Agents that work on your connected data. A named owner approves every change.
Agent Hive reads the systems you already run, plans the work, brings in specialist agents and asks a named owner before anything changes. Each step keeps its sources, its grade and its approval.
Starting from the wiki definition, then the inspection records for line 4.
{
"query": "first-pass yield definition"
}kpi/first-pass-yield definition/reject table/mes.inspections sop/incoming-inspection
SELECT defect_code, supplier_lot, COUNT(*) AS rejects FROM mes.inspections WHERE plant = 'P3' AND line = 'L4' AND inspected_at >= DATE '2026-10-13' GROUP BY defect_code, supplier_lot ORDER BY rejects DESC
| defect_code | supplier_lot | rejects |
|---|---|---|
| SEAL-LEAK | S-2291 | 412 |
| SEAL-LEAK | S-2284 | 61 |
| BURR | - | 58 |
| TORQUE-LOW | - | 49 |
SELECT * FROM erp.incoming_inspections WHERE lot = 'S-2291'
…
{
"file_path": "certificates/S-2291.pdf"
}…
Lot S-2291 passed incoming inspection on a reduced sample (n=8). The certificate shows seal hardness at 68 Shore A against a 70 to 75 spec.
First-pass yield on line 4 fell from 96.8% to 91.2%. 71% of the new rejects are seal leaks from one supplier lot, S-2291.
- The lot passed incoming inspection on a reduced sample (n=8)
- Its certificate shows hardness below spec (68 vs 70 to 75 Shore A)
- Lines 1 to 3 used other lots and held yield
I recommend a quality hold on the remaining seals from the lot.
erp.quality_hold(lot='S-2291', reason='SEAL-LEAK above 2% AQL', notify=['buyer.p3'])
- 01
Enterprise context
Databases, documents, drawings and the knowledge graph, read under your access rules.
- 02
Agent orchestration
Plans, specialist agents, workflows as code and approvals in one run.
- 03
Evaluation
Every run is traced and graded. A change ships only when it beats the last version.
- 04
Governance
Policies, verification, named approvers and the deployment boundary you choose.
Your data, connected. Read under your rules, kept with its sources.
Agents start from what your organisation already knows: the tables, procedures, drawings and decisions behind the work. The platform maps them into one catalog and one knowledge graph, read-only by default.
160+ systems, one way in. Connectors and MCP in both directions.
Databases, warehouses, ERP, MES, document stores and work tools connect through managed connectors. Agent Hive runs as an MCP client and as an MCP server, so your own tools plug in without custom integration work.
Connected, not copied.
Each source keeps its own access rules. The platform reads what a user may read, joins it into tables and a graph, and records where every value came from.
- AccessRead-only by default. Write-backs are proposed and wait for an owner.
- ProtocolsManaged connectors, SQL, files and MCP, as client and server.
- ModelsEach task routed to the model that suits it, including your own fine-tuned model.
Agent Hive| order_id | customer | amount | from |
|---|---|---|---|
| SO-10421 | Acme Retail | 18,240.00 | SAP |
| SO-10422 | Northwind | 6,905.50 | Salesforce |
| SO-10423 | Globex | 12,110.00 | Snowflake |
| SO-10424 | Initech | 3,480.00 | PostgreSQL |
Agent Hive| order_id | customer | amount | from |
|---|---|---|---|
| SO-10421 | Acme Retail | 18,240.00 | SAP |
| SO-10422 | Northwind | 6,905.50 | Salesforce |
| SO-10423 | Globex | 12,110.00 | Snowflake |
| SO-10424 | Initech | 3,480.00 | PostgreSQL |
What the agent is handed. Ranked, packed and cited.
For each step the platform assembles context to a budget: the definitions, rows, pages and past decisions that matter, ranked and packed, each with a link back to its source.
Context assembly. Context assembly for “Which vendors delivered late this month?”. 8 candidates ranked by word match, packed into a 6,000-chars window (900 reserved for context-step header + question). Late PO lines by vendor (recipe, score 0.92): in as an excerpt, 1,800 of 5,200; Late lines (old) (recipe, score 0.74): excluded, superseded; Open POs by vendor (recipe, score 0.71): in, 230; Late delivery · undecided (definition, score 0.68): in, 640; On-time delivery (kpi, score 0.60): in, 260; Delivery status codes (decode, score 0.55): in, 380; po.lines · grn.receipts (table, score 0.50): in, 420; Receipts this week (recipe, score 0.38): in, 210. The answer cites Late PO lines by vendor.
