Technology & Software

Developer Support Copilot

Designed for Software engineer and AI platform engineer

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.

Contract TEC-01 · primary aggregate ServiceOperationalContext · mode loading

Decision brief

Change approval and production execution: evidence ready for review

This brief starts with the decision, evidence, and accountable owner. The guided workflow then shows how the recommendation was produced.

Decision signals

The evidence and control points that shape this recommendation.

Decision owner

Service owner or change advisory approver

The named role remains accountable for the consequential decision.

Governed evidence

6 record types

Structured records and cited text ground the recommendation.

Workflow

5 controlled stages

Each transition records its input, output, status, and audit context.

Human controls

1 approval gate

Approval gates prevent the copilot from making consequential decisions.

Business problem

A retrieval API's p99 latency triples in West Europe while error rate stays flat.

Decision to make

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.

Outcome to show

executedChange gives Service owner or change advisory approver the evidence needed to begin the final governed business outcome, with the decision trail retained for review.

  1. 1Symptom and telemetry correlation
  2. 2Deployment bisection
  3. 3Prior-art and runbook retrieval
  4. 4Remediation proposal with blast radius
  5. 5Change approval and production execution

Step 1 of 5

Ready: Start with the business question, then use the single button above.

The output appears here immediately. More technical evidence remains available below.

System logic, GenAI, and human accountability

The demonstration keeps deterministic controls, AI assistance, and approval separate.

System logic

Source systems enforce identity, workflow order, policy filters, and record updates.

GenAI contribution

Retrieval and generation assemble relevant evidence into a cited recommendation or draft.

Human accountability

Service owner or change advisory approver verifies material claims and approves the consequential action.

Workflow stages

Run the stages in order before using the Copilot. Every stage explains what happens, why it matters, the evidence it uses, and the complete API request and response.

Seeded record
Loading
Document type
Loading
Container
Loading
Partition key
Loading
Current stage
Loading

API demonstration guidance

Run a stage to see its explanation, evidence, full request, and full response.

Grounded chat

Ask a question and receive an answer grounded in retrieved ServiceOperationalContext evidence.

Answer and evidence

Select a starter question or enter your own.

Evidence

Domain implementation workspace

Loaded live from /api/config, /api/domain/model, and /api/domain/sample.

Domain objective
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.
Primary aggregate
ServiceOperationalContext
Primary container
serviceOperationalContexts
Hierarchical key
/tenantId + /serviceId
Schema version
1

Sample scenario

A retrieval API's p99 latency triples in West Europe while error rate stays flat. The copilot correlates the window to a deployment 40 minutes earlier that changed the embedding model deployment from a provisioned to a standard SKU, shows tokens-per-minute utilization pinned at 100 percent with 4,900 throttled requests, and finds two prior tickets with the same symptom resolved by restoring provisioned throughput. It cites the capacity runbook, which classifies SKU changes on tier-1 services as change-advisory-required, and proposes a rollback of the SKU change plus a provisioned-throughput increase, assessing blast radius as single-region. The service owner approves at the required level and the change executes.

Physical Cosmos DB containers

Every container provisioned for this accelerator with its hierarchical partition key.
Container Role Hierarchical partition key Document types
serviceOperationalContexts Primary /tenantId + /serviceId Service, DeploymentManifest, PlatformTelemetry, IncidentTicket, RemediationProposal
serviceRunbookLibrary Reference /tenantId + /procedureCategory RunbookChunk

Document types

Contract document types, their owning container, and their identifier pattern.
Type Container Partition key Identifier pattern Embedding fields
Service serviceOperationalContexts /tenantId + /serviceId service::{serviceId} None
DeploymentManifest serviceOperationalContexts /tenantId + /serviceId service::{serviceId}::deployment::{deployedAtUtc}::{releaseVersion} None
PlatformTelemetry serviceOperationalContexts /tenantId + /serviceId service::{serviceId}::telemetry::{metricTimestampUtc}::{metricName} None
RunbookChunk serviceRunbookLibrary /tenantId + /procedureCategory procedure::{procedureCategory}::runbook::{runbookDocId}::{chunkOrdinal} chunkVector
IncidentTicket serviceOperationalContexts /tenantId + /serviceId service::{serviceId}::ticket::{ticketNumber} symptomVector
RemediationProposal serviceOperationalContexts /tenantId + /serviceId service::{serviceId}::remediation::{proposalId} rationaleVector

Query patterns