Why this exists.
Drop in a list of prospect companies on Sunday night. Builder visits each website, finds the right person on LinkedIn, checks if they look like the kind of buyer you want, and writes a personalised opener for each one.
A patchwork that breaks.
- A shared spreadsheet nobody opens on time
- Prompts copy-pasted into a chat window
- A contractor who disappears for two weeks
- Output that lands in a different shape every run
A workflow that ships.
- One brief, one cadence, one place to read it
- Every claim cited, every step reviewable
- A finished artifact in your team’s format
- Your sales team opens Monday to a ready-to-go list with background on every prospect.
Four moves.
Builder runs each move with a preview attached — so you know what lands before you ever hit send. Skip freely once you know which parts carry the weight.
- 01Kickoff
Upload your list of companies — a spreadsheet or straight from HubSpot.
Builder starts with the brief and asks only for what's missing. No boilerplate intake form, no setup meeting.
Chat · marieteYUpload your list of companies — a spreadsheet or straight from HubSpot.BBuilder is working - 02Gather
Tell Builder what your best customers look like.
Sources are pulled, cleaned, and cross-checked against prior runs — every claim carries a citation you can trace.
checklist · step-02Source connected · tell builder whatContext loadedFirst pass completeSource connected - 03Reason
Connect LinkedIn and your CRM.
The agent thinks out loud where it matters — trade-offs named, assumptions surfaced, judgments explained.
ranked results01Research · automated lead0.9402Leads · automated lead0.8203Overnight · automated lead0.67 - 04Draft
Schedule it weekly. Review the results. Send the emails.
A first draft lands in the format your team already uses. You edit the last 10%, not the first 90%.
delivery · inboxBnewBuilder → your teamjust now · scheduled weeklyResearch leads overnightYour sales team opens Monday to a ready-to-go list with background on every prospect.Open briefing
Paste these into Builder.
Three prompts — a kickoff, a full run, and a packaging pass. Copy the one that matches the phase you're in. Rewrite any detail to fit your business.
You are Builder. I want to research leads overnight — Drop in a list of prospect companies on Sunday night. Builder visits each website, finds the right person on LinkedIn, checks if they look like the kind of buyer you want, and writes a personalised opener for each one. My goal: Your sales team opens Monday to a ready-to-go list with background on every prospect. Walk me through the first move and tell me what you need from me.
Run the full playbook end-to-end: Upload your list of companies — a spreadsheet or straight from HubSpot. Tell Builder what your best customers look like. Connect LinkedIn and your CRM. Schedule it weekly. Review the results. Send the emails. Ask before skipping any step. Show work as you go.
Deliver the output as a single brief I can share with the team — lead with "3hr → 8min", then the receipts. Call out anything that changed assumptions mid-run.
Inputs in, outputs out.
Builder runs on the inputs on the left and hands back the artifacts on the right. Skip any input — the agent will ask for it the first time it needs it.
- One source of truth (CSV, CRM, or warehouse)
- A one-paragraph brief on the goal
- The KPI you want to move
- A scored, cited brief you can forward
- A structured file for downstream automation
- An alert when anything material changes
A finished artifact, not a todo list.
Every run ends the same way — a packaged brief in the channel your team already reads. Here's a preview of what shows up.
Here's the brief for this week. I ran the playbook end-to-end, flagged anything that shifted against last run, and packaged the output for Slack and the shared drive.
- Upload your list of companies — a spreadsheet or straight from HubSpot.
- Tell Builder what your best customers look like.
- Connect LinkedIn and your CRM.
- Schedule it weekly. Review the results. Send the emails.
Where teams stall.
Three ways we see this go sideways — and how to avoid each one.
Pointing the agent at stale or half-connected data. Clean the source once, compound every run after.
Running it once and forgetting. Put it on a weekly cadence so the numbers actually move.
Skipping the first review. Check the first run by hand — trust compounds from there.
Before you start.
Usually one source is enough to see value. Builder can run on a CSV paste for the first pass; connect the CRM, the data warehouse, or the tool of record once you want it to run on its own.
Most teams put this on a weekly cadence. That's the sweet spot between "too noisy to read" and "too stale to act on". Adjust once you see how the numbers behave.
Whoever owns the downstream action. Builder hands back a finished result — the value is in somebody actually reading it and shipping the decision the same day.
It usually isn't. The first pass is calibration — tell Builder what was off, rerun, and the second is close. By the fourth it reads like a teammate.