Discuss your project
← All use cases

Use case · Sales

Many opportunities.
The right ones first.
The next step.

We start from your CRM data, your sales process and your team's experience. Together with sales and IT we clarify which signals count, who may see which customers and where sales decides. The result is your workflow for daily sales steering.

CORAProcess assistant

Your team

“Use our CRM, the order history from the ERP and our sales playbook. Create a workflow that scores open opportunities every morning: calculate the probability of closing, spot opportunities without a next step and summarise the latest customer contacts. Propose a concrete next step for each opportunity. Show everyone only their own customers. Discounts above the approval limit go to the head of sales.”

CORA is drafting the process …

The description becomes the workflow

Describe once.
Run every time.

Your description becomes a daily workflow: from current CRM data to a prioritised task list for every salesperson.

CORA builds the process. Your team reviews the test cases and approves it. Only then does it run for every matching event – with your permissions.

Score opportunities · Summarise context · Recommend next step

  1. CRM data
  2. Check rights
  3. Score opportunities
  4. Next step
  5. Task in CRM
Discuss your project

One run in detail

How CORA prepares a sales day.

A morning in sales: from open opportunities in the CRM to a task for the responsible person.

All names, numbers and values in this example are fictitious.

  1. TriggerTuesday, 7:00 am – daily run.
  2. IntegrationRead opportunities

    126 open opportunities in the CRM, 31 of them in Anna K.'s territory. CORA only sees the customers Anna K. is allowed to see.

  3. CodeScore opportunities
    OpportunityStageClosing probability
    CH-2041 Engineering NorthQuote64 %
    CH-2077 Hospital group SouthQualification38 %
    CH-1993 Logistics WestNegotiation81 %
  4. RuleCheck

    CH-2077: no activity for 23 days, flagged. CH-1993: discount request above the approval limit, sent to the head of sales.

  5. AISummarise and recommend
    CH-2041: the last contact was the technical meeting on 3 November; the delivery time for spare parts is still open. Next step: clarify the delivery time with production and send an updated quote by Friday.
  6. IntegrationCreate task

    Task in the CRM: “Clarify delivery time, update quote” – due Friday, assigned to Anna K.

  7. HumanDecide

    Anna K. takes on the task. The head of sales rejects the high discount and approves a lower one.

From existing documents to a tested workflow

From existing documents
to a tested workflow

1Your documents and example cases

ExampleOpportunity CH-2041 (fictitious)
  • Stage
  • Volume
  • Last contact
DocumentSales playbook
  • Stages
  • Next steps
ExampleLost opportunity CH-1877 (fictitious)
  • Loss reason

2Business systems and data

SystemCRM
  • Opportunities
  • Activities
  • Contacts
SystemERP
  • Order history
  • Open quotes
RuleDiscount limit
  • Defines the approval path

3People, roles and rights

Person cardSales
Own customers
Role cardHead of sales
Team and discounts
Other customerBlocked
No access
  1. Build process
  2. Test
  3. Approve

Running process

  1. CRM data
  2. Check rights
Active opportunity
  1. Summarise context
  2. Next step
No activity
  1. Reminder
  2. Task in CRM
Discount over limit
  1. Head of sales approval

Process steps in detail

What AI does – and what rules, code and integrations handle.

CORA uses AI where language, context or unstructured information needs to be understood. Calculations run as tested code, limits and responsibilities as rules, system access through defined integrations. Approvals stay with people.

  • AILanguage model: understands, summarises, drafts2×
  • RuleFixed conditions, thresholds, responsibilities3×
  • CodeCalculations and models, versioned and testable1×
  • IntegrationRead and write access via MCP servers or interfaces2×
  • HumanReview, approval and decision1×
  1. 01

    Daily start

    The workflow runs every morning and whenever an opportunity changes significantly.

    Rule

    Implementation: Schedule plus changes to stage or volume in the CRM

  2. 02

    Read opportunities and history

    CORA reads opportunities, activities, quotes and order history of permitted customers.

    Integration

    Implementation: MCP servers for CRM and ERP, within the user's rights

  3. 03

    Calculate closing probability

    Stage, age, contact frequency and purchase history produce a traceable score per opportunity.

    Code

    Implementation: Scoring model based on your history, versioned

  4. 04

    Spot inactive opportunities

    Opportunities without a next step are flagged.

    Rule

    Implementation: No activity within the agreed period, close date passed

  5. 05

    Summarise contacts

    The AI summarises recent conversations, open questions and objections in a few sentences.

    AI

    Implementation: Language model reads notes and emails for the opportunity

  6. 06

    Recommend next step

    The AI proposes a concrete next step and justifies it with the playbook and history.

    AI

    Implementation: Language model with the sales playbook

  7. 07

    Check discounts

    Discount requests above the limit become an approval task for the head of sales.

    Rule

    Implementation: Approval limit per role

  8. 08

    Create task

    The recommendation lands as a task with the responsible person. Customers are never contacted automatically.

    Integration

    Implementation: Write access to tasks and notes in the CRM

  9. 09

    Act or dismiss

    Your team adopts, changes or dismisses the recommendation.

    Human

    Implementation: Salespeople

Connected systems

  • CRMreads opportunities and activities, writes tasks and notesvia MCP server
  • ERPreads orders and open quotesvia MCP server
  • Email and calendarreads correspondence and meetings for the opportunityvia interface (API)
  • Company sign-inchecks identity and rolevia single sign-on

How we work

We start with your
actual work.

  1. 01

    Understand existing documents

    Sales playbook, stage definitions and won and lost example opportunities show us how your team recognises good opportunities. From them we derive scoring criteria, required fields and follow-up tasks. We clarify unclear stages with the head of sales.

  2. 02

    Connect data and business systems

    With your IT we connect CRM, ERP, email and calendar. Customer number and opportunity ID link the data. We define where data is read and where CORA may create tasks and notes in the CRM.

  3. 03

    Assign identities, rights and roles

    Identity comes from your company sign-in and the CRM. Salespeople see their customers, the head of sales sees the team. The AI acts on behalf of the responsible person and applies their visibility rules.

  4. 04

    Test together and go live

    From the description, documents and clarified system access, CORA drafts the process. Together with your business unit we select test cases and expected results. Testing runs without write access. Example tests: Active opportunity, opportunity without contact for weeks, discount request above the approval limit, missing contact data.

Your team decides on rules, AI steps and approvals. We activate the tested workflow, compare effort and results and practise the next changes in the skill workshop. Integrations, knowledge and reusable building blocks remain as the foundation for further processes.

Discuss your project

How the case
runs

Every day CORA reads the permitted opportunities, calculates the closing probability and spots opportunities without a next step. Each gets a short summary and a proposal that lands as a task in the CRM.

What it
produces

Prioritised opportunity list per person, summary of recent contacts, reasoned recommendation for the next step and approval tasks for discounts. Everything stays linked to the opportunity in the CRM.

Where your team
decides

Your sales team decides which recommendation to act on. Customers are not contacted automatically. Discounts above the approval limit require the head of sales.

More use cases

We show you where AI can take work off your hands right away.

Discuss your project