Find local points of sale

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.

# Find and qualify local points of sale

You have access to a local/web search tool and email. Run this for
**[target city or region]**.

## 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 — search and email.

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.

## 1. Search each target city three ways

- **Local listings:** run a places/maps search for your category and
  positioning in the city (e.g. "independent [category] shop
  [city]"), then two or three phrasing variants — by neighborhood, by
  style keyword — since no single query returns everyone.
- **Web guides:** search for "best [category] shops [city]"-style
  articles and roundups. These often list five to fifteen shops in one
  page that a places search alone would miss.
- **Scrape the guides you find:** pull the full list of names,
  addresses, and descriptions out of each article rather than reading
  it as prose — that's where most of the volume comes from.
- Record every candidate in one running list: name, city,
  neighborhood, address, website, and a free-text note. Don't create a
  new list per city — one running table, filtered by city, so nothing
  has to be re-found on a later pass.

## 2. Qualify before spending an email on anyone

- Check positioning fit from the shop's own site or social presence:
  does what they carry actually sit next to what you'd want to sit
  next to?
- Signals worth weighting: an active, recently-posted social account;
  a strong aggregate review score; a price point compatible with your
  own wholesale terms.
- Rank into a small number of tiers rather than a single score — it
  keeps the reasoning visible and makes step 4's cadence easier to
  prioritize.
- Drop anything that fails positioning fit outright before it reaches
  a human's inbox review.

## 3. Read the reviews for your top tier

- For your highest-priority shops only (this doesn't scale to the
  whole list, and doesn't need to), pull their public reviews and read
  what customers actually mention — style, selection, service.
- Pull one real detail per shop worth referencing in the first
  message. A generic compliment reads as generic; a specific one
  reads as done homework.

## 4. Reach out, then follow a fixed cadence

- First message: a personalized opener using the step 3 detail where
  you have one, two lines on what you make and where it sits, and a
  concrete next step — a lookbook/catalog plus terms, or a short call.
- Fixed follow-up schedule, not a judgment call each time: a short
  nudge at day 7, a different channel at day 14, then archive and move
  on at day 21 if there's still no response.
- Log every contact and its outcome against that shop's record so a
  later pass never re-sends the same opener.

## 5. Keep the ones who say yes coming back

- For every shop that starts stocking you, send the new collection
  each season and do a real check-in on a fixed cadence — don't let a
  live account go quiet the same way a cold one does.
- Track which accounts are active vs. gone quiet the same way you
  tracked prospecting status — this is the same list, just past the
  "yes."

## Output

Report: how many shops found per city, how many qualified, how many
contacted, response rate, and how many became active accounts.