@nbaschez Close to a piece of this. I’m building @pathmodeio as the product-decisions version: human-owned intent specs any agent can read over MCP.
The scarce layer isn’t context storage, but judgment: what should change, what must not break, and why.
Code is downstream of intent.
Pathmode + @github closes the loop: read your repo while you draft the spec, push it to a GitHub Issue, and auto-flip the intent to "shipped" when the PR merges.
https://t.co/ILOsua4BgM
Reading State of AI Design 2026. Designers say judgment is what they hold on to: framing, rationale, systems thinking. All above 60%.
But judgment isn't preserved by keeping it close. It's preserved by writing it down in a form the next person can use.
https://t.co/Ha8Iw3BmW0
Just five weeks ago, “Intent” was a product. Today, it’s a workflow modifier inside their product.
Intent isn't a developer workflow category. It's a product judgment layer.
We're excited to share that Intent, our newest multi-agent orchestration platform, is live on Product Hunt today. If you’ve been enjoying what we’re building, it would mean a lot if you could support us🥳
Check us out here 👉 https://t.co/Pwp9mf3NBD
@rauchg https://t.co/3KgBKvAMfN — built to cure my own vibe-coding hangovers.
Agents execute literally. Specs are the new ceiling. Pathmode versions intent + evidence and serves it to Claude Code / Cursor over MCP.
Primarily Claude.
Introducing PostHog Code, the product editor that:
- Understands your product
- Identifies usage patterns
- Triages bugs and errors for you
- Creates PRs to fix them
- Continuously monitors and improves your product
Join the waitlist: https://t.co/pTuwqCzo1I
Pathmode now reads your site.
Paste a URL on https://t.co/Cf7oUiILDQ. You'll see your Product, Evidence, and the questions your homepage raises — before you create an account. Pathmode reads the site. You write the Intent.
Available now.
What excites me most is how agents and AI are making @linear vision more true: the product building system for modern companies.
We’ve spent years building the foundation around context & goals, (customer feedback, docs, projects, issues, initiatives), coordination, and planning.
Now soon, we will be extending that to execution: writing code, reviewing code, automating code writing and product management.
The product system would be become:
- capturing requests and feedback from many channels in to one place, with their full context to understand customer needs and make plans.
- agent interface to that shared interface to company context and codebase knowledge to ask questions or task work
- orchestrating multiple Linear agents and other agents in that shared environment to to build from the context, or from the problems you see
- automatically noticing product gaps, routing problems, triaging, and resolving work as it comes in
If you want to work applying AI, agents to the best product orgs in the in the world, we’re hiring across engineering, design, and product.
also btw:
- Been profitable for years. We have made money, not lost money over the years
- Growth accelerating quarter after quarter.
- Employee tender offers when possible.
DMs open.
Shipped: AI Spec Review in Pathmode.
Critique your spec across 6 dimensions — outcomes, edge cases, verification, constitution conflicts, evidence grounding, drift — before you hand it to a coding agent.
Catch the half-baked work before the agent runs it.
https://t.co/Z2gOllbMqQ
Olen viime aikoina kirjoitellut siitä, millaisena näen tulevaisuuden designerin roolin. Meillä @Terveystalo:ssa se tulevaisuuden designer on jo olemassa, ja nyt haetaan tiimiin lisävahvistusta.
https://t.co/b96BOO51Iq
Anthropic just made specs load-bearing.
The "Outcomes" feature in their Managed Agents launch is the most underweighted part of the announcement. Why it matters — even if you'll never touch the Anthropic platform.
“Velocity used to separate teams, but now velocity is becoming a commodity. What’s left is the judgment behind what’s being built.”
https://t.co/1JkcRQhY8Q
Karpathy routes more tokens into knowledge than code now. Most product teams still do the opposite — sprinting to build before they understand what to build. That gap is where products fail.
Karpathy just proved the Intent Layer thesis from the research side. He’s spending more tokens on knowledge than code. The same shift is happening in product development. The bottleneck isn’t building, it’s structured context. That’s what @pathmodeio is.
Wow, this tweet went very viral!
I wanted share a possibly slightly improved version of the tweet in an "idea file". The idea of the idea file is that in this era of LLM agents, there is less of a point/need of sharing the specific code/app, you just share the idea, then the other person's agent customizes & builds it for your specific needs.
So here's the idea in a gist format: https://t.co/NlAfEJjtJV
You can give this to your agent and it can build you your own LLM wiki and guide you on how to use it etc. It's intentionally kept a little bit abstract/vague because there are so many directions to take this in. And ofc, people can adjust the idea or contribute their own in the Discussion which is cool.