# Operational patterns by team

## Find the work that should run itself.

Start with the manual bottleneck: reading context, reconciling systems, or reshaping the same report. Diaphora turns that repeated work into a governed blueprint.

### The recurring pattern

1. Read scattered context  
2. Apply rules and reconcile  
3. Return a typed outcome

Same inputs · same controls · repeatable result

#### Create  
— Plain language in

#### Distribute  
— API, MCP, or scheduled

#### Govern  
— RBAC, ABAC, and DLP

## Choose your operating problem

Each pattern below starts with work a person repeats and ends with an inspectable, versioned outcome. Open a team to see the blueprints behind it.

### UC-01  
**Customer Success · 3 blueprints**  
**Account health without the gut feel**  
Nobody needs to read every Slack thread to know if an account is healthy — that's an inference problem, not a willpower problem. These blueprints read the scatter, Slack, usage, audit, and return the same structured health read every time.

#### Manual bottleneck  
Account health lives in someone's head, read fresh out of Slack threads every time.

#### Blueprint returns  
One structured health read — usage, audit, and error data, reconciled automatically

- BigQuery  
-  Slack

#### Adoption risk  
- Error patterns  
Explore [Customer Success](/content/use-cases/customer-success/index.html)

### UC-02  
**Revenue & Sales · 2 blueprints**  
**Reps stop walking in cold**  
The prep a rep needs already exists — in the CRM, the calendar, the transcript. Reconciling it by hand is the unnecessary step. These blueprints do the reconciling and hand back one document.

#### Manual bottleneck  
Call history, open items, and CRM gaps live in three systems — reconciled by hand, every time, if at all.

#### Blueprint returns  
One prep doc, assembled from CRM, calendar, and past calls — before every call

- Avoma  
- Google Calendar  
- Salesforce  
- Meeting summary  
Explore [Revenue & Sales](/content/use-cases/revenue-workflows/index.html)

### UC-03  
**Product Intelligence · 2 blueprints**  
**Every call read. Not the three you had time for.**  
Reading transcripts one at a time doesn't scale — and it's the wrong job for a person anyway. These blueprints read all of them, by topic, and hand back a structured answer.

#### Manual bottleneck  
The real answer is buried across dozens of transcripts — reading them one by one doesn't scale.

#### Blueprint returns  
Topic-level answers across the entire call corpus

- Avoma  
- Google Drive  
- Keyword research  
- Conversational  
Explore [Product Intelligence](/content/use-cases/product-intelligence/index.html)

### UC-04  
**Platform Analytics · 2 blueprints**  
**Know which MCP servers earn their keep. Without the joins.**  
Every question about fleet health is a manual join across telemetry tables. That's not judgment — it's plumbing. These blueprints make the join, and hand back the same snapshot on a schedule.

#### Manual bottleneck  
Understanding one server's real performance means joining tables by hand. Every time.

#### Blueprint returns  
One fleet-wide view — usage, errors, dormant connections

- BigQuery  
- Server telemetry  
- Adoption  
- Fleet ranking  
Explore [Platform Analytics](/content/use-cases/platform-analytics/index.html)

## True of every blueprint, whatever the use case

- **Zero prompt drift**  
Every blueprint is a versioned contract. Run 1 and run 10,000 behave identically.
- **Scoped sessions**  
Each LLM call sees only the context it needs — no one giant prompt, no context rot.
- **Typed output**  
Blueprints return validated objects pinned to a schema, not text you have to parse.
- **Reusable like an API**  
Parameterise once and call it from anywhere — versioned, auditable, shareable.