Documentation · Workflows
How to Sync People Data Labs Matches into HubSpot with Claude Code
Connect PDL and HubSpot in Deepline, describe your ICP in the chat, and Claude runs the full search + enrich + upsert. PDL's match confidence lands as a HubSpot custom property so sales views can prioritize by tier.
What you need
- • People Data Labs account (Any plan — Deepline works on whatever tier you have)
- • HubSpot account (Any plan with API access — see provider docs)
- • Claude Code installed locally
- • ~2 minutes
Step-by-step
- 1
Install Deepline
One command installs the Deepline CLI and registers a workspace. Takes about 30 seconds. You only do this once per machine.
curl -s "https://code.deepline.com/api/v2/cli/install" | bash deepline auth register - 2
Connect People Data Labs in the Deepline dashboard
In the Deepline dashboard, click Integrations → People Data Labs → paste your API key. Deepline uses PDL inside waterfalls and also directly via its dedicated search/enrich tools.
- 3
Connect HubSpot in the Deepline dashboard
In the Deepline dashboard, click Integrations → HubSpot → Authorize. HubSpot's OAuth flow opens in a new tab — pick the account and confirm scopes (contacts read/write, notes write). Deepline handles the token refresh forever.
- 4
Chat with Claude
Open Claude Code and describe the workflow in plain English. Deepline handles the tool calls, waterfall routing, rate limits, auth refresh, and dedup. An example prompt for this pair:
> From PDL, find VPs of RevOps at US software companies with 201-500 employees. Only keep likelihood >= 8 matches with a work email. Upsert into HubSpot Contacts by email. Store pdl_id and pdl_likelihood as custom properties. Set lifecyclestage='lead'. - 5
Deploy as a workflow
Once Claude's one-off run looks right, type "Deploy this as a workflow" and tell it the schedule. Deepline wraps the exact prompt + tool chain as a recurring workflow with run history, billing, and alerting in the dashboard.
> Deploy this as a workflow that runs every weekday morning at 8am.
Cost math
For 1,000 leads: $2.80
~0.28 credits per Contact reaching HubSpot. PDL per-match cost; HubSpot upsert is free. Deepline's credit pricing is pay-as-you-go — see code.deepline.com/docs/pricing for current rates.
Why do it in Claude Code
Waterfall routing by default
Deepline tries the cheapest provider first and only falls back if it misses. For People Data Labs workflows, this means email enrichment stops at the first valid hit — you don't pay for the second and third provider unless you need to.
Deploy the exact prompt as a schedule
Once the one-off run looks right, "Deploy this as a workflow" wraps the same prompt + tool chain as a cron-scheduled workflow. Run history, per-run billing, and retry logic all live in the dashboard. No DevOps.
One place for every provider credential
People Data Labs keys, HubSpot OAuth, waterfall fallbacks (Hunter, Dropcontact, Findymail, Prospeo) — all live in the Deepline dashboard. Rotate once; every workflow picks up the new credential automatically.
What people are saying
“Waterfall enrichment consistently delivers 80%+ match rates versus 35-50% from any single provider.”
“ZoomInfo pulled about 75% on its own, Apollo about 65%. A 4-provider waterfall landed at 88%.”
Citations sourced from community posts, vendor case studies, and engineering blogs. See src/data/workflow-social-proof.md in the repo for the full sentiment bank.
Troubleshooting
People Data Labs integration shows red in the Deepline dashboard
Cause: People Data Labs credentials are either expired, revoked at the provider side, or the account tier doesn't expose API access.
Fix: Click the integration row in the dashboard → Test Connection. If it fails, re-paste the API key (or re-run OAuth for OAuth-based providers). Confirm the provider account tier includes API access — most providers gate this to paid tiers.
Workflow run succeeds but 0 rows landed in the destination
Cause: The filter returned 0 matches, OR rows failed a downstream gate (email not verified, already in destination, deliverability check failed).
Fix: Open the run in the Deepline dashboard → expand the step-by-step trace. Every row's path is logged: matched/unmatched at each stage. Most frequent culprit is the email-verification gate. Loosen the filter or remove the gate in the prompt if that's the cause.
Scheduled workflow stopped firing
Cause: Either hit a provider rate-limit, ran out of Deepline credits, or the destination API returned 500s Deepline classified as permanent.
Fix: Dashboard → Workflows → Recent Runs. Failed runs show the exact error and a "Replay" button. Credits are visible top-right. Rate-limit issues auto-resume once the window resets; permanent errors need intervention.
FAQ
Do I need an Anthropic API key for this?
No. You need Claude Code (the CLI/IDE). Deepline provides the tool-execution layer and credit system. Your Claude Code subscription or Anthropic API key handles the LLM calls — Deepline handles the GTM actions underneath.
How does Deepline handle dedup across runs?
Built-in. For HubSpot as a destination, Deepline uses the provider-native idempotency key (email for HubSpot/Attio, External_Id for Salesforce, campaign-level dedup for Instantly/Smartlead/Lemlist). Reruns update existing records instead of creating duplicates.
Can I still use my own API keys?
Yes. Paste them in the Deepline dashboard under Integrations. Deepline uses your keys for the actual provider calls — you keep your provider contracts, billing, and rate limit allocation. Deepline's credit billing only covers the orchestration + waterfall layer.
What if my filter only matches 3 rows but the workflow says 1000?
Deepline runs exactly what you describe. The 1000 in cost-math is the reference cost per 1K rows — a 3-row run costs 3/1000 of that total. You never pay for rows that don't exist.
Can I combine this with a waterfall?
Yes. Mention it in the prompt — e.g. "If People Data Labs doesn't return an email, fall back to Hunter → Dropcontact → Findymail." Deepline assembles the waterfall automatically and charges you only for the provider that successfully finds each row.
Related workflows
People Data Labs → Instantly
Connect People Data Labs and Instantly in Deepline, describe your ICP as an Elasticsearch-DSL query, and Claude runs search + enrich + filter-by-likelihood + Instantly push. Skip-on-low-confidence by default.
Apollo → HubSpot
Connect Apollo and HubSpot in Deepline, tell Claude exactly who to find and how to tag them in HubSpot, and the workflow runs. Deepline batches 100 Contacts per HubSpot call and handles the 150 req/10s rate limit.
ZoomInfo → HubSpot
Connect ZoomInfo and HubSpot in Deepline, describe the accounts you want in plain English, and Claude pulls + enriches + upserts. Dedupes by domain so nightly runs never create duplicates.
Want this workflow pre-configured?
Run it on Deepline or fork the full skill pack on GitHub. Either way, the code is yours to read and change.