Developer Support Copilot
Outcome
Give software and AI platform engineers one grounded surface that diagnoses service incidents and platform constraints together: correlate deployment manifests, quota and token telemetry, runbooks and prior tickets so a latency spike or a model capacity wall is explained and remediated with an approved, cited change.
| Portfolio attribute | Value |
|---|---|
| Primary persona | Software engineer and AI platform engineer |
| Primary aggregate | ServiceOperationalContext |
| Cosmos DB containers | 2 |
| Grounding data | code metadata, architecture standards, deployment manifests, quota and usage telemetry, tickets, runbooks, logs |
| Development estimate | USD 60-220 monthly dev estimate |
| Runtime options | Python FastAPI and C# ASP.NET Core |
Productivity hypothesis
These measures reflect the workflow, evidence, decision boundary, and industry risk for this use case.
| Impact type | Measure | Conservative internal assumption | Customer measurement |
|---|---|---|---|
| Productivity | Issue-to-diagnosis-ready time | 15-30% reduction | (baseline median issue-to-diagnosis minutes - assisted median minutes) / baseline median minutes * 100 |
| Quality or risk | Diagnosis and correlation correctness | 5-10 percentage-point improvement | assisted percentage meeting the diagnosis-correctness rubric - baseline percentage |
Important: Conservative internal pilot assumptions only; not public benchmarks, commitments, or expected customer results. Validate against a comparable baseline or matched control cohort with mandatory human review.
Rationale: Incident, quota, deployment, and migration evidence supports faster diagnosis preparation for engineering teams.
Pilot guardrail: Engineers approve all production changes, migrations, quota changes, and governance actions.
Customer validation plan
- Baseline the current workflow with representative users and tasks.
- Run the accelerator on the same task mix with human review retained.
- Measure issue-to-diagnosis-ready time and diagnosis and correlation correctness with the documented formulas.
- Replace internal assumptions with customer-observed results before a business case.
Why Azure Cosmos DB
This AI solution needs an operational data plane, not only a vector index:
- Hybrid vector and full-text retrieval combines semantic recall with exact identifiers, codes, names, and domain language.
- Hierarchical partition keys and metadata predicates keep tenant and domain boundaries in the normal query path.
- Operational JSON, source chunks, workflow and agent state, feedback, and audit records remain together for low-latency reads and governed writes.
- Change feed reacts to source and operational updates without polling.
- Autoscale throughput, configurable consistency, and multi-region distribution support variable demand and enterprise availability.
Domain workflow

| Stage | Actor | Input → output | Approval |
|---|---|---|---|
| 1. Symptom and telemetry correlation | Developer support copilot | PlatformTelemetry → correlatedSymptomSet | Policy controlled |
| 2. Deployment bisection | Change correlation service | DeploymentManifest → suspectChangeSet | Policy controlled |
| 3. Prior-art and runbook retrieval | Retrieval orchestrator | suspectChangeSet → RunbookChunk | Policy controlled |
| 4. Remediation proposal with blast radius | Developer support copilot | RunbookChunk → RemediationProposal | Policy controlled |
| 5. Change approval and production execution | Service owner or change advisory approver | RemediationProposal → executedChange | Human required |
Technical architecture

Cosmos DB data model
| Container | Hierarchical partition key | Documents | Search paths |
|---|---|---|---|
serviceOperationalContexts | /tenantId, /serviceId | Service, DeploymentManifest, PlatformTelemetry, IncidentTicket, RemediationProposal | /symptomVectorEmbedding, /rationaleVectorEmbedding, /symptomVector, /rationaleVector |
serviceRunbookLibrary | /tenantId, /procedureCategory | RunbookChunk | /chunkVectorEmbedding, /chunkVector |
Query contract
| Query | Container | Scope | Purpose |
|---|---|---|---|
| QuotaHeadroomByModelDeployment | serviceOperationalContexts | single-partition | Show which model deployments are approaching their token or provisioned-throughput ceiling in a region. |
| DeploymentBisectionWindow | serviceOperationalContexts | single-partition | List deployments that landed inside the regression window for bisection. |
| SimilarPriorIncidents | serviceOperationalContexts | single-partition | Find prior tickets with a semantically similar symptom to reuse a proven resolution. |
| TierAppropriateRunbookRetrieval | serviceRunbookLibrary | single-partition | Retrieve the remediation procedure valid for this service tier along with its change-control level. |
Python and C# services route each document type to its declared container and hierarchical partition key. ETag-based writes protect mutable aggregates, while append-only records and bounded cross-partition queries preserve scale.
Azure deployment

Clone the source repository, authenticate with Azure, and run:
Set-Location accelerators/technology-software/developer-support-copilot
az login
./Deploy.ps1 -Runtime python -Location eastus2
Change python to csharp to deploy the .NET implementation.
Explore the implementation
- Launch signed-in demo
- Implementation article
- Domain data model
- Workflow and API contract
- Python application
- C# application
- Domain container Bicep
- Platform Bicep
- Cost and configuration
- Source repository