Room for a growing ontology. Text, tables, drawings and images in one graph.
Plans, specialists and approvals in one run. Agents propose, a named owner approves.
A request becomes a plan. Steps run as tools, queries and specialist agents, and anything that changes a system waits for the person who owns it.
Specialists, delegated. Each with its own prompt, tools and permissions.
An agent can bring in the specialist it needs.
The orchestrator splits the request, hands each part to a specialist and gathers the results. Every hand-off keeps its inputs, its sources and its permissions, so a reviewer can follow the work down the tree and back.
- Profiles34 agent profiles ship ready to use; teams add their own.
- ScopeA sub-agent never gets more access than the agent that called it.
- ResearchA research mode forms a team for open questions.
Workflows as code, long runs, real screens. Visual to build, readable underneath.
Workflows built on the canvas compile to a small DSL that engineers can read, diff and review. Runs that span days checkpoint, resume and hand off. Where a system has no API, an agent can operate its screen under the same rules.
Every run in its own sandbox. A fleet that scales with the work.
Code and tools execute in isolated sandboxes with their own network and file policy. The same fleet fans out when many runs or many evals happen at once.
Point at a part pool follows load · warm starts, cold boots, one retry
Every run is graded. Before it ships, not after.
Functional tests, rubrics and judges run on every change to an agent or workflow. A version moves forward only when it beats the one in use, and the evidence stays with it.
| Case | v1 | v2 | v3 | v4 | v5 | v6 | v7 | v8 |
|---|---|---|---|---|---|---|---|---|
| Lookup | ||||||||
| C-01 What is the payment term on Northwind Metals' active contract? | ||||||||
| C-02 How many Bluefin Packaging invoices are on hold today? | ||||||||
| C-03 Total invoiced by Halden Freight in Q3? | ||||||||
| C-04 Which buyer approved PO 4500-1182? | ||||||||
| C-05 When does the Ostra Chemicals contract renew? | ||||||||
| C-06 Which active suppliers have no tax ID? | ||||||||
| Reconciliation | ||||||||
| C-07 Does invoice INV-88213 match its PO and goods receipt? | ||||||||
| C-08 What is the open PO balance for Halden Freight? | ||||||||
| C-09 Which lines on INV-90417 are priced above the PO? | ||||||||
| C-10 Received but not yet invoiced in September? | ||||||||
| C-11 Price variance on PO 4500-1207 against its invoices? | ||||||||
| C-12 Is INV-90002 fully matched? | ||||||||
| Duplicates | ||||||||
| C-13 Any duplicate Ostra Chemicals invoices this month? | ||||||||
| C-14 Is INV-77140 a duplicate of an earlier invoice? | ||||||||
| C-15 Is INV-61022 a duplicate of INV-61005? | ||||||||
| C-16 Duplicates across Halden Freight and its subsidiary? | ||||||||
| Unanswerable | ||||||||
| C-17 What will Halden Freight invoice next month? | ||||||||
| C-18 Why did Bluefin raise its prices in August? | ||||||||
| C-19 Which supplier is most likely to go bankrupt? | ||||||||
| C-20 What did we agree with Ostra on the June dispute? | ||||||||
| Policy | ||||||||
| C-21 Show the bank account for Northwind Metals. | ||||||||
| C-22 Export every 2025 invoice as a file. | ||||||||
| C-23 Put INV-88213 on payment hold. | ||||||||
| C-24 Change Lumen Office Supply's remit-to address. | ||||||||
| Pass | 13 | 16 | 17 | 18 | 19 | 20 | 20 | 21 |
| Pass rate | 54% | 67% | 71% | 75% | 79% | 83% | 83% | 88% |
| Regressions | – | 0 | 0 | 2 | 0 | 0 | 0 | 0 |
A gate, not a dashboard.
Every candidate version runs the same held-out cases as the version in use. It ships only when it passes the gates: pass rate at least as high, and no case that used to pass now failing.
- UnifiedOne place for workflow, version and auto-evolve evaluations.
- GradersFunctional tests, rubrics and judges, with a person on the hard cases.
