← all playbooks

Start every morning with a short list of companies worth calling

A saved workflow that runs on your schedule and leaves a short, ranked list in your workspace each morning: the company, the reason to call today, and the person to call. Nothing is sent.

use when
you want the signal plays run for you on a schedule, as one short list each morning and not a query you have to remember
starts from
Just your niche

The prompt

Paste it into Claude Code or the Claude desktop app with Hyreflow connected. The first line tells your agent to use Hyreflow, so it reads the play, asks before it spends anything, and hands the work back to you.

paste this into Claude
Use hyreflow and set up a scheduled workflow that gives me a business
development brief every morning.

On <WEEKDAYS> at <TIME>, sweep <INDUSTRIES> in <GEOGRAPHY> for companies
with new <ROLE_TITLES> roles, a recent raise, or a new leader in <FUNCTION>.

- Qualify each company against my ideal client:
  <PASTE YOUR ICP, OR NAME YOUR BEST CLIENTS>.
- Cap the list at <N> companies, best first. For each, give me the reason
  it is on the list today, the source, and one person to call with their
  work email.
- Leave out any company you showed me in the last <DAYS> days, unless
  something else has happened there since.
- Save it as a workflow on a cron trigger. Tell me where the list will be
  waiting for me and which time zone the schedule runs in.

Run it once by hand now and show me the output and the cost per run before
you schedule it.

The workflow delivers a list and contacts nobody. If I ask for drafts
later, stage the outreach, do not send anything.

Replace every <PLACEHOLDER> with your own detail. Everything else can stay as written.

What you need first

  • A description of your ideal client, specific enough to be written into a filter
  • The market, role titles and leadership functions the brief should cover
  • At least one signal play already run by hand, so you know what good output looks like
  • A Hyreflow workspace with credits, because every scheduled run is metered

Tools it can reach for

The agent picks per step from what your workspace has. Nothing here is required by name.

What happens when you run it

Free steps are marked free. Anything that spends credits is marked, and the agent asks before the first paid run of any size.

  1. 1

    Agree what goes in the brief

    free

    Which signals, which market, your ideal client, how many companies, and how long a company stays off the list after you have seen it. A scheduled run cannot ask you questions, so they are settled here.

  2. 2

    Sweep the three signals

    credits

    Openings in your discipline, recent funding rounds and leadership appointments, each pulled for your market from a company signals source. Every pull is capped and charged per result, and anything older than your window is discarded.

  3. 3

    Qualify against your ideal client

    credits

    Size and geography are plain rules. The judgement on fit runs as a metered AI step, because a scheduled run has no assistant in the conversation to make that call for free.

  4. 4

    Rank, cap and hold back repeats

    free

    Companies with more than one reason to call go to the top and the list is cut to your number. Holding back companies you were shown recently is written in at this point, and the hand run is where you check it works.

  5. 5

    Find the person to call

    credits

    One company-scoped search per company on the capped list for whoever owns hiring in your discipline, then the work email waterfall, which stops at the first hit.

  6. 6

    Run it once by hand

    credits

    The workflow is saved with an on-demand trigger and called once, so you see a real list and what that run cost before any schedule exists.

  7. 7

    Put it on the schedule

    free

    The trigger becomes a cron schedule and the workflow is published. Each run after that is metered like the hand run, recorded step by step in the run history, and can be disabled whenever you choose.

What a run costs

Credits are spent per company the play actually works, and a lookup that finds nothing usually costs nothing. The two figures are the run where the first provider answers and the run where every lookup walks its full chain.

companiesif the first provider answersif every lookup walks the chain
25$2.121 credits$11110 credits
100$6.262 credits$40400 credits
500$28280 credits$1981980 credits
1,000$56560 credits$3963960 credits

Free before anything is charged

  • Agree what goes in the brief
  • Rank, cap and hold back repeats
  • Put it on the schedule

What moves the number

  • The channel. This play buys work email, because these are people you are approaching about work you want to win. A work address is the cheaper of the two to find.
  • Coverage on people search and work email. The chain stops at the first provider that answers, and only that provider bills.
  • How many companies survive the free filters. Everything dropped before the paid steps costs nothing.
  • The scoring and drafting steps run on the metered agent, charged on what they read and write rather than per company, so they sit outside this table.
  • Providers you connect with your own key. Those calls bill your account, not your credits.

