Solutions

Manage the process and you manage the business. We offer general use cases, a manufacturing suite built on WitBPM and WitAI, and industry-specific solutions. Each one states plainly what the AI does and what it does not.

Use cases

Start where it is mandatory, frequent and tied to money

This is the most reliable adoption order we know. Put the processes people touch daily and that affect them personally on the system first, and the change management takes care of itself.

Expense claims

  • Invoice recognition, duplicate and authenticity checks
  • Budget commitment and automatic routing above limits
  • Travel standards matched by grade and city

AI Surfaces the applicable policy clause and flags sequential invoices, unusual frequency and deviation from the departmental average.

Purchase requests and orders

  • Requisition, quotation, supplier confirmation, order, receipt and payment in one line
  • Central purchasing with tiered approval
  • Two-way synchronisation of orders and master data with ERP

AI Recomputes a price baseline and its deviation, cross-checks comparable quotations, and recommends a review.

Contract management

  • Initiation, pre-review, execution, variation and archiving
  • Receipt and payment tracking with reconciliation
  • Electronic archive with expiry reminders

AI Compares clauses against your template and flags hidden risk and tax-inclusive discrepancies.

Budget control

  • Preparation, release, commitment, adjustment and execution analysis
  • Available balance validated live at each step
  • Multi-dimensional dashboards

AI Explains variance and suggests adjustments consistent with historical definitions.

HR and performance

  • Onboarding to offboarding, leave, overtime, travel booking
  • Review cycles started automatically
  • Multi-organisation routing and delegation

AI Summarises appraisal material and checks the review process against policy.

IT and admin services

  • Resource requests, asset issue, supplies, meetings and vehicles
  • Standard service catalogue and SLA reminders
  • Duty rosters, records and asset registers

AI Classifies tickets, recommends a handler and surfaces similar past tickets.

Application suite

Manufacturing systems

Built on WitBPM and WitAI. These are not five separate products: they share one process engine, one form and permission model and one agent foundation, so they interoperate by construction and can be adopted one at a time.

SRM Supplier relationship management

The supplier lifecycle: onboarding and qualification, grading and performance review, sourcing and quotation, purchase orders and reconciliation, annual review and exit.

  • Onboarding and qualification records
  • Sourcing, quotation and award
  • Orders, receipt and reconciliation
  • Performance rating and grading

AI Extracts qualification and quotation documents; recomputes a cost pass-through baseline and flags deviations; compares contract clauses against your template.

CPQ Configure, price, quote

Selection, pricing and quotation for configurable products: configuration rule validation, cost and margin calculation, tiered discount approval, quotation and contract generation.

  • Configuration and rule validation
  • Cost and margin calculation
  • Tiered discount approval
  • Quotation and contract generation

AI Extracts requirements from an enquiry and matches feasible configurations; flags unusual discounts with evidence, while the arithmetic stays deterministic.

QMS Quality management

Incoming, in-process and finished-goods quality: inspection plans and judgements, non-conforming material handling, corrective and preventive action, quality events and traceability, documentation and audit.

  • Inspection plans and rules
  • Non-conformance and concession
  • 8D / CAPA actions
  • Traceability and audit

AI Structures inspection reports; checks the completeness of corrective actions against your quality manual; groups similar historical defects and suggests root-cause leads.

MES Manufacturing execution

Shop-floor execution: work order dispatch and reporting, routings and work instructions, equipment and tooling, material readiness and WIP traceability, exception escalation.

  • Dispatch and production reporting
  • Routings and work instructions
  • Equipment, tooling and checks
  • WIP traceability and exceptions

AI Classifies shop-floor exceptions and recommends a response; turns process documents and past resolutions into searchable knowledge; analyses downtime and scrap deviation.

OMS Order management

Order fulfilment from intake to delivery: entry and validation, availability and scheduling, changes and insertions, shipment and invoicing, delivery tracking and complaints.

  • Order intake and validation
  • Availability and scheduling
  • Changes, insertions and rescheduling
  • Shipment, invoicing and tracking

AI Extracts key terms from customer orders and checks them against agreed pricing; warns about delivery risk early and proposes a revised date for a person to confirm.

Why build on a platform instead of buying five products

One organisation and permission model, one engine, one set of form and reporting tools means approval chains run continuously across systems. Downgrade a supplier in SRM and order fulfilment in OMS and incoming inspection in QMS can tighten with it, without another integration project.

How this relates to ERP, PLM and WMS

We do not replace systems of record. Every data object has one authoritative owner, and we synchronise two-way through the unified tool gateway, additively and non-invasively, so upgrades remain reversible.

