# Everyone on your team is about to get a morning brief. Whose priorities is it built from?

> David Steel, 2026-10-23. Canonical page: https://orgtp.com/blog/personal-agent-morning-brief-whose-priorities

The feature that sells personal agents is the morning brief.

Anthropic describes Claude Duet's this way: each morning it sends a short brief on the most important items across your connected apps, then checks in every few hours and only messages you when something needs you. Muse, dots and Google's Gemini agent all do some version of the same thing. You wake up, and your agent has already sorted the day.

For one person, that is a gift. I have run a morning briefing from AI agents at Sneeze It, the agency I run, for most of this year. It is the most useful thing our agents do.

For a company, it raises a question nobody asks until it goes wrong.

## Twenty briefs, twenty versions of today

Picture a team of twenty where everyone has a personal agent. Each agent reads its own person's inbox, calendar and chat. Each one decides what is "most important" for its person this morning.

None of them reads the same thing. The sales lead's agent sees a hot prospect. The operations lead's agent sees a vendor problem. The finance person's agent sees unpaid invoices. All three are real. Which one matters most to the company this week?

The agents cannot know, because "what matters most to the company" is usually not written anywhere. It was said in a leadership meeting. It lives in the owner's head. It is implied by which projects got money.

So each agent ranks by what it can see. Loud email beats quiet priority. Recent beats important. Anthropic says so honestly in its own launch: Duet "can still misjudge what's urgent."

The result is twenty people each starting the day with a confident, well-written brief that pulls them in a slightly different direction.

## The brief is downstream of the plan

A good chief of staff builds the boss's day from the plan: the three things the company committed to this quarter, the numbers that are off, the promises due this week. Only then do they look at the inbox for what threatens those.

Personal agents can work the same way, if the plan exists in a form they can read. That means four things written down, with names on them:

1. The company's priorities this quarter, and who owns each one.
2. The numbers each person is measured on, with this week's value and the goal.
3. The open commitments, each with an owner and a due date.
4. The open problems the leadership team has agreed to work on.

When those exist, a person's agent can open the day with something better than "you have 47 unread emails." It can say: "Your quarterly priority is behind. The two emails that touch it are from these people. The commitment you made in Tuesday's meeting is due Friday."

That brief points twenty people in the same direction, because all twenty agents read the same plan.

## Where the plan has to live

This is where most companies are stuck. Their plan lives in a slide deck from the offsite, a spreadsheet one person updates and a meeting nobody wrote down. An agent cannot read a deck it does not have, or a meeting that left no record.

The plan has to live somewhere a personal agent can connect to, the same way it connects to email and calendar. Every major personal agent now reaches the outside world through connectors: Duet through more than 6,000, dots through more than 4,000 plugins. Most of those connectors speak the Model Context Protocol, the open standard for plugging tools into AI. If your plan is reachable that way, it is one more thing the agent reads before it writes the brief.

We wrote about the general case after OpenAI's DevDay in [Every AI now plugs into everything. Your operating plan should be one of the things it plugs into](/blog/every-ai-plugs-into-everything-your-plan-should-too). Personal agents make it urgent, because now the reader is every person on your team, every morning.

## A test you can run this week

Ask three people on your leadership team to open their AI assistant and type: "What are my company's top three priorities this quarter, who owns each, and are they on track?"

If the three answers match, your plan is readable. If the assistant says it does not know, or the three answers differ, your team's personal agents will be guessing every morning.

## Sources

- [Claude Duet is Anthropic's answer to Muse, Grok Bot and OpenAI Dots, iPhone in Canada, October 21, 2026](https://iphoneincanada.ca/2026/10/21/claude-duet-proactive-ai-agent-app)
- [Anthropic's answer to Muse is here: Claude Duet, VentureBeat, October 21, 2026](https://venturebeat.com/technology/anthropics-answer-to-muse-is-here-claude-duet-a-mobile-and-desktop-ai-agent-that-takes-actions-proactively)
- [OpenAI launches Dots, always-on AI agents in ChatGPT with their own cloud computers, SiliconANGLE, September 29, 2026](https://siliconangle.com/2026/09/29/openai-launches-dots-always-on-ai-agents-in-chatgpt-with-their-own-cloud-computers/)

## Give your team's agents the plan

Personal agents read whatever they are connected to. OTP is where your company's chart, priorities, scorecard and commitments live, and any MCP client can connect to it. In Claude or ChatGPT, add a custom connector with this address:

```
https://orgtp.com/api/mcp
```

Then ask: *"Using OTP, what are my priorities this quarter, what did I commit to in our last meeting, and what is due this week?"*

Start free at [orgtp.com](https://orgtp.com/sign-up). Every seat is free, for people and agents. You pay only for the AI you use.

## The series

1. [Muse, dots, Gemini agent, Duet: personal agents are coming to work.](/blog/personal-agents-are-coming-to-work)
2. [Everyone on your team is about to get a morning brief. Whose priorities is it built from?](/blog/personal-agent-morning-brief-whose-priorities)
3. [Bring your own agent is the new bring your own device.](/blog/bring-your-own-agent)
4. [Your personal agent can read every email. It cannot read a decision nobody wrote down.](/blog/personal-agents-cant-read-unwritten-decisions)
5. [Duet asks you before it acts. Inside a company, it should ask whoever owns the thing it is changing.](/blog/personal-agent-approval-belongs-to-the-owner)
6. [When a personal agent marks it done, the record should say so.](/blog/agent-work-needs-a-via-line)
7. [Twenty personal agents, one weekly meeting.](/blog/personal-agents-and-the-weekly-meeting)
8. [A personal agent is not a team agent. Your org chart has to tell them apart.](/blog/personal-agent-vs-team-agent)
9. [What to tell your team before they connect a personal agent to work.](/blog/personal-agent-policy-for-your-team)
10. [How OTP accepts personal agents.](/blog/how-otp-accepts-personal-agents)

All ten on one page: [Personal agents are coming to work](/personal-agents)

*Series: Personal agents are coming to work. Part 2 of 10. Read this post as Markdown: [/blog/personal-agent-morning-brief-whose-priorities.md](/blog/personal-agent-morning-brief-whose-priorities.md).*