Lana Novikova

For agentic systems founders and dev tools founders: People do not want to pay for raw markdown and they shouldn't have to. But they may pay for orchestration, hosting, updates, collaboration, portability, analytics, and managed execution. These can be great businesses.

The current AI coding paradox: Agents increase throughput only when tasks are scoped tightly enough to run unattended. But if tasks are scoped that tightly, humans often become the bottleneck again. Because up to the point you described all the details, another task you're running in parallel is likely to be finished and in need of review. *thinking_dino*

@bunopus_en Welcome!

Happy to start new journey!

That’s why I think AI vendors should invest more in open interfaces: MCP for tools A2A for agents ACP for IDEs/editors Interoperability is a product feature.

Vertical integration looks great on strategy slides. Real teams are messy. Mixed (AI) tools, legacy systems, fragmented workflows. That’s why openness often beats owning the whole stack.

Frosted glass effect is an absolute delight I am using a custom theme inspired by the legendary @catppuccintheme Pleasure to my eyes ☕

@borshchguy Exactly. "Trust at 3am" usually comes down to very concrete things: previews, diffs, audit logs, permissions/guardrails, and rollback – much more than the agent loop itself.

spent way more time on the harness than the agents themselves. turns out 'can i actually trust this thing at 3am' is where all the real engineering goes

An AI agent is not a product because it can act. It becomes a product when a human can predict, inspect, and trust its actions. The industry is converging on this: the real product is the harness around autonomy. #agentorchestration #aiagent #agenticai

@getsome_air is also looking in this direction with the Agentic review, a feature that reviews the changes an agent has made and leaves comments which you then can send to other agents sessions to address. Pro tip: set a different model for review than you use for code generation 😉

Even VS Code’s agent UX points in this direction: the value is not just that the agent can act, but that humans can review changes, inspect the session, and decide what gets applied. That’s the harness around autonomy. code.visualstudio.com/docs/copilot/a…

I agree that a good code review is context-heavy as it combines code understanding with human intent. But "needs a lot of context" and "needs a frontier model" are different claims. Recent work on long-context and repo-level code tasks suggests a lot depends on retrieving the right code/API context and filtering noise, not on throwing the biggest model at the long diff. We have been experimenting with compacting the long diffs for git message completions, and medium-sized models (4b/7b) were enough. Frontier models still make sense for the hardest ambiguous cases, but I doubt they’re the right default forever.

@_Unsolved_ Well, for a good code-review model needs a lot of context. And I'd leave it to frontier models for now.

Half of AI product management isn't picking the best model. It's deciding what should never touch one – and what needs a much smaller one or even non-AI.

The PM skill isn't knowing AI. It's knowing which AI – and when "no AI" is the right call. The most important trade-off is rarely intelligence. It's frequency × latency × cost × trust.

Frontier models are for ambiguity, reasoning, generation. Everything else is an engineering choice you're paying for with latency and trust. Even high-hype features like AI code review could be done using smaller models.

AI’s next phase is not about better prompts. It’s about better operating models. I use Air as a PM to orchestrate agent workflows across research, synthesis, and execution. The value is not just productivity, it’s visibility, parallelism, and staying hands-on while agents work.

Some say 2026 will be the year of agent orchestration 😉

I was lucky to have early access, and I can say that it is now my daily tool for managing AI agentic (Claude code in particular) tasks, I use it both to bootstrap new pet projects and to maintain some older repos, I combine local tasks with the ones running in a git tree, run preview, review, and commit/push changes there. Please try, share feedback. Folks did a truly great job on this one #air #jetbrains

I'm speaking at #OSSummit Europe, 27 August in Amsterdam! Join my session "User Research in Open-source Projects" - learn how OSS projects can understand users without dedicated UX teams. Plus: free research toolkit! 🧵 sched.co/25Vxb

@sandark7 Как только увидела про поиск нового ведущего, моментально подумала про тебя 🔥🔥🔥🔥

3/8 Поэтому когда пару месяцев назад я увидел, что ребята ищут нового соведущего, мне это показалось очень символичным. Мы всегда шли параллельно, но по‑своему: я делал подкасты, отталкиваясь от людей и их историй, а они глубоко раскрывали темы через гостей.

Как я стал соведущим Подлодки В 2017 году в офисе Рамблера Егор Толстой, Стас Цыганов и Глеб Новик запустили свой подкаст. Мы тогда сидели вместе в опенспейсе на Даниловской мануфактуре, и примерно тогда же в соседней переговорке я создавал Frontend Weekend. Тред, лайк рт, 1/8