What is StackOne Deep Query?

StackOne Deep Query lets AI agents filter, search and aggregate records stored by Data Sync. It returns only the counts or fields a task needs, without calling the provider API at query time. Agents use it through {action}_s1query tools over MCP.

How does Deep Query work with MCP?

Each synced action gets a query tool next to its live tool, named after the action, such as sapsuccessfactors_list_job_records_s1query. The list_s1query_queryable_fields tool tells the agent which fields it can filter, sort and aggregate. Both are available through StackOne's Tool Gateway MCP, and agents can find them with Tool Discovery.

Can an agent use Deep Query across different apps?

Yes. Each synced app gets its own query tool, so an agent can query several apps and compare the results. For example, it can count Workday leavers and open requisitions in Oracle Fusion HCM by department, then set the two side by side.

How does Deep Query help agents respond faster?

Deep Query reads indexed records already stored in StackOne, avoiding a live provider request during the query. For example, an IT helpdesk agent can read a caller's manager and cost center from synced SAP SuccessFactors records. Use the live action when the task requires the provider's current state.

Can Deep Query filter fields the provider API cannot?

Yes. Deep Query filters on any field in the synced records, whatever query parameters the provider API exposes. The agent discovers the available fields before querying them.

How fresh are Deep Query results?

Deep Query reads the most recently synced data, so freshness depends on your Data Sync schedule. Incremental runs update changed records where supported; full re-syncs also reconcile deletions. Use the live action when a task needs the provider's current state.

Is Deep Query a replacement for RAG?

For structured records, yes: counts, filters, text search and lookups need no separate retrieval pipeline. Deep Query does not index the contents of binary files or images, so keep RAG for documents. Read the Deep Query documentation for its supported operations.

How do I enable Deep Query?

Enable Data Sync for a syncable action on its Connector Profile and save your schedule. Once records are synced, use the query tool from your agent or the S1Query entry in Actions Request Tester. The Data Sync setup guide explains configuration and monitoring.

Deep Query for AI agents. Faster, cheaper answers from your business data.

Deep Query lets AI agents filter, search and aggregate records kept by StackOne Data Sync, in under a second. The agent gets only the counts and fields it needs, without a call to the source API.

Start Free Book Demo

MCP A2A SDK

What's the average base salary by department in New York?

Querying synced records

list_s1query_queryable_fields SAP SuccessFactors user fields

sapsuccessfactors_list_users_s1query 6,150 records → 6 averages

Average base salary across 6,150 New York employees:

Engineering$168,000

Product$165,714

Sales$129,400

Finance$119,500

People$111,857

Support$70,500

1 query · 6 averages · no provider API call · 4,708 tokens per run

Companies already connected through StackOne

Deep Query use cases. Get the records and totals
your task needs.

Deep Query filters and counts synced records inside StackOne and sends your agent only the result, cutting the tokens a task uses by up to 99.9%.

What's the average base salary by department in New York?

SAP SuccessFactors users 30,000 synced employees6,150 match location: New York6 department averages

Engineering $168,000 Support $70,500 People $111,857 Product $165,714 Finance $119,500 Sales $129,400

{
  "filter": {"term": {"location": "New York"}},
  "aggs": {
    "by_department": {
      "terms": {"field": "department"},
      "aggs": {"average": {"avg": {"field": "salary"}}}
    }
  }
}

Then the agent groups the 6,150 records by department and averages salary for each group itself.

Engineering has the highest average base salary in New York at $168,000, and Support the lowest at $70,500.

One of 200 synced records

{
  "userId": "ocole0",
  "firstName": "Omar",
  "lastName": "Cole",
  "department": "Product",
  "location": "Berlin",
  "managerName": "Sam Nair",
  "costCenter": "4430 · Product",
  "jobTitle": "Product Manager",
  "salary": 73000
}

sapsuccessfactors_list_users_s1queryFilter New York employees, average salary by department

{
  "filter": {
    "term": {
      "location": "New York"
    }
  },
  "aggs": {
    "by_department": {
      "terms": {
        "field": "department"
      },
      "aggs": {
        "average": {
          "avg": {
            "field": "salary"
          }
        }
      }
    }
  }
}

All results

Engineering	$168,000
Support	$70,500
People	$111,857
Product	$165,714
Finance	$119,500
Sales	$129,400

Returned by sapsuccessfactors_list_users_s1query

[
  {
    "key": "Engineering",
    "doc_count": 1200,
    "average": {
      "value": 168000
    }
  },
  {
    "key": "Support",
    "doc_count": 1200,
    "average": {
      "value": 70500
    }
  },
  {
    "key": "People",
    "doc_count": 1050,
    "average": {
      "value": 111857
    }
  },
  {
    "key": "Product",
    "doc_count": 1050,
    "average": {
      "value": 165714
    }
  },
  {
    "key": "Finance",
    "doc_count": 900,
    "average": {
      "value": 119500
    }
  },
  {
    "key": "Sales",
    "doc_count": 750,
    "average": {
      "value": 129400
    }
  }
]

