drew dillon

Today we're launching Brief into open beta. Your AI Product Navigator. The product layer for AI-powered teams. Built with 100+ teams shipping with agents.

"We just connect Claude Code to our call notes."

Partially why there's a proliferation of dev tools is that visual QA hasn't gotten any easier.

A PRD that says "user can manage their team" is one sentence and four screens. Where the list lives. What the invite step looks like. Where you land after a delete. The agent has to invent all of it. It will invent badly. Brief lets you wireframe inside the PRD itself, in a format the coding agent can read. The structure becomes part of the spec.

@adelbucetta We actually use @usebrief for the whole spectrum. From ideation to PRD writing to individual tickets.

@drewdil that's true but also doesn't consider the complexity of some tickets what if it's a 5-page doc or multiple dependencies? that's not something you can just recreate in slack

The reason bugs sit isn't laziness. It's that filing a "real" ticket means leaving the conversation, opening another tab, and recreating context that was right there in Slack two minutes ago. Don't make people switch tools. Bring the tool to where they are. AI Ships. Brief Navigates.

Opinionated product context means AI agents are 49% more likely to actually build the right thing. We proved it. 👀

@petergyang Fortunately or unfortunately, I think it's Slack.

All agentic coding apps are starting to look the same. This is the latest Antigravity app from IO, which looks pretty slick. But I think this UI is only optimized for a single person to work to agents. The UI for teams and orgs to work well with agents still needs to be figured out.

Dumping data into a vector store and calling it "context" is just search with extra steps. Brief reads your sources with a product lens. Open a ticket about a customer concern, the related PRDs and past fixes are already wired up. AI Ships. Brief Navigates.

@YengT9 Let's goooooooooo

70,000 members. 162 countries. 4 months. Introducing Lekondo THE THIRD SPACE FOR FASHION 🌎 Now available on iOS and Android

yooooo, @usebrief-@NousResearch-@linear-Codex powered dark factory run from @SlackHQ . boutta crank this sucker to 11.

how many tokens are spent every day relitigating context you already told a different agent?

@gokulr Did they say the words “em dash” as a sentence break 🤣

THE QUIET PART I met an entrepreneur today who actually said to me "But here's the quiet part that nobody says out loud". I was LOLing so hard.

I'm an Anthropic outage hipster. always into them before they get cool.

Treating your agent's context window like a junk drawer is why it keeps making the same mistakes. Don't dump. Hand it a book report.

Your agent doesn't need every file. It needs the right ones for this ticket. Brief's CLI onboards any coding agent in one command, then hands it a focused "book report" per task. Relevant context only, kept outside the context window. Full context. Full window.

a customer was just saying the same about the @usebrief bot. because it's broader, has intent and memory, it's just a lot more useful.

Coding agents do the same thing. They interrupt you. Brief lets them ask Brief instead. Less interrupts. Same answers.

Build phase was always a real-time interrupt loop. Engineers asked the PM when they hit something the PRD didn't cover.