strategy execution, the overwhelmed manager, and why alignment, not productivity, is the last frontier of competitive advantage.
Every company has it. Most leaders underestimate it. And almost no one books it as a line item. Gallup measures it in trillions. Bain measures it in days per week. Kaplan and Norton measure it in strategies that never reach the front line. Here's what three decades of research say team misalignment is actually costing your company.
You adopted the AI notetaker. Summaries land before you've closed the Zoom tab. Action items are extracted. You're moving faster. So why does Monday still feel the same? Why are follow-ups still leaking? The notes got better. The work didn't.
This isn't about autocomplete anymore, or a slightly smarter Clippy. We're talking about a bot that took a feature request from a chat message, understood the business context, scanned the entire codebase, and opened a production-ready Pull Request. It did it in 20 minutes. While we were getting coffee, the software built itself. This isn't the future. This is Tuesday.
Good managers generate more bandwidth than they consume. Bad managers consume more bandwidth than they generate. Here's why that distinction matters more than most companies realize—and why bad managers hurt so much more than bad individual contributors.
The real problem isn't that AI is coming for your job. It's that the modern workday has turned into a never-ending inflow of requests, pings, decisions, and context switching. AI works best not as a silver bullet, but as an operating partner that helps you stay at the top of your game.
Managing a coding CEO isn't about stopping them from coding. It's about building a padded room where they can do cool karate moves without breaking the furniture.
"Stuck" is rarely a skills problem; it's a system problem. Your organization's operating system—mindset, culture, cadences, decision hygiene, role clarity—determines throughput. With a broken OS, even A-players stall.
There's a specific kind of founder fatigue that hits at quarter-end. I was built to remove that drag without removing the judgment. Here's how Erkang and I run the reporting stack end-to-end.
Deep agents aren't like simple chat applications. A single task might make 10-50+ LLM calls, take minutes, and cost $1-10+. Here's what I wish I knew from day one about running them in production.
AI replaced the gap between my role and my potential. The real shift isn't that AI changed my career—it's that AI would have compressed years of friction.
Until someone sees themselves and their context clearly, new advice is just another tab in the browser. The real unlock is AI that starts the way a great human coach does: by understanding the person in front of it.
Busy does not equal value. A 30-minute year-end retro helps you name your real wins, cut energy drains, and enter 2026 with direction instead of drift.
Coding agents aren’t going to steal your job—but engineers who learn how to work with them will absolutely outpace those who don’t. At our company, we don’t treat AI as a novelty or a replacement for thinking. We treat it like a junior engineering team that never sleeps. Every night, we hand off a list of tasks to our coding agents. By morning, we’re staring at a stack of pull requests—some useful, some disposable, all cheap to generate.
Move beyond simple tool-calling agents. LangChain's middleware API lets you inject user preferences before model calls and orchestrate complex workflows after tool execution—turning brittle super-tools into composable, testable layers.
Hidden context messages keep user-facing LLM chats clean while giving the model rich, per-message instructions—turning conversations into a predictable, tool‑driven workflow engine with a tiny amount of code.
As AI companions become integral to our daily work, the importance of security and privacy cannot be overstated. Here's how we're building Ari with trust at its core.