Deep Query

4,708 tokens

Live API

268.2K tokens

98.2%fewer tokens

$107$1.88per 100 runs

Model

Without Deep Query, the agent asks the provider API for New York employees, selecting only the fields it needs, up to 1,000 per call, one page after another, and does the counting, grouping or summing itself. A call takes about 0.3 seconds plus time for what it returns, the agent spends about 3 seconds on each turn, and the model reads everything it gets at about 6,500 tokens a second. Deep Query answers a query in about 0.2 seconds, and its run is one query and one turn. Records are measured with the o200k_base tokenizer and priced at the model's public input rate. Both sides include about 2,600 tokens for the prompt and the query tool's definition, and the Deep Query side about 2,000 more for extra field lookups, retried queries and the agent's output.

~1 min~4 sper run

Which 10 companies have the most open pipeline value?

Pipedrive deals 2,400 synced deals1,500 open10 organization totals

Kestrel Energy $635,000 · 30 deals Meridian Bank $560,000 · 20 deals Tidewater Shipping $465,000 · 60 deals Alder Pharma $440,000 · 30 deals Harbor Analytics $360,000 · 90 deals

pipedrive_list_deals_s1query

{
  "filter": {"term": {"status": "open"}},
  "aggs": {
    "by_organization": {
      "terms": {"field": "org_id", "size": 10, "order": {"total": "desc"}},
      "aggs": {"total": {"sum": {"field": "value"}}}
    }
  }
}

pipedrive_list_organizations_s1query

{
  "filter": {
    "terms": {"id": [7002, 7001, 7004, 7020, 7003, 7033, 7019, 7009, 7005, 7015]}
  },
  "source": ["name", "id"]
}

Then the agent sums value by org_id across the open deals itself, keeps the top 10 and asks for their names.

Kestrel Energy has the most open pipeline at $635,000, then Meridian Bank at $560,000.

One of 240 synced records

{
  "id": 51000,
  "title": "Cedar Logistics renewal",
  "value": 2500,
  "currency": "USD",
  "status": "open",
  "org_id": 7022,
  "owner_id": 31,
  "stage_id": 3,
  "pipeline_id": 1,
  "probability": 35,
  "add_time": "2026-01-31T09:00:00Z",
  "expected_close_date": "2027-01-02"
}

One of 40 synced records

{
  "id": 7001,
  "name": "Meridian Bank",
  "owner_id": 31,
  "address": "100 Main Street, New York, NY",
  "add_time": "2024-01-15T10:00:00Z"
}

pipedrive_list_deals_s1queryFilter open deals, sum value for the top 10 organizations

{
  "filter": {
    "term": {
      "status": "open"
    }
  },
  "aggs": {
    "by_organization": {
      "terms": {
        "field": "org_id",
        "size": 10,
        "order": {
          "total": "desc"
        }
      },
      "aggs": {
        "total": {
          "sum": {
            "field": "value"
          }
        }
      }
    }
  }
}

pipedrive_list_organizations_s1queryLook up the 10 organizations by id

{
  "filter": {
    "terms": {
      "id": [
        7002,
        7001,
        7004,
        7020,
        7003,
        7033,
        7019,
        7009,
        7005,
        7015
      ]
    }
  },
  "source": [
    "name",
    "id"
  ]
}

All results

Kestrel Energy	$635,000 · 30 deals
Meridian Bank	$560,000 · 20 deals
Tidewater Shipping	$465,000 · 60 deals
Alder Pharma	$440,000 · 30 deals
Harbor Analytics	$360,000 · 90 deals
Nimbus Cloud	$345,000 · 50 deals
Zephyr Airlines	$320,000 · 40 deals
Redwood Capital	$315,000 · 20 deals
Pinnacle Insurance	$290,000 · 40 deals
Upland Software	$277,500 · 80 deals

Returned by pipedrive_list_deals_s1query

[
  {
    "key": "7002",
    "doc_count": 30,
    "total": {
      "value": 635000
    }
  },
  {
    "key": "7001",
    "doc_count": 20,
    "total": {
      "value": 560000
    }
  },
  {
    "key": "7004",
    "doc_count": 60,
    "total": {
      "value": 465000
    }
  },
  {
    "key": "7020",
    "doc_count": 30,
    "total": {
      "value": 440000
    }
  },
  {
    "key": "7003",
    "doc_count": 90,
    "total": {
      "value": 360000
    }
  },
  {
    "key": "7033",
    "doc_count": 50,
    "total": {
      "value": 345000
    }
  },
  {
    "key": "7019",
    "doc_count": 40,
    "total": {
      "value": 320000
    }
  },
  {
    "key": "7009",
    "doc_count": 20,
    "total": {
      "value": 315000
    }
  },
  {
    "key": "7005",
    "doc_count": 40,
    "total": {
      "value": 290000
    }
  },
  {
    "key": "7015",
    "doc_count": 80,
    "total": {
      "value": 277500
    }
  }
]

