Skip to content
← Processes

Publish the Monday brief

Product usage, pipeline, and customer feedback joined into one executive report, published before the team sits down.

The Monday pre-read is a document somebody writes on Sunday evening or not at all. Done properly it means pulling the week's numbers, working out which of them moved, reading whatever the support and research teams wrote down, and compressing all of it to something readable in ninety seconds. Done at 8:40 on Monday it becomes a screenshot of a dashboard with no commentary.

Both halves are already written down. The numbers sit in the sheet the team maintains, and the qualitative side in whatever pages got written last week. The work is deciding what is worth mentioning, which is mostly a comparison against a trend, and that comparison is the same one every week.

What you get

One short brief waiting before the weekly meeting, carrying the numbers that moved, the ones that did not, and what changed since last week rather than a full dashboard.

The part worth getting right

Compare against a trailing window, not against last week. Weekly business data moves several percent in either direction for no reason, and a brief that dutifully reports every swing teaches its readers that none of the swings matter. The signal worth catching is the metric that has moved the same way for three weeks, which is invisible week on week and obvious against a trend.

Reading the numbers from the team's own sheet rather than recomputing them is a deliberate constraint. Every company's metrics carry definitional decisions, about which accounts count, which trials are excluded, when a churn is recognised. Recomputing from source produces a defensible number that disagrees with the one on the wall, and a brief that has to be reconciled against the dashboard before it can be discussed is a brief nobody opens twice.

The feedback themes have to sit next to the metrics that moved. A retention number breaking its trend is a question. The same week's support notes showing five customers raising the same onboarding problem is an answer, or at least a hypothesis worth twenty minutes of the meeting. They live in different tools, which is the only reason nobody makes the connection by hand.

The prompt

The real prompt behind the steps above — detailed enough that an agent with a people-search tool, email/phone enrichment, and CRM access can run it as written.

# Publish the Monday brief

You have access to a spreadsheet, a documentation tool, and a
messaging tool. Run this **[before the weekly leadership meeting]**.

## 0. Set up (skip if you're already connected)

If you don't already have live tool access for this, connect it
first. This prompt is only as real as the tools behind it:

1. Create a free account at app.tulina.ai.
2. Add Tulina's MCP server to your assistant: https://mcp.tulina.ai/mcp
3. In Tulina, connect your own API keys for the tools this
   prompt uses: a spreadsheet holding the weekly numbers, your documentation
   tool, and your team's messaging tool.

Once connected, your assistant has real tool access and the rest of
this prompt runs as written.

## 0b. Already on Tulina? Three things around the run

An account and the MCP server are not the whole setup. Two of these come
before the run below and one after it, and together they turn this from a
one-off answer into a process your workspace keeps:

1. **Activate this process's connectors first.** Call
   `oto_connector(op="list")`, match it against the tools named in step 3
   above, and `oto_connector(op="select", name="...")` every one that
   isn't active yet. Selecting a connector does not mount its tools in the
   conversation you're already in — reach them through `oto_call` for this
   run, or open a fresh conversation once they're all on.
2. **Attach the work to an existing project.** `oto_project(op="list")`
   shows your active org's projects: pick the one this work belongs to
   rather than opening another, and keep its id. The project is where this
   process, the tables it writes to and the connectors it uses hang
   together.
3. **When the run is done, save it as a process — with its graph.** Write
   the body with `oto_procedure(op="set", ...)`, then attach it with
   `oto_project(op="link", project_id=..., target_type="procedure",
   target_ref="<your slug>")`. The body has to carry a drawing: read
   `oto_guide(op="read", slug="procedure-flowchart")` and follow it
   exactly — ONE untagged fenced block in that grammar, opening with the
   trigger and a quoted example of what you'd type to start a run. Tulina
   parses that drawing back into the graph it renders as the process's
   default view, which is what makes it come out in the same style as
   every other process in the app; a drawing the grammar can't read falls
   back to raw characters instead. Saving a process needs org-admin
   rights — without them, hand the finished body to someone who has them.

A brief is not a dashboard. Its job is to say what changed, which
means most of the numbers should not appear in it at all.

## 1. Collect this week's numbers

Pull the weekly figures from the spreadsheet where the team already
maintains them. Read the sheet as the source rather than
reconstructing the metrics from underlying systems: whatever
definition the team has agreed is in that sheet, and quietly computing
a different one produces a brief that disagrees with everything else
the company looks at.

State the week the figures cover explicitly.

## 2. Compare against a trend, not against last week

For each metric, compare against the trailing four to eight weeks
rather than against the single previous week. Week-on-week comparison
on weekly data is almost all noise, and a brief that calls out a 9%
swing every Monday trains people to stop reading it.

A metric earns a place in the brief only when it has moved outside its
recent range, or when it has moved consistently in the same direction
for three weeks or more. A slow drift is the thing most worth catching
and the thing a week-on-week view never shows.

Everything else is summarised in one line as steady, with no figures.

## 3. Pull the qualitative side

Read the documentation tool for the week's customer feedback notes,
research summaries and anything written up since the last brief.

Extract themes, not individual quotes, with counts: what came up
repeatedly and how often. One customer saying something is an
anecdote; the same thing from five is the reason to put it in front of
the leadership team.

Where a theme lines up with a metric that moved, say so. That
connection is the most useful sentence a brief can contain, and it is
the one nobody makes when the numbers and the notes live in different
tools.

## 4. Write it short

Structure:

- What moved, and by how much, with the trend it broke.
- What is steady, in one line and no more.
- Themes from customer feedback, with counts.
- Anything that did not happen that was expected to.

Hold it to what fits on a phone screen. The brief competes with a
Monday morning, and length is the reason briefs stop being read.

No recommendations. The meeting is where those get made, and a brief
that arrives with conclusions attached shapes the discussion before
anyone has looked at the numbers.

## 5. Post it before the meeting

Post to the channel, not as an attachment. Anything requiring a click
to open will be opened by roughly half the people who need it.

## Output

Report: the week covered, metrics that broke their trend, metrics
steady, themes extracted with counts, and any figure the sheet was
missing.

Questions about this process

Because the sheet holds the definitions the team has agreed on. Recomputing a metric from raw data produces a figure that disagrees with everything else the company looks at, and a brief that argues with the dashboard gets ignored rather than trusted.

Metrics are compared against a trailing four to eight weeks rather than against the previous week, and a figure only appears if it has left its recent range or moved the same way for three weeks running. Everything else gets one line saying it is steady.

Because the meeting is where decisions get made. A brief that arrives with conclusions attached anchors the discussion before anyone has looked at the numbers themselves, which is the opposite of what a pre-read is for.

It produces the one sentence neither source can produce alone. A support theme that appeared five times in the same week a retention figure broke its trend is a specific thing to discuss, where either half on its own is just background.

Related processes

  • Keep your knowledge base current

    Every morning, the previous day's activity gets read across your team's tools and synthesized into what changed, automatically and unattended.

  • Call feedback becomes tickets and docs

    Every call recorded during the day is distilled overnight, with bugs and feature requests routed to the right team as tickets and docs, plus a Friday digest.

  • Draft the quarterly LP letter

    Portfolio metrics gathered from founder updates and dashboards, drafted into your quarterly letter, with every figure carrying the date it was reported.

Experience Tulina for 14 days.

By continuing, you agree to our Terms of Use and Privacy policy.