Industry platform

WitWatt: PV and storage data aggregation and intelligent O&M

Built for third-party operations providers in solar and storage. It consolidates plant data scattered across different vendor clouds into one consistent set of figures, then connects it to work orders and AI diagnosis, closing the loop from data to field service.

Cross-brand, cross-platform ingestion

Huawei FusionSolar, Sungrow iSolarCloud, GoodWe, Solis, Growatt, Chint, Hoymiles, Hopewind and other major clouds. Official and northbound APIs are used wherever they exist; browser-based collection covers the platforms that publish none.

One set of figures

Daily, monthly, annual and lifetime yield, current power, equivalent full-load hours and storage charge/discharge, all normalised to kWh, kW and kWp at the point of ingestion. Differences in units, time zones and settlement days never reach downstream systems.

Observable collection health

Writes are idempotent per plant and date, so re-collection updates rather than duplicates. A sudden drop in plant count, globally or per account, raises an alert, so jobs cannot run green while the reports quietly drift.

Fault alarm aggregation

Inverter and platform-side alarms are pulled from each cloud, normalised to a common severity and status model, de-duplicated by the vendor alarm id, and pushed to WeCom, DingTalk or Feishu.

Closed-loop O&M (WitBPM)

Alarm to work order, dispatch, on-site, repair, re-inspection, acceptance and settlement, with every step recorded and replayable.

AI diagnosis (WitAI)

Attribution of yield deviation, peer comparison across similar plants, and automatic report drafting. Every conclusion carries its evidence chain and confidence, and is confirmed by a person.

WitWatt is deployed as a separate industry platform, sharing its lineage with the WitBPM process engine and the WitAI agent foundation. It runs alongside existing EMS, SCADA or ticketing systems.

Industries

Industry-specific processes

The platform itself is industry-agnostic: any organisation with approvals, collaboration and an audit requirement can use it. The industries below are simply where we have done the work.

Manufacturing

Automotive components, photovoltaics, equipment and consumer goods. Either management processes alone (purchase requests and orders, material requests, engineering change, budget and expense) or the full SRM, CPQ, QMS, MES and OMS suite above, synchronised two-way with your existing ERP, PLM and WMS.

Typical processes

  • Engineering change (ECR/ECN)
  • Procurement and materials
  • Non-conformance and quality events
  • Budget and expense control
Method

Four steps to get a process running

Inventory and prioritise

Map existing processes, policies and documents; rank them by mandatory, frequent and money-related; agree the first wave.

Configure and integrate

Build with the process and form designers, connect identity and business systems, configure agents from shipped capabilities without writing business code.

Sandbox and pilot

Blind-test recommendation quality on real samples, set the authorisation level for each judgement, and roll out in stages rather than all at once.

Operate and evolve

Publish acceptance and post-hoc accuracy monthly; widen or tighten authorisation on the data; re-parse policies when they change.

FAQ

Delivery and commercial questions

How do I request a demo, and how quickly do you reply?

Use the form on the contact page, email sales@witbpm.cn, or call 021-54890228. We reply within one working day. The demo is built around one of your own real processes.

How long does it take to validate an AI scenario?

A single-scenario proof of concept usually takes four to six weeks: offline validation on anonymised samples first, then a blind test on real samples, then agreement on the authorisation level for each judgement.

Which processes should we start with?

Start with processes that are mandatory, frequent and tied to money: expense claims, purchase requests, contract approval. They are used daily and affect people personally, which is what makes the change stick. Expand in stages from there.

Do you have a full suite of business systems as well as the platform?

Yes. Built on WitBPM and WitAI we offer SRM (supplier relationship management), CPQ (configure, price, quote), QMS (quality management), MES (manufacturing execution) and OMS (order management). They share one process engine, one organisation and permission model and one agent foundation, so they can be combined freely or adopted one at a time.

Do you have a ready-made platform for the solar industry?

Yes. WitWatt is a PV and storage data aggregation and intelligent O&M platform built on WitBPM and WitAI, for third-party operations providers. It ingests across vendor clouds including Huawei FusionSolar, Sungrow iSolarCloud, GoodWe, Solis and Growatt, normalises the data, then feeds work orders and AI diagnosis.

Do you support domestic (Xinchuang) software and hardware stacks?

Compatibility with domestic operating systems, databases and middleware is verified per project and documented in a compatibility report. Please confirm the specific list with us.

See all FAQs and the glossary →

Have a specific process in mind?

Send us a sample document and the relevant policy. You will get a feasibility view and a recommendation within two working days.