Returned by pipedrive_list_organizations_s1query

[
  {
    "name": "Meridian Bank",
    "id": 7001
  },
  {
    "name": "Kestrel Energy",
    "id": 7002
  },
  {
    "name": "Harbor Analytics",
    "id": 7003
  },
  {
    "name": "Tidewater Shipping",
    "id": 7004
  },
  {
    "name": "Pinnacle Insurance",
    "id": 7005
  },
  {
    "name": "Redwood Capital",
    "id": 7009
  },
  {
    "name": "Upland Software",
    "id": 7015
  },
  {
    "name": "Zephyr Airlines",
    "id": 7019
  },
  {
    "name": "Alder Pharma",
    "id": 7020
  },
  {
    "name": "Nimbus Cloud",
    "id": 7033
  }
]

Deep Query

5,056 tokens

Live API

498.8K tokens

98.9%fewer tokens

$200$2.02per 100 runs

Model

Without Deep Query, the agent asks the provider API for open deals, up to 500 per call, one page after another, and does the counting, grouping or summing itself. Then the agent asks the provider API for the 10 organizations by id. A call takes about 0.3 seconds plus time for what it returns, the agent spends about 3 seconds on each turn, and the model reads everything it gets at about 6,500 tokens a second. Deep Query answers a query in about 0.2 seconds, and the agent sends its 2 queries one after the other. Records are measured with the o200k_base tokenizer and priced at the model's public input rate. Both sides include about 2,600 tokens for the prompt and the query tool's definition, and the Deep Query side about 2,000 more for extra field lookups, retried queries and the agent's output, plus about 160 for each extra query.

~2 min~7 sper run

Which 10 suppliers did we spend the most with this quarter?

Xero 1,150 invoices + 2,200 bank transactions600 bills + 1,700 payments this quarter49 supplier totals

Westgate Property $555,000 · 30 bills + 0 payments Tandem Consulting $470,000 · 40 bills + 0 payments Cloudline Hosting $233,770 · 0 bills + 300 payments Vertex Software $154,700 · 20 bills + 120 payments Metro Travel $151,080 · 0 bills + 400 payments

xero_list_invoices_s1query

{
  "filter": {
    "bool": {
      "must": [
        {"term": {"Type": "ACCPAY"}},
        {"range": {"Date": {"gte": "2026-07-01"}}}
      ]
    }
  },
  "aggs": {
    "by_supplier": {
      "terms": {"field": "Contact.Name", "size": 50, "order": {"total": "desc"}},
      "aggs": {"total": {"sum": {"field": "Total"}}}
    }
  }
}

xero_list_bank_transactions_s1query

{
  "filter": {
    "bool": {
      "must": [
        {"term": {"Type": "SPEND"}},
        {"range": {"Date": {"gte": "2026-07-01"}}}
      ]
    }
  },
  "aggs": {
    "by_supplier": {
      "terms": {"field": "Contact.Name", "size": 50, "order": {"total": "desc"}},
      "aggs": {"total": {"sum": {"field": "Total"}}}
    }
  }
}

Then the agent adds up bills and payments by supplier itself and keeps the top 10.

Westgate Property was paid the most this quarter at $555,000, then Tandem Consulting at $470,000.

One of 115 synced records

{
  "InvoiceID": "972d5c56-0310-4310-8170-000000000310",
  "InvoiceNumber": "INV-02200",
  "Type": "ACCREC",
  "Status": "PAID",
  "Contact.Name": "Kestrel Energy",
  "Date": "2026-07-03",
  "DueDate": "2026-07-28",
  "Total": 3500,
  "CurrencyCode": "USD"
}

One of 220 synced records

{
  "BankTransactionID": "3b07d244-0900-4900-8300-000000000900",
  "Type": "SPEND",
  "Status": "AUTHORISED",
  "Contact.Name": "Ridge Telecom",
  "Date": "2026-07-04",
  "Total": 55,
  "BankAccount.Name": "Operating account",
  "Reference": "Monthly plan",
  "CurrencyCode": "USD"
}

xero_list_invoices_s1queryFilter this quarter's bills, sum by supplier

{
  "filter": {
    "bool": {
      "must": [
        {
          "term": {
            "Type": "ACCPAY"
          }
        },
        {
          "range": {
            "Date": {
              "gte": "2026-07-01"
            }
          }
        }
      ]
    }
  },
  "aggs": {
    "by_supplier": {
      "terms": {
        "field": "Contact.Name",
        "size": 50,
        "order": {
          "total": "desc"
        }
      },
      "aggs": {
        "total": {
          "sum": {
            "field": "Total"
          }
        }
      }
    }
  }
}

xero_list_bank_transactions_s1queryFilter this quarter's spend, sum by supplier

{
  "filter": {
    "bool": {
      "must": [
        {
          "term": {
            "Type": "SPEND"
          }
        },
        {
          "range": {
            "Date": {
              "gte": "2026-07-01"
            }
          }
        }
      ]
    }
  },
  "aggs": {
    "by_supplier": {
      "terms": {
        "field": "Contact.Name",
        "size": 50,
        "order": {
          "total": "desc"
        }
      },
      "aggs": {
        "total": {
          "sum": {
            "field": "Total"
          }
        }
      }
    }
  }
}

