01 · Executive Summary
A next-generation support automation initiative
Telefónica Tech's AgentOps is a next-generation, AI-powered support automation initiative. Born from hands-on experimentation with AWS AgentCore after training events in December 2025, it evolved from two independent MVPs — a Cost Assistant and an Observability Agent — into a unified, production-grade Tier 1 support automation platform.
Both MVPs were validated with 3 select clients in Q1 2026, achieving an 80% reduction in information retrieval time. Telefónica Tech's AgentOps takes this proven foundation to enterprise scale — with a multi-channel serverless architecture (web chat, voice, and ITSM) built on Amazon Bedrock AgentCore, targeting 5x volume capacity, 60% capacity reallocation toward innovation, and 24/7 autonomous operation.
⚡ Total annual investment: $53,465.42 USD — fully offset by AWS sandbox credits (effective net cost: $0).
Timeline: First MVPs (December 2025), client validation & strategic vision (Q1 2026), full production deployment April – October 2026.
02 · Problem Statement
The current state
Partner support teams manage expanding portfolios of technical inquiries across increasingly complex AWS environments. Each ticket follows a familiar journey: classify, verify information, investigate resources, draft guidance, monitor responses, and coordinate escalations. Technical engineers are heavily burdened by these repetitive, low-complexity tasks that do not require human intuition — creating a significant "innovation tax."
Key challenges
- Reactive support model: Teams respond to issues as they arrive, with no capacity for proactive service.
- Single-channel constraint: Customers are funneled through one interface (ITSM tickets) even when a quick chat or phone call would resolve the issue faster.
- Linear scaling constraint: Growing the customer base requires proportionally growing headcount.
- Talent misallocation: Engineers capable of complex troubleshooting spend time on routine analysis.
- Knowledge silos: Complex issue resolutions stay locked with individuals rather than becoming team assets.
- Response time limitations: Human-dependent support cannot deliver 24/7 near-instantaneous responses.
- Scalability ceiling: Current infrastructure cannot handle 5x ticket volume growth.
Business impact of inaction
- Inability to scale the customer base without significant hiring investment.
- Continued erosion of engineering capacity for innovation and proactive client improvements.
- Loss of institutional knowledge as it remains locked with individual engineers.
- Competitive disadvantage as peers adopt AI-driven support models.
- Increasing operational costs per ticket as complexity and volume grow.
03 · Strategic Vision
From proof-of-concept to production scale
A deliberate two-phase strategy validates the concept, then scales to enterprise production.
Phase A — First MVPs & Validation (December 2025 – Q1 2026)
Two independent MVPs built after AWS training events on AgentCore and Strands Agents SDK:
- Cost Assistant (Maykel Cano) and Observability Agent (Marcos Moreno) — standalone web apps with chat interface connected to client AWS accounts.
- Built on AgentCore Runtime, Strands SDK, Bedrock (Claude), Cognito with MFA, DynamoDB from day one.
- Presented to Altostratus leadership. Deployed to 3 select clients — 80% faster information retrieval for decision-making.
- AWS training on multi-agent orchestration confirms the unified platform approach — the demo featured 3 agents (cost, observability, remediation), 2 of which the team had independently built.
- Ester Nieto joins as Product Owner, gathering client feedback and validating real-world use cases to inform feature priorities across the platform roadmap.
Phase B — Telefónica Tech's AgentOps (April – October 2026)
Takes the validated foundation to enterprise production scale with a multi-channel serverless architecture:
- Three entry channels — Web Chat (React SPA on CloudFront), Voice (AI Voice Agent + Nova Sonic S2S), and ITSM (ServiceNow webhooks) — all converging on the same Supervisor.
- Bedrock AgentCore for managed agent runtime, memory, identity, and gateway (MCP).
- MCP tools via AgentCore Gateway for intelligent resolution across all specialist agents.
- Bedrock Knowledge Bases for continuously improving responses.
- DynamoDB with KMS encryption for conversations and account configuration.
- Full observability with CloudWatch (logs, metrics, alarms, dashboards).
- Multi-account support, AWS Support escalation, cross-region inference.