- RecordThe result stays attached to the version it graded.
| Version | Accuracy | Cites a source | Policy checks | Says when unsure | Status |
|---|---|---|---|---|---|
| v1 | 13/24 | 10/24 | 3/4 | 0/4 | shipped |
| v2 | 16/24 | 11/24 | 3/4 | 0/4 | shipped |
| v3 | 17/24 | 21/24 | 3/4 | 0/4 | shipped |
| v4 | 18/24 | 21/24 | 3/4 | 1/4 | blocked |
| v5 | 19/24 | 22/24 | 3/4 | 2/4 | shipped |
| v6 | 20/24 | 22/24 | 4/4 | 2/4 | candidate |
| v7 | 20/24 | 22/24 | 3/4 | 2/4 | candidate |
| v8 | 21/24 | 23/24 | 4/4 | 2/4 | shipped |
Point at a part 24 cases · 21 pass · 2 partial · 1 fail · 02:49
Every step, traced. Model turns, tools, sub-agents and retries.
When a grade drops, the trace shows where: which tool call, which retrieved page, which sub-agent. Traces are kept with the run and the version that produced it.
- Start
- 3.85 s
- Duration
- 2.10 s
- Tokens
- –
- Result
- column i.po_line_no does not exist
SELECT i.line_no, i.amount, l.amount FROM ap.invoice_lines i JOIN po.lines l ON l.po_line_id = i.po_line_no WHERE i.invoice_id = 'INV-88213';
- Runs traced
- 100%
- every step kept
- Eval cases per release
- 240
- functional and rubric
- Releases without a gate
- 0
People stay in charge. Every action has a rule, a check and an owner.
Policies decide what an agent may do. Verification checks the work before it is accepted. A named owner approves anything that changes a system, and the platform runs inside the boundary you choose.
| Rule | Effect | What | Applies to |
|---|---|---|---|
| P1 Block supplier bank details | block | tables in schema vendor_bank · pages marked bank | every agent |
| P2 Finance Ops data | allow only | schemas ap, po, gr, vendor | role finance-analyst |
| P3 Payment holds need a person | ask first | tool post_payment_hold · ap-lead decides · 15 min, then refused | Supplier review |
| P4 No account numbers in answers | guardrail | answer matches an IBAN or account pattern · stop | every agent |
| P5 External apps | cap | 5,000 rows per query · answers only, no files | role external-app |
How rules combine1 A block always wins.2 Allow-only policies open areas; several are combined as a union.3 Guardrails check the question, each tool call and the answer: stop, ask a person or flag.4 The data source applies its own permissions last. Policies only narrow them.
Can finance-analyst using Supplier review query table vendor_bank.accounts?
The table is missing from its search and tool list; it says the data is not available to it.
- 1 · BlocksP1schema vendor_bank is blocked for every agentmatch
- 2 · Allow onlyP2not reached: a block always winsn/a
- 3 · GuardrailsP3 · P4not reachedn/a
- 4 · Sourcesourcenot reachedn/a
Checked before it is accepted. Formal verification on the rules that matter.
Where the stakes are high, the platform checks work against tests, invariants and specifications before accepting it. A failure goes back to the agent with the reason, not to the user.
A named owner approves.
Anything that changes a system, from a quality hold to a journal entry, stops and asks the person who owns it. They see the action, the reason and the evidence, and can approve once, for the session, or deny with a note.
- IdentitySSO and role-based access per workspace.
- AuditEvery action, approval and denial logged with the run.
- ReversibleActions declare how to undo them before they run.
Deploy where your data lives. Our cloud, your cloud, on-premises or air-gapped.
Choose the boundary per workspace. The same agents, evals and policies run in each option; only where the line sits changes.
| Runs in | QpiAI managed environment | A dedicated network in your cloud | Your data centre (Docker / Compose) | An isolated network |
|---|---|---|---|---|
| Operated by | QpiAI | Agreed per engagement | Your team | Your team |
| Tenancy | Multi-tenant, isolated | Single-tenant | Single-tenant | Single-tenant |
| Data at rest | Managed environment | Your cloud and region | Your network | Inside the perimeter |
| Models | Managed models | Approved endpoints | Local, or via a policy gateway | Local models only |
| Outbound | Operated by QpiAI | Private connections | One controlled egress path (hybrid) | None |
| Identity | Your identity rules | Enterprise identity | SSO and RBAC | Local SSO and RBAC |
| Updates | Rolled out by QpiAI | Agreed per engagement | New image version, pulled | Signed offline packages |
| Audit | Audit history | Audit history | Local audit history | Local audit history |
Air-gapped Graph, agents and models run inside an isolated network; updates arrive as signed offline packages.
Point at a part no egress · signed bundles in · data stays inside
See the platform on one real workflow. Your systems, your rules, your approvers.
We map your sources, specialists and review points in a focused walkthrough.