Combined supplier totals

Westgate Property	$555,000 · 30 bills + 0 payments
Tandem Consulting	$470,000 · 40 bills + 0 payments
Cloudline Hosting	$233,770 · 0 bills + 300 payments
Vertex Software	$154,700 · 20 bills + 120 payments
Metro Travel	$151,080 · 0 bills + 400 payments
Brightpath Recruiting	$145,000 · 20 bills + 0 payments
Harbor Legal LLP	$134,000 · 30 bills + 0 payments
Upstream Marketing	$131,350 · 30 bills + 40 payments
Quantum Payroll Services	$126,000 · 30 bills + 0 payments
Ironwood Facilities	$63,000 · 30 bills + 0 payments

Returned by xero_list_invoices_s1query

[
  {
    "key": "Westgate Property",
    "doc_count": 30,
    "total": {
      "value": 555000
    }
  },
  {
    "key": "Tandem Consulting",
    "doc_count": 40,
    "total": {
      "value": 470000
    }
  },
  {
    "key": "Brightpath Recruiting",
    "doc_count": 20,
    "total": {
      "value": 145000
    }
  },
  {
    "key": "Harbor Legal LLP",
    "doc_count": 30,
    "total": {
      "value": 134000
    }
  },
  {
    "key": "Quantum Payroll Services",
    "doc_count": 30,
    "total": {
      "value": 126000
    }
  },
  {
    "key": "Vertex Software",
    "doc_count": 20,
    "total": {
      "value": 108000
    }
  },
  {
    "key": "Upstream Marketing",
    "doc_count": 30,
    "total": {
      "value": 95000
    }
  },
  {
    "key": "Ironwood Facilities",
    "doc_count": 30,
    "total": {
      "value": 63000
    }
  },
  {
    "key": "Keystone Insurance",
    "doc_count": 10,
    "total": {
      "value": 59000
    }
  },
  {
    "key": "Canal Print",
    "doc_count": 50,
    "total": {
      "value": 21000
    }
  },
  {
    "key": "Zinc Hardware",
    "doc_count": 40,
    "total": {
      "value": 19000
    }
  },
  {
    "key": "Iris Translation",
    "doc_count": 30,
    "total": {
      "value": 17500
    }
  },
  {
    "key": "Loom Furniture",
    "doc_count": 30,
    "total": {
      "value": 14000
    }
  },
  {
    "key": "Fern Florists",
    "doc_count": 20,
    "total": {
      "value": 13500
    }
  },
  {
    "key": "Sage Accounting",
    "doc_count": 20,
    "total": {
      "value": 11500
    }
  },
  {
    "key": "Maple Waste",
    "doc_count": 20,
    "total": {
      "value": 11000
    }
  },
  {
    "key": "Vale Maintenance",
    "doc_count": 30,
    "total": {
      "value": 10500
    }
  },
  {
    "key": "Unity Legal",
    "doc_count": 20,
    "total": {
      "value": 7500
    }
  },
  {
    "key": "Wren Design",
    "doc_count": 10,
    "total": {
      "value": 7000
    }
  },
  {
    "key": "Oak Plumbing",
    "doc_count": 10,
    "total": {
      "value": 6000
    }
  },
  {
    "key": "Anchor Signs",
    "doc_count": 10,
    "total": {
      "value": 5500
    }
  },
  {
    "key": "Tide Water Co",
    "doc_count": 10,
    "total": {
      "value": 5000
    }
  },
  {
    "key": "Grove IT Support",
    "doc_count": 20,
    "total": {
      "value": 4500
    }
  },
  {
    "key": "Ridge Telecom",
    "doc_count": 10,
    "total": {
      "value": 4000
    }
  },
  {
    "key": "Quartz Labs",
    "doc_count": 10,
    "total": {
      "value": 3500
    }
  },
  {
    "key": "Pier Parking",
    "doc_count": 10,
    "total": {
      "value": 3000
    }
  },
  {
    "key": "Nova Training",
    "doc_count": 10,
    "total": {
      "value": 2500
    }
  }
]

