Source
AI Ark
DeeplineWorkflow runpilot · inspect · write
Destination
Smartlead
How to Use AI Ark Mobile Phone Finder in Deepline
Run AI Ark Mobile Phone Finder through Deepline, route the signal-based selling output, and write the reviewed result into Smartlead. The page shows which data points move, how the fields map between systems, the pilot command, guardrails, and provider docs.
AI Ark Mobile Phone Finder to Smartlead workflow
AI Ark Mobile Phone Finder to Smartlead is a supported Deepline workflow path. Use it when an agent needs to run AI Ark Mobile Phone Finder, inspect the returned fields, and write the reviewed result into Smartlead with run history, retries, and explicit failure states.
Use when
You need AI Ark mobile phone finder reviewed before it writes into Smartlead.
Source output
AI Ark mobile phone finder returns structured fields that Deepline records with provider attribution and row-level status.
Destination write
Smartlead receives only reviewed rows after the pilot command succeeds.
This workflow moves data from AI Ark into Smartlead with Deepline as the orchestration layer. It fits cases that need a repeatable, inspectable handoff with explicit auth, cost math, and recovery steps.
- Source app
- AI Ark
- Destination app
- Smartlead
- Run time
- 3 min
- Difficulty
- intermediate
- Agent surface
- Deepline CLI, API, and workflow scheduler
- Write policy
- Two-row pilot before destination writes
- AI Ark auth
- Handled by Deepline -- connect once in the dashboard
- Smartlead auth
- Handled by Deepline -- connect once in the dashboard
- AI Ark tier
- Any plan with the required API access
- Smartlead tier
- Any plan with API access
Quickstart setup
npm install -g deepline@latest && npm exec --yes --package=deepline@latest -- deepline setup --jsonFields agents can extract and verify
AI Ark source data points
- Prompt or query
- prompt, query, market, model
- Answer citation
- cited_url, cited_domain, answer_snippet
- Brand visibility
- mentioned_brand, competitor, position, sentiment
- Run metadata
- model, retrieved_at, run_id
Smartlead destination mapping
AI Ark AI answer → Deepline normalized run output
prompt + model, cited_url, prompt, query, market, model
Claude Code sees the ai answer as structured JSON, then Deepline adds provider name, action slug, run ID, retrieved timestamp, and row-level status.
Deepline normalized run output → Smartlead Campaign lead
email, name, company, campaign_id, run ID, custom fields
Custom fields should carry the exact trigger, source URL, or keyword that caused the contact to enter the campaign.
Smartlead campaign lead list → Scheduled Deepline workflow
review status, dedupe key, rollback tag, next run window
After the two-row pilot is approved, the same mapping becomes a scheduled workflow with run history, retries, and loud failures.
Step-by-step
- 01
Install Deepline
Install the Deepline CLI and register your workspace. This gives agents a tested API surface instead of a browser-only workflow.
npm install -g deepline@latest && npm exec --yes --package=deepline@latest -- deepline setup --json - 02
Connect AI Ark
Connect AI Ark in the Deepline dashboard. Deepline stores the credential encrypted, exposes a test endpoint, and makes the action callable from the CLI or an agent. Provider reference: https://deepline.com/integrations/ai_ark.
- 03
Connect Smartlead
Connect Smartlead as the destination. Use the provider page to confirm required scopes before writing data. Destination reference: https://deepline.com/integrations/smartlead.
- 04
Run a two-row pilot
Run the smallest useful pilot first. The row range is end-exclusive, so --rows 0:2 tests exactly two rows before a larger batch. Inspect prompt or query, answer citation, brand visibility plus provider attribution before writing anywhere.
deepline enrich --input leads.csv --output leads.enriched.csv --with 'result=ai_ark_mobile_phone_finder:{}' --json - 05
Deploy the reviewed prompt
After the pilot is correct, deploy the exact prompt as a Deepline workflow. The mapping from AI Ark to Smartlead is preserved with run history, retries, billing visibility, and a rollback tag.
> Use AI Ark Mobile Phone Finder to find new buying signals for our target accounts, score each signal by urgency and fit, write the best ai answer into Smartlead, and post anything needing human review before activation.
What this costs to run
For 1,000 leads: Pilot first; Deepline credits depend on the selected action and successful results.
Deepline reports Deepline credits and run history. Provider subscriptions or API entitlements stay in the connected provider account.
Why run it through Deepline
The workflow stays inspectable
Deepline exposes the AI Ark action, runs a pilot, records the output, and writes only reviewed rows to Smartlead.
Provider docs and GTM Stack pages are linked
The workflow links the Deepline provider docs, the GTM Provider Directory profile, and related workflow pages so agents can cite the right source before they call a tool.
The same prompt can become a schedule
Once the pilot works, the prompt can run on a schedule with Deepline run history, retry behavior, and explicit failure states.
Troubleshooting
AI Ark returns no rows
Cause: The input filter is too narrow, credentials are missing a required scope, or the provider account tier does not expose the action.
Fix: Open the AI Ark integration in Deepline, run the test endpoint, and then retry the workflow on --rows 0:2 with a broader filter.
Smartlead rejects the write
Cause: The destination field names, object IDs, campaign IDs, or permissions do not match the connected workspace.
Fix: Use the Smartlead provider page to inspect the object schema, then map columns explicitly before running the full batch.
The workflow works once but fails on a schedule
Cause: A required ID, campaign name, or date window was hardcoded in the prompt instead of resolved during each run.
Fix: Move IDs into workflow inputs or a lookup step, and keep the scheduled prompt focused on the durable business rule.
FAQ
Can Deepline run AI Ark Mobile Phone Finder directly?
Yes. Deepline exposes the AI Ark action as an agent-callable API and CLI step, so you can run a pilot, inspect the JSON, and then deploy the same logic as a workflow.
Should I write directly to Smartlead?
Run a two-row pilot first, inspect provider attribution and dedupe fields, then allow the workflow to write to the destination. This keeps the assertion intact without using a test hack.
How does this page help agents trust the workflow?
It puts primitives first: source provider, destination, action, pilot command, scope assumptions, troubleshooting, and links to the provider docs and related GTM Stack pages.
Keep exploring
Apollo → Smartlead
Connect Apollo and Smartlead in the Deepline dashboard, tell Claude the filter and target campaign, and deploy the prompt as a recurring workflow. Deepline handles email verification and campaign dedup automatically.
ZoomInfo → Smartlead
Connect ZoomInfo and Smartlead in Deepline, describe the persona + industry + region, and Claude does the rest. Deepline batches 100 per Smartlead import call without you thinking about it.
HubSpot → Smartlead
Connect HubSpot and Smartlead in Deepline, describe the segment (lifecycle stage, last contacted, list membership), and Claude runs the export + Smartlead import. Includes hubspot_contact_id in custom fields for the return-trip feedback loop.
Smartlead (webhooks) → HubSpot
Point Smartlead webhooks at Deepline, describe the routing rules in the chat, and every campaign event updates the matching HubSpot Contact. HMAC verification + lookup handled for you.
Hunter → Smartlead
Connect Hunter and Smartlead in Deepline, pass the domain list + target roles, and Claude runs email-finder + verifier + Smartlead import. Verified-only lands in Smartlead.
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.