yarnnnyarnnn

How It Works

Your tools. Your context.
Their work. Your review.

yarnnn connects to your tools, keeps a shared knowledge base, and runs recurring work on schedule. Your agents accumulate context continuously. Your feedback sharpens future output instead of resetting every session.

Four steps. Then it runs itself.

From first context to a running system.

01

Connect your tools

Link Slack, Notion, or GitHub. Upload docs. Or just start talking — your agents learn from every source.

02

Describe the work

Tell yarnnn what you need in plain language. It assigns the right agent and sets the schedule.

03

Agents deliver

Your team runs on schedule — daily, weekly, monthly — whether you're online or not.

04

Review & improve

Check the output. Edit what needs changing. Your corrections teach the agents what you actually want.

01

Your team is ready at signup

You don't build agents from scratch. A researcher, analyst, writer, tracker, designer, platform connectors, and an orchestrator are waiting when you sign up.

Your roster

Nine agents, each with a specialty

Six universal specialists — a researcher, analyst, writer, tracker, designer, and orchestrator — plus platform connectors for your tools.

R
Researcher
Finds and evaluates sources
A
Analyst
Synthesizes patterns and meaning
W
Writer
Drafts polished deliverables
T
Tracker
Monitors signals and changes
D
Designer
Creates charts, images & visuals
S
Slack Bot
Reads your channels & threads
N
Notion Bot
Reads your pages & databases
G
GitHub Bot
Follows repos & activity
Y
YARNNN
Manages and orchestrates the team
How they work together
Accumulation specialists

Researcher, Analyst, Writer, and Tracker build up knowledge over time.

Production specialist

Designer creates charts, images, and visual assets for your deliverables.

Platform connectors

Read your Slack, Notion, and GitHub so the team always has fresh context.

Orchestrator

The agent you talk to. Manages tasks, coordinates the team, and explains what's happening.

Identity

They get smarter, not wider.

Each agent deepens its knowledge of your business over time. The more they work, the better the output.

02

Assign tasks

Describe what you need in plain language. yarnnn assigns the right agent, sets the schedule, and starts delivering.

Example task
W
Weekly leadership briefRecurring · Weekly

Slack and Notion keep the workspace fresh. The Writer assembles the week's changes, decisions, and risks into one Monday morning brief.

Task modes
Recurring

Runs on cadence indefinitely — daily, weekly, monthly

Goal

Bounded. Runs until success criteria are met

Reactive

On-demand or event-triggered

Competitor intelligence briefRecurring

Researcher + Analyst + Writer

Market research deep diveGoal

Researcher + Analyst

Meeting prep briefReactive

Tracker + Writer

03

Share context

Everything your agents know lives in a shared knowledge base. Every source you add makes their work more specific to your business.

Chat

Describe what matters through conversation

Docs

Upload files that agents reference

Slack

Channels, threads, conversations

Notion

Pages, databases, wikis

No one source is required. The system can start from conversation alone, then get more grounded as documents and connected tools accumulate.

04

You review. They learn.

Agents produce finished deliverables — formatted, attributed, and delivered on schedule. Edit what needs changing and your feedback becomes learned behavior.

PDF
weekly-status.pdf
PDF report
From:Content Agent
Subject:Weekly Team Recap — Mar 24
Key highlights this week:
Email delivery
Competitor Brief
R
Research Agent
Updated 2h ago
Intelligence brief
Feedback loop

The weekly recap is too long. Lead with risks and keep it under 500 words.

Got it. I'll update this task to lead with risks and cap at 500 words. That preference will carry forward to future runs.

Agents collaborate on tasks

Most tasks need one agent handling the full chain. For bigger jobs, multiple agents contribute domain expertise to a single task.

Example: Weekly leadership brief
S

Slack Bot keeps fresh internal discussion and decision context available

R

Researcher adds external moves and market shifts

W

Writer synthesizes it into one brief for leadership

Task combines their work into one brief, delivered Monday 8 AM

Why it gets better, not stale

Unlike chat tools that reset every session, yarnnn agents accumulate real understanding of your work.

Preferences

Your structure, tone, emphasis

Learned from your edits. Every correction teaches the agent what you actually want.

Patterns

Shared knowledge base

Fresh material from your tools, files, and prior outputs keeps every task grounded instead of starting from scratch.

Domain knowledge

Research, competitors, team dynamics

Accumulated findings that deepen with every task run. Can't be replicated by switching tools.

History

Every output feeds better output

Three months of accumulated work means every new output builds on everything that came before.

What people ask for

Describe the task in plain language. yarnnn assigns the right agent and handles the rest.

Give me a weekly digest from #engineering and #product.

Every Friday, send leadership a status report as a PDF.

Track these three competitors and give me a weekly update.

Before my meetings, generate a prep brief from Slack and Notion.

Research the AI agent market and deliver findings weekly until I say stop.

Summarize my week across all platforms every Friday.

Start with one task.

Sign up, connect your tools, and assign your first piece of recurring work.

Meet your AI team