Returned by xero_list_bank_transactions_s1query

[
  {
    "key": "Cloudline Hosting",
    "doc_count": 300,
    "total": {
      "value": 233770
    }
  },
  {
    "key": "Metro Travel",
    "doc_count": 400,
    "total": {
      "value": 151080
    }
  },
  {
    "key": "Vertex Software",
    "doc_count": 120,
    "total": {
      "value": 46700
    }
  },
  {
    "key": "Pixel Studio",
    "doc_count": 60,
    "total": {
      "value": 42290
    }
  },
  {
    "key": "Upstream Marketing",
    "doc_count": 40,
    "total": {
      "value": 36350
    }
  },
  {
    "key": "Summit Office Supplies",
    "doc_count": 250,
    "total": {
      "value": 29100
    }
  },
  {
    "key": "Silverleaf Catering",
    "doc_count": 180,
    "total": {
      "value": 27630
    }
  },
  {
    "key": "Redline Couriers",
    "doc_count": 150,
    "total": {
      "value": 11660
    }
  },
  {
    "key": "Yarrow Health",
    "doc_count": 20,
    "total": {
      "value": 5600
    }
  },
  {
    "key": "Ember Electric",
    "doc_count": 20,
    "total": {
      "value": 4100
    }
  },
  {
    "key": "Nova Training",
    "doc_count": 20,
    "total": {
      "value": 4100
    }
  },
  {
    "key": "Vale Maintenance",
    "doc_count": 20,
    "total": {
      "value": 4100
    }
  },
  {
    "key": "Ridge Telecom",
    "doc_count": 20,
    "total": {
      "value": 3350
    }
  },
  {
    "key": "Kite Events",
    "doc_count": 10,
    "total": {
      "value": 3250
    }
  },
  {
    "key": "Unity Legal",
    "doc_count": 20,
    "total": {
      "value": 3050
    }
  },
  {
    "key": "Grove IT Support",
    "doc_count": 10,
    "total": {
      "value": 2500
    }
  },
  {
    "key": "Loom Furniture",
    "doc_count": 10,
    "total": {
      "value": 2500
    }
  },
  {
    "key": "Quartz Labs",
    "doc_count": 10,
    "total": {
      "value": 2050
    }
  },
  {
    "key": "Canal Print",
    "doc_count": 10,
    "total": {
      "value": 1300
    }
  },
  {
    "key": "Sage Accounting",
    "doc_count": 10,
    "total": {
      "value": 1300
    }
  },
  {
    "key": "Haven Security",
    "doc_count": 10,
    "total": {
      "value": 550
    }
  },
  {
    "key": "Oak Plumbing",
    "doc_count": 10,
    "total": {
      "value": 550
    }
  }
]

Deep Query

5,684 tokens

Live API

619K tokens

99%fewer tokens

$248$2.27per 100 runs

Model

Without Deep Query, the agent asks the provider API for this quarter's bills, up to 1,000 per call, one page after another, and does the counting, grouping or summing itself. In the same turns, the agent asks the provider API for this quarter's spend transactions, up to 1,000 per call, one page after another, and does the counting, grouping or summing itself. A call takes about 0.3 seconds plus time for what it returns, the agent spends about 3 seconds on each turn, and the model reads everything it gets at about 6,500 tokens a second. Deep Query answers a query in about 0.2 seconds, and the agent sends its 2 queries in one turn. Records are measured with the o200k_base tokenizer and priced at the model's public input rate. Both sides include about 2,600 tokens for the prompt and the query tool's definition, and the Deep Query side about 2,000 more for extra field lookups, retried queries and the agent's output, plus about 160 for each extra query.

~2 min~4 sper run

Which 10 customers opened the most refund tickets this quarter?

Zendesk tickets 9,600 synced tickets1,740 refund tickets this quarter10 organization counts

Northwind Traders 390 Contoso 150 Tailspin Toys 150 Fourth Coffee 120 Proseware 120

{
  "filter": {
    "bool": {
      "must": [
        {"match": {"description": "refund"}},
        {"range": {"createdAt": {"gte": "2026-07-01"}}}
      ]
    }
  },
  "aggs": {"by_organization": {"terms": {"field": "organization", "size": 10}}}
}

Then the agent compares the 300 counts and keeps the top 10.

Northwind Traders opened the most refund tickets this quarter (390), then Contoso (150).

One of 320 synced records

{
  "id": 480000,
  "subject": "The customer is asking for a",
  "description": "The customer is asking for a refund on their last order. Export to CSV fails with a timeout.",
  "status": "open",
  "group": "Shipping",
  "priority": "high",
  "requester": "Jordan Novak",
  "createdAt": "2026-09-01",
  "organization": "Consolidated Messenger"
}

zendesk_list_tickets_s1querySearch descriptions for refund this quarter, count the top 10 organizations

{
  "filter": {
    "bool": {
      "must": [
        {
          "match": {
            "description": "refund"
          }
        },
        {
          "range": {
            "createdAt": {
              "gte": "2026-07-01"
            }
          }
        }
      ]
    }
  },
  "aggs": {
    "by_organization": {
      "terms": {
        "field": "organization",
        "size": 10
      }
    }
  }
}

All results

Northwind Traders	390
Contoso	150
Tailspin Toys	150
Fourth Coffee	120
Proseware	120
Adventure Works	90
Alpine Ski House	60
Bellows College	60
Blue Yonder Airlines	60
Consolidated Messenger	60

