Skip to content
CloudOps
Newsletter
All prompts
AI for Microsoft Teams Difficulty: Intermediate ClaudeChatGPT

Teams Salesforce Integration for Customer Impact Tracking Prompt

Track customer impact during incidents — link Salesforce account / case data to Teams incident channels, surface impacted customers, prioritize comms by ARR / criticality, and auto-update post-incident.

Target user
Platform engineers + customer success bridging incident response and customer accounts
Difficulty
Intermediate
Tools
Claude, ChatGPT

The prompt

You are a senior platform engineer who has built Teams ↔ Salesforce integrations that turned blind incident response ("how many customers are affected?") into precise, prioritized comms.

I will provide:
- Salesforce org setup (CRM model — Accounts, Contacts, Cases, Opportunities, Custom Objects)
- Service identification (which Salesforce field maps to which infrastructure service)
- Customer tiers (Enterprise / Mid / SMB) + their ARR
- Existing customer-impact tracking (manual / partial)
- Compliance overlay (CCPA / GDPR for customer data in Teams)

Your job:

1. **What data to surface in Teams during an incident**:
   - **Customers affected** — by infrastructure service or by customer report
   - **Per-customer signal**: ARR tier, named CSM, last open case, sentiment
   - **High-touch accounts** — proactive outreach required
   - **Risk signal** — affected customers in upcoming renewal cycle
   - **Aggregate signal** — total ARR affected, count by tier

2. **Architecture**:
   - **Service-to-Account mapping** — your service catalog + Salesforce account custom field
   - **Real-time refresh** — webhook from Salesforce on Case events; periodic poll for state
   - **Teams Bot** — pulls from Salesforce, posts as Adaptive Cards in incident channels
   - **Connector** — Logic App / Power Automate flow or custom service

3. **Bot commands** in incident channel:
   - `@bot impact <service>` — lists customers affected, sorted by ARR
   - `@bot account <name>` — pulls Salesforce snapshot for one account
   - `@bot escalate <account>` — creates a Salesforce Case + notifies CSM
   - `@bot summary` — aggregate impact (ARR, count, tiers)
   - `@bot postmortem` — generate customer-impact section for postmortem

4. **Adaptive Card design** for "customers affected" output:
   - **Header** — service + impact start time + estimated affected count
   - **FactSet** — total ARR affected, count by tier
   - **Top 5 accounts table** — name, tier, ARR, CSM, last open case, sentiment
   - **Actions** — Export full list, Create CSM outreach plan, Open Salesforce report

5. **CSM outreach plan**:
   - For top-tier accounts: bot auto-DM CSMs with affected account context
   - For mid-tier: bot posts in CSM Teams channel with bulk list
   - For SMB: in-app notification only
   - Track outreach completion in Salesforce activity log

6. **Postmortem integration**:
   - Customer-impact section auto-populated:
     - Total accounts affected, ARR at risk
     - Top 10 accounts listed with their open cases
     - Time-to-comms per tier
   - Link from postmortem to Salesforce report

7. **Sentiment + churn signal**:
   - Pull customer sentiment from Gainsight / Salesforce health score
   - Flag at-risk customers ("renewal in 30d AND active incident") for elevated attention
   - Auto-create CS Outreach tasks for at-risk

8. **Compliance & data handling**:
   - PII (account names, contact emails) handled per regime
   - Don't post PII in non-compliant channels (use private channel for high-tier accounts)
   - Sensitivity label on cards with customer data
   - Retention aligned to incident retention policy

9. **Authentication**:
   - Service Principal in Azure AD with delegated Salesforce permissions
   - Or service-to-service via Salesforce Connected App + OAuth
   - Don't use user tokens for service-wide queries

10. **Anti-patterns to avoid**:
   - Posting full account list in public channels (compliance + noise)
   - Pulling fresh data on every command (cache; rate-limit Salesforce)
   - Ignoring customer sentiment when prioritizing comms
   - Not closing the loop in Salesforce (update Case + Activity)
   - Real-time over polling without throttling (Salesforce limits)

Output as: (a) data flow architecture, (b) Service-to-Account mapping pattern, (c) bot command catalog, (d) Adaptive Card JSON for customer impact summary, (e) CSM outreach plan generation, (f) postmortem integration, (g) sentiment + churn signal usage, (h) compliance + auth.

Bias toward: prioritize comms by ARR + sentiment, automate CSM outreach plan, every action logs back to Salesforce, compliance-aware data handling.
Newsletter

Free: the DevOps AI Incident-Triage Cheat Sheet

Subscribe and we’ll send you the one-page cheat sheet — plus weekly AI prompts, automation ideas, and tool reviews for infrastructure engineers. One email a week. No spam, unsubscribe anytime.

  • AI Incident-Triage Cheat Sheet (PDF)
  • Access to 1,603 DevOps AI prompts
  • One practical workflow email per week