Agents
Shape a job once, then hand it to an agent: a teammate that runs it with its own tools and knowledge, wherever the work shows up.
Somewhere in your week there's a job you've already figured out: pull the pipeline, check it against last week, write it up the way the team likes it. An agent is the teammate you hand that job to. It carries the brief, the tools to do the work, and the knowledge to do it your way, and it's on call wherever the work shows up.
Shape the job once, then hand it to an agent
The agent runs it with its own tools and knowledge, wherever the work arrives: a thread, a schedule, your team's Slack. Same teammate, same standards, every time.
When a job deserves an agent
A fresh thread is enough for a one-off question or unfamiliar work. Create an agent when the responsibility itself has become reusable.
The same result is needed again
A weekly pipeline brief, support triage, launch production, or another job with a recognizable finished result.
The work follows a stable brief
The role uses recurring standards, tools, source material, or judgment that would otherwise need to be explained in every thread.
The work keeps finding you
You start it every week, the calendar starts it, teammates ask for it, or a system sends the same kind of event.
The agent gives that responsibility a name and a durable home. Update its instructions, connect an integration, or teach it a skill, and the next job reaches the same role wherever it starts.
What an agent brings to the job
Identity and instructions
The identity and standing instructions: what the job is, what good looks like, how to work with you. Written once, read on every run. See Configuration.
Model and limits
The default model, reasoning effort, runtime, subagent model, turn timeout, and context controls that fit the work. See Models and compute.
Tools and integrations
Built-in capabilities like search, browsing, and code, plus the apps you've connected: Slack, your CRM, your sheets. See Tools and integrations.
Knowledge and learning
The memories it draws on, the skills it follows, and the files you've attached, plus what it's allowed to learn from its own runs. See Knowledge access.
Autonomy and trust
Its usual execution mode, approval behavior, and permission to hand work to another agent. These settings control how independently it may act.
Invocations
A thread when you ask, a schedule when the calendar does, Slack when the team does. See Invocations.
The same teammate, everywhere it works
Put the same agent on a schedule, bring it into Slack, or give it an email address. Every run starts with the same instructions, tools, and standards. See Invocations for more on how you can run your agents from anywhere.
Schedule
Put recurring work on the calendar so the agent runs it on time and delivers the result where it belongs.
Slack
Bring the agent into channels and DMs so teammates can reach it where they already work.
Give the agent an inbox so forwarded messages can start work and replies can stay in the conversation.
What it remembers between jobs
Skills, memories, and documents are durable knowledge. The earlier conversation stays in its thread unless the agent is allowed to search it or preserve something it learned. See Knowledge for more detail.
Skills
Reusable methods for doing the work: a research process, report format, brand voice, API pattern, or checklist.
Memories
Small standing facts and preferences the agent can retrieve in future runs, without asking you to explain them again.
Documents
Larger bodies of reference material the agent reads and keeps current: structured, versioned, and available across the threads that should see it.
How an agent completes work
Take a Pipeline Analyst that owns the Monday morning brief. It knows the format leadership expects, can reach the CRM, and compares this week's pipeline with the last one.
Work reaches the agent
At 7 AM Monday, a saved schedule sends the recurring request. A thread, Slack mention, email, webhook, or another agent could start the same role through a different invocation.
The agent loads its working setup
The Pipeline Analyst brings the same instructions, model defaults, CRM connection, tools, reporting skill, memories, and autonomy settings to the run. The invocation supplies the request; the agent supplies how the work should be done.
The run happens in a thread
The thread holds the request, tool calls, working files, approvals, and finished brief. It remains the complete record even when the result is also delivered to Slack or another destination.
Review improves the next run
Open the thread from Activity. Clarify the instructions when the role was unclear, save a repeatable method as a skill, or preserve a standing fact as a memory.
Creating an agent
Click the + icon beside Agents in the sidebar or open the Agents directory to access the unified creator. The creation experience gives you three paths:
- Coworker starters: Choose from curated, pre-configured role starters for common jobs like meeting summaries, support triage, and research.
- Ideas for you: Explore tailored role suggestions with prefilled prompts designed for your team's workflow.
- Custom prompt: Describe the responsibility in plain English, with direct options to draft the agent through conversation or open the form editor.
The agent directory and card indicators
The Agents directory gives you visibility into every teammate in your account. Each agent card provides operational indicators at a glance:
- Knowledge chip: Shows the agent's memory scope (synced, curated, or standalone) and the count of learned memories it currently holds.
- Automation status pill: Displays active recurring schedules and Live mode status. Hover over the pill to inspect exact schedule intervals, next execution times, and Live check frequencies without opening the agent's settings.
Where to go next
Each part of the role has its own page. Start with whichever decision you're making.
Configuration
How an agent gets made and what a saved agent carries across its tabs.
Activity
The agent's run history: every thread it worked, live and interactive, in one list.
Models
Choose the reasoning model that fits the job, the speed, and the budget.
Agent delegation
Let one agent hand work to specialist agents and bring the result back.
Knowledge access
Control what the agent can see and whether runs can change what it knows.
Invocations
Where the agent is on call: schedules, Slack, email, webhooks, and more.
Skills
Teach a method once so the agent does specific work your team's way.
Memories
Save standing facts the agent should carry into future runs without re-explaining.