Returned by zendesk_list_tickets_s1query

[
  {
    "key": "Northwind Traders",
    "doc_count": 390
  },
  {
    "key": "Contoso",
    "doc_count": 150
  },
  {
    "key": "Tailspin Toys",
    "doc_count": 150
  },
  {
    "key": "Fourth Coffee",
    "doc_count": 120
  },
  {
    "key": "Proseware",
    "doc_count": 120
  },
  {
    "key": "Adventure Works",
    "doc_count": 90
  },
  {
    "key": "Alpine Ski House",
    "doc_count": 60
  },
  {
    "key": "Bellows College",
    "doc_count": 60
  },
  {
    "key": "Blue Yonder Airlines",
    "doc_count": 60
  },
  {
    "key": "Consolidated Messenger",
    "doc_count": 60
  }
]

Deep Query

4,712 tokens

Live API

87,680 tokens

94.6%fewer tokens

$35.07$1.88per 100 runs

Model

Without Deep Query, the agent lists the 300 customer organizations and asks the provider API for one count each, up to 10 calls per turn. A call takes about 0.3 seconds plus time for what it returns, the agent spends about 3 seconds on each turn, and the model reads everything it gets at about 6,500 tokens a second. Deep Query answers a query in about 0.2 seconds, and its run is one query and one turn. Records are measured with the o200k_base tokenizer and priced at the model's public input rate. Both sides include about 2,600 tokens for the prompt and the query tool's definition, and the Deep Query side about 2,000 more for extra field lookups, retried queries and the agent's output.

~2 min~4 sper run

Which candidates told us they're open to relocating to London?

Greenhouse candidate notes 200,000 synced notes12 notes with the phrase12 candidates · 4 fields

Candidate	Job title	Author	Date
Priya Mensah	Data Engineer	Ana Walsh	Sep 20
Mei Cole	Product Designer	Ben Cole	Sep 15
Omar Shah	Staff Engineer	Lena Nair	Aug 14
Avery Shah	Staff Engineer	Priya Walsh	Jul 8
Oscar Morgan	Data Engineer	Zara Walsh	May 16

{
  "filter": {
    "bool": {
      "must": [
        {"match_phrase": {"body": "open to relocating to London"}},
        {"range": {"createdAt": {"gte": "2025-09-24"}}}
      ]
    }
  },
  "sort": [{"createdAt": "desc"}],
  "source": ["candidateName", "jobTitle", "author", "createdAt"]
}

Then the agent reads all 200,000 notes for "open to relocating to London" and filters the rest itself.

12 candidates said they're open to relocating to London, most recently Priya Mensah for Data Engineer.

One of 250 synced records

{
  "id": "nt_088001",
  "candidateId": "cand_040011",
  "candidateName": "Nadia Okafor",
  "jobTitle": "Product Designer",
  "author": "Alex Costa",
  "body": "Catch-up after the take-home review. Panel feedback was positive overall, with a few open questions about testing strategy that the hiring manager wants to cover in the final round. Wants to understand the team's roadmap before the next round. Flagged to the hiring manager as a strong match. Will chase references this week and share availability for the final round by Friday.",
  "createdAt": "2026-08-16"
}

greenhouse_list_notes_s1queryMatch the phrase in a year of notes, newest first

{
  "filter": {
    "bool": {
      "must": [
        {
          "match_phrase": {
            "body": "open to relocating to London"
          }
        },
        {
          "range": {
            "createdAt": {
              "gte": "2025-09-24"
            }
          }
        }
      ]
    }
  },
  "sort": [
    {
      "createdAt": "desc"
    }
  ],
  "source": [
    "candidateName",
    "jobTitle",
    "author",
    "createdAt"
  ]
}

Returned by greenhouse_list_notes_s1query

[
  {
    "candidateName": "Priya Mensah",
    "jobTitle": "Data Engineer",
    "author": "Ana Walsh",
    "createdAt": "2026-09-20"
  },
  {
    "candidateName": "Mei Cole",
    "jobTitle": "Product Designer",
    "author": "Ben Cole",
    "createdAt": "2026-09-15"
  },
  {
    "candidateName": "Omar Shah",
    "jobTitle": "Staff Engineer",
    "author": "Lena Nair",
    "createdAt": "2026-08-14"
  },
  {
    "candidateName": "Avery Shah",
    "jobTitle": "Staff Engineer",
    "author": "Priya Walsh",
    "createdAt": "2026-07-08"
  },
  {
    "candidateName": "Oscar Morgan",
    "jobTitle": "Data Engineer",
    "author": "Zara Walsh",
    "createdAt": "2026-05-16"
  },
  {
    "candidateName": "Nadia Martin",
    "jobTitle": "Product Designer",
    "author": "Jordan Iqbal",
    "createdAt": "2026-05-10"
  },
  {
    "candidateName": "Eli Martin",
    "jobTitle": "Senior Backend Engineer",
    "author": "Alex Ferreira",
    "createdAt": "2026-03-31"
  },
  {
    "candidateName": "Zara Costa",
    "jobTitle": "Account Executive",
    "author": "Sam Lund",
    "createdAt": "2026-02-28"
  },
  {
    "candidateName": "Omar Brun",
    "jobTitle": "Account Executive",
    "author": "Lena Carter",
    "createdAt": "2026-01-10"
  },
  {
    "candidateName": "Eli Brun",
    "jobTitle": "Staff Engineer",
    "author": "Theo Ferreira",
    "createdAt": "2025-12-04"
  },
  {
    "candidateName": "Ines Mensah",
    "jobTitle": "Account Executive",
    "author": "Alex Haddad",
    "createdAt": "2025-11-26"
  },
  {
    "candidateName": "Avery Morgan",
    "jobTitle": "Product Designer",
    "author": "Theo Lund",
    "createdAt": "2025-10-11"
  }
]