An estimate, not a quote, priced at the volume credit rate. Your agent sizes the run against your own workspace and tells you what it will cost before it spends anything.

The cadence matters more than the query

Every signal play answers a question you have to remember to ask. Who is hiring. Who raised. Who has a new boss. Each gets run on a quiet afternoon and then not again for a month, which is how a signal with a short shelf life ends up stale.

The daily brief turns that round. One short list is waiting each morning: the companies worth calling today, the reason each one is there, and the person to call. It is the scheduled combination of three plays: find every company hiring in your market, reach a funded company before the roles go live and reach a new leader before they choose their recruiters. Read those for why each signal is worth a call.

A handful of companies you will call beats sixty you will scroll past, so the list is capped, ranked, and cleared of what you have already seen.

What you get back

A saved workflow in your workspace, and from each run a table: company, the reason it is there today with the source, how it fits your ideal client, and one person to call with title and work email.

A saved workflow is a fixed pipeline that Hyreflow runs for you on a trigger: on demand, from a webhook, or on a cron schedule. Every step is metered and every run is recorded, step by step, in the run history in the dashboard. The output is stored as a dataset you can open or download, and it waits there for you. Nothing in the workflow contacts anyone.

Variations worth knowing

Leave the contact step out. A cheaper brief names companies and reasons only, and you look up the person for the two or three you decide to call.

Weekly, not daily. The schedule is a standard five-field cron expression, so any set of days works. A narrow niche may not fill a list every morning.

Where this goes wrong

Scheduling a filter you have not tested. A workflow does not improvise. The judgement you would apply in conversation has to be written into it in advance, and a loose fit check produces a confident, wrong list every day.

Forgetting that it spends. A scheduled run does not ask permission each morning. You approve the shape and the cost of one run, then every run spends within the limits written into it. Check the run history early and disable the workflow if cost or quality drifts.

A list that repeats. A company on Monday's list should not be on Tuesday's unless something changed. Run the workflow twice by hand and compare the lists before you rely on it.

A brief nobody opens. If opening the list is not part of your morning, the schedule is only spending credits.

Treating it as a send list. These are companies picked by a filter. Each one still deserves a look before you write to anyone.

Questions

Why does it have to run by hand first?

Because a workflow does exactly what is written into it, every day, without judgement. If the fit check is too loose or the cap too high, a hand run shows you that on one list. A schedule shows you the same fault every morning and charges you for each one. The hand run also gives you the figure you need before agreeing to a schedule: what one run costs.

Does a scheduled run ask before it spends?

No, and it is better to be clear about that. The agent asks before it builds anything and shows you what one run cost. After that a scheduled run has nobody to ask, so it spends within the limits written into the workflow: the size of each pull, the cap on companies, one contact per company. If the cost per run is not one you would approve every morning, tighten the limits before you schedule it. You can disable the workflow whenever you want it to stop.

Where does the list arrive?

In your workspace. Every run is recorded in the workflow's run history in the dashboard, step by step, and its output is stored as a dataset you can open or download. Plan on opening it there as part of how you start the day.

How does it avoid showing me the same companies every day?

Two things. Anything older than your window is discarded on every run, so last month's raise does not resurface. And the prompt asks for companies shown in the last few days to be held back unless something else has happened there. Test that before you trust it: run the workflow by hand twice and compare the two lists.

Does the brief send anything to the companies on it?

No. The workflow in this play produces a list and stops. It does not email, message or enrol anyone. Outreach to a company on the list is a separate step that you start yourself, with its own review.