Deep Query

4,949 tokens

Live API

21.3M tokens

99.9%fewer tokens

$8,507$1.98per 100 runs

Model

Without Deep Query, the agent asks the provider API for every note from the last 12 months, selecting only the fields it needs, up to 500 per call, one page after another, and does the counting, grouping or summing itself. A call takes about 0.3 seconds plus time for what it returns, the agent spends about 3 seconds on each turn, and the model reads everything it gets at about 6,500 tokens a second. Deep Query answers a query in about 0.2 seconds, and its run is one query and one turn. Records are measured with the o200k_base tokenizer and priced at the model's public input rate. Both sides include about 2,600 tokens for the prompt and the query tool's definition, and the Deep Query side about 2,000 more for extra field lookups, retried queries and the agent's output.

~77 min~4 sper run

Records

Status

Topic

Top 10 by count

Zendesk tickets 9,600 synced tickets2,220 tickets mentioning a refund10 counts by organization

Northwind Traders 480 Contoso 210 Litware 180 Tailspin Toys 180

{
  "filter": {"match": {"description": "refund"}},
  "aggs": {"by_organization": {"terms": {"field": "organization"}}}
}

Then the agent compares the 300 counts and keeps the top 10.

2,220 tickets, the most for Northwind Traders (480).

One of 9,600 synced records

{
  "id": 480000,
  "subject": "The customer is asking for a",
  "description": "The customer is asking for a refund on their last order. Export to CSV fails with a timeout.",
  "status": "open",
  "group": "Shipping",
  "priority": "high",
  "requester": "Jordan Novak",
  "createdAt": "2026-09-01",
  "organization": "Consolidated Messenger"
}

zendesk_list_tickets_s1queryBuilt from your choices

{
  "filter": {
    "match": {
      "description": "refund"
    }
  },
  "aggs": {
    "by_organization": {
      "terms": {
        "field": "organization"
      }
    }
  }
}

Returned by zendesk_list_tickets_s1query

[
  {
    "key": "Northwind Traders",
    "doc_count": 480
  },
  {
    "key": "Contoso",
    "doc_count": 210
  },
  {
    "key": "Litware",
    "doc_count": 180
  },
  {
    "key": "Tailspin Toys",
    "doc_count": 180
  },
  {
    "key": "Fourth Coffee",
    "doc_count": 150
  },
  {
    "key": "Proseware",
    "doc_count": 120
  },
  {
    "key": "Adventure Works",
    "doc_count": 90
  },
  {
    "key": "Bellows College",
    "doc_count": 90
  },
  {
    "key": "Consolidated Messenger",
    "doc_count": 90
  },
  {
    "key": "Humongous Insurance",
    "doc_count": 90
  }
]

Deep Query

4,710 tokens

Live API

87,680 tokens

94.6%fewer tokens

$35.07$1.88per 100 runs

Model

~2 min~4 sper run

Faster tool responses. Read synced data
without waiting on the source API.

Deep Query reads records already stored in StackOne, so your agent gets an answer even while a provider's API is slow or rate-limited.

Live lookup0.2 to 12.7 s

Agent Provider APIAnswer

Deep Query About 0.2 s

Agent Synced recordsAnswer

A live lookup waits 0.2 to 12.7 seconds for the provider API to answer. Deep Query reads the synced records in about 0.2 seconds.

Configure Data Sync. Set how often Data Sync
refreshes your records.

Choose which actions to sync and set a schedule for each one. Deep Query reads those stored records, so the schedule sets how fresh its results are.

Follow the Data Sync setup guide

01Pick an actionOpen a Connector Profile and find a list action that supports sync.

WorkdayProfile · HR agent

ActionType

List WorkersRead

Get WorkerRead

List OrganizationsRead

Update WorkerWrite

02Enable Data SyncSelect the sync icon and switch Data Sync on for that action.

Data Sync· List WorkersOptimize

Setup

Enable Data Sync

Preferences

Sync every 1 hour

Full re-sync 1 day

Save Changes

03Set the scheduleChoose how often new and changed records sync, and how often a full re-sync runs.

Data Sync· List WorkersOptimize

Setup

Enable Data Sync

Preferences

Sync every 1 hour

Full re-sync 1 day

Save Changes

04SaveSave the profile to start syncing.

Data Sync· List WorkersOptimize

Setup

Enable Data Sync

Preferences

Sync every 1 hour

Full re-sync 1 day

Save Changes Data Sync saved

05StackOne syncsStackOne pages through the provider API on your schedule and keeps the records current.

Workday API

Synced records7,200

Full sync7,200 records
Incremental38 changed
Incremental12 changed

06Your agent queriesThe action's query tool is ready over MCP to filter, search and aggregate.

How many active employees are in each US department?

workday_list_workers_s1query1 query

filter: status active, country US
aggs:   terms department

2,400 active employees in the US, 510 of them in Product.

Sync any list action, including your own.

An action declares Data Sync in its connector's YAML before anyone can turn it on. StackOne's connectors declare it for common records. In your own connector, you choose. Edit the block to see how it changes each sync run and the tool your agent gets.

Build your own connector Read the YAML reference

workday.workers.s1.partial.yaml

- actionId: list_workers
  dataSync:
    allowed: true
    indexField: id
    pagination:
      type: cursor
      response:
        dataKey: data
        nextKey: next
      iterator:
        key: next
        in: query
    incremental:
      type: time_filter
      iterator:
        key: updated_after
        in: query
      format: iso8601
      response:
        updatedAtPath: updated_at

Valid. The action offers Data Sync.

In the Connector Profile1

List WorkersSynced hourly · changes only Read

Data Sync can't be turned on while allowed is false.

Sync run2

237workers syncedchanged since the last run

GET/workers?updated_after=2026-09-24T09:00:00Z100 · next=c_8f2a
GET/workers?next=c_8f2a&updated_after=2026-09-24T09:00:00Z100 · next=c_90bd
GET/workers?next=c_90bd&updated_after=2026-09-24T09:00:00Z37 · no next
Done in 3 requests. Unchanged workers stay as they were.

What your agent gets3

workday_list_workers_s1query

Filter, search, sort and count synced Workday workers, in about 0.2 seconds.

departmentstatuscountryjobTitlestartDateprobationEndDate

filtermatchsortaggssource

No query tool. The agent can only page through the live Workday API.

Deep Query syntax. Filter, search and count
on any synced field.

Query tools take OpenSearch-style queries. Your agent looks up each synced field and its type first, then filters, searches and aggregates on it.

Filter

termequals
termsany of
rangegt · gte · lt · lte
existshas a value
wildcardEng*
booland · or · not

Search text

matchany of the words
match_phrasethe exact phrase
search"phrases" +must -not prefix*

Aggregate

termsgroup by
date_histogramby day, week, month
histogram · range · date_rangebuckets
sum · avg · min · max
cardinalitydistinct count
value_count · stats · percentiles

Shape the result

sortany field, asc or desc
sourceonly the fields named
page_sizeup to 200
skipup to 10,000

Deep Query FAQ. How Deep Query works
with your AI agent.

Deep Query sends the agent the result instead of the records. In a SAP SuccessFactors salary example, the API can filter to New York employees and return only their department and salary, but can't average them, so the agent pages 6,150 records through 7 calls, about 268.2K tokens per run. A Deep Query run is about 4,708 tokens, of which the result is 108. Both runs count the prompt, the tool definitions and the data the agent reads. The Deep Query run also counts the agent's output and the field lookups and retries around a query. 100 runs on Claude Opus 5.5 at $4 per million input tokens cost $107 against $1.88.

Get started with Deep Query.

Turn on Data Sync for a supported action and your agent gets its query tools over MCP.

Start Free Book Demo

Deep Query for AI agents. Faster, cheaper answers from your business data.

Deep Query use cases. Get the records and totals your task needs.

Faster tool responses. Read synced data without waiting on the source API.

Configure Data Sync. Set how often Data Sync refreshes your records.

Sync any list action, including your own.

Deep Query syntax. Filter, search and count on any synced field.

Deep Query FAQ. How Deep Query works with your AI agent.

What is StackOne Deep Query?

How does Deep Query work with MCP?

Can an agent use Deep Query across different apps?

How does Deep Query help agents respond faster?

Can Deep Query filter fields the provider API cannot?

How does Deep Query reduce AI agent token costs?

How fresh are Deep Query results?

Is Deep Query a replacement for RAG?

How do I enable Deep Query?

Get started with Deep Query.

Deep Query use cases. Get the records and totals
your task needs.

Faster tool responses. Read synced data
without waiting on the source API.

Configure Data Sync. Set how often Data Sync
refreshes your records.

Deep Query syntax. Filter, search and count
on any synced field.

Deep Query FAQ. How Deep Query works
with your AI agent.