Strategic objectives
| # | Objective | Target |
| 1 | Automate Response | Near-instantaneous response times for L1 inquiries using specialized AI agents and Amazon Bedrock. |
| 2 | Multi-Channel Access | Web chat, voice (phone), and ITSM tickets — all served by the same supervisor and knowledge base. |
| 3 | Enhance Scalability | Serverless backend capable of handling 5x current ticket volume. |
| 4 | Proactive Value | Reallocate 60% of support team capacity toward proactive consulting and new solution development. |
| 5 | Capture Knowledge | Automatic documentation builds a searchable, ever-growing knowledge base from every resolved interaction. |
| 6 | Full Observability | Real-time monitoring of AI accuracy and system performance via Amazon CloudWatch. |
04 · Validated Foundation
Multi-agent architecture
| Agent | Domain Expertise |
| Supervisor Agent | Validates AWS context, extracts service & region info, routes to the most appropriate specialist agent. |
| Observability Agent | CloudWatch metrics, logs, and alarms. X-Ray distributed traces. Guided troubleshooting: alarms → metrics → logs → traces. |
| Cost Agent | AWS cost queries, forecasting, anomaly detection, rightsizing. Access to Cost Explorer, Compute Optimizer, Budgets, Pricing. |
| Security & Compliance Agent | Security auditing, compliance checks, configuration analysis, vulnerability detection. Coming soon. |
| Remediation Agent | Autonomous L1 incident resolution with human-in-the-loop approval. Executes corrective actions with operator confirmation. |
Validated real-world scenarios
- Cost Analysis: "How much did we spend this quarter on EC2?" — The Supervisor routes to the Cost Agent, which queries Cost Explorer, breaks down by service, account, and region, and provides optimization recommendations.
- Active Alarms: "What are the active alarms in production?" — The Supervisor routes to the Observability Agent, which checks CloudWatch alarms and provides guided troubleshooting: alarms → metrics → logs → traces.
- Log Analysis: "Show me error logs from the last hour" — The Supervisor routes to the Observability Agent for CloudWatch log analysis with pattern detection and root cause identification.
05 · Solution Architecture
Multi-channel serverless architecture
Three entry channels — web chat, voice, and ITSM — converge on the same Supervisor, the same specialist agents, and the same knowledge base. Every component is serverless; every interaction is isolated; every channel benefits from every other channel's learnings.
Entry channels
| Channel | Flow |
| 1 — Web Chat | React SPA → CloudFront → AgentCore Runtime → Supervisor → Specialist Agent → AI Response. |
| 2 — Voice | Phone Call → AI Voice Agent → Nova Sonic S2S → AI Agent → MCP → AgentCore Gateway → Supervisor. |
| 3 — ITSM | ServiceNow → API Gateway → Lambda Bridge → AgentCore Runtime → Supervisor → Response back to ticket. |
Platform layers
| Layer | Components |
| Entry Points | CloudFront (Web Chat), AI Voice Agent (Voice), API Gateway (REST, HTTP, WebSocket) + ServiceNow webhooks (ITSM). |
| AI / Agent Layer | AgentCore Runtime, Gateway, Memory, Identity, Browser Tools; Anthropic Claude on Amazon Bedrock; Nova Sonic speech-to-speech. |
| Specialized Agents | Supervisor, Observability, Cost, ITSM, Security & Compliance, Remediation. |
| Compute | ECS Fargate, AWS Lambda. |
| Knowledge & Storage | Amazon S3, Amazon DynamoDB, Bedrock Knowledge Bases. |
| Observability | Amazon CloudWatch (Logs, Metrics, Alarms, Dashboards). |
| Integration | ServiceNow, AWS Support API, Bedrock Knowledge Bases. |
AWS services inventory
| Service | Configuration | Purpose |
| Amazon Bedrock | Geo Cross-Region, On Demand, 1 req/min. | Generative AI inference for all agents. |
| Bedrock AgentCore | Runtime, Gateway (MCP), Memory, Identity, Browser Tools. | Managed agent orchestration & observability. |
| AI Voice Agent | AI Agents · Nova Sonic S2S · MCP tools · Return-to-Control. | Voice channel — bidirectional audio streaming with human escalation. |
| Amazon CloudFront | Global CDN in front of the React SPA. | Low-latency web chat delivery. |
| API Gateway | REST, HTTP, WebSocket. | ITSM entry point + ServiceNow webhook receiver. |
| ECS Fargate + Lambda | Containerized backend, serverless functions. | Backend API, MCP servers, ITSM bridge. |
| DynamoDB | On-demand, KMS encryption. | Conversations, session state, account configuration. |
| S3 | Standard storage. | Frontend hosting (SPA), data source for Bedrock Knowledge Bases. |
| CloudWatch | Logs, Metrics, Alarms, Dashboards. | Full observability stack. |
| Secrets Manager | Encrypted credential storage. | API keys, integration tokens, service credentials. |
Architecture design patterns
- Multi-Channel Access: Web chat, voice, and ITSM tickets all converge on the same Supervisor via AgentCore Runtime and the AgentCore Gateway (MCP), so every channel reuses the same agents and knowledge base.
- Multi-Agent Specialization: Supervisor routes to domain-specific agents rather than a single general-purpose AI.
- MCP Tools: Specialist agents connect to AWS services via MCP servers deployed on AgentCore Gateway for intelligent resolution.
- Human-in-the-Loop: Return-to-control hand-offs on voice (Connect), operator confirmation for critical actions.
- Serverless-First: Every compute component scales automatically.
- Knowledge-Augmented AI: Bedrock Knowledge Bases for agent context, continuously enriched from resolved interactions.
- Full Observability: Dedicated CloudWatch integration across channels, agents, and infrastructure.
- Agent Isolation: AgentCore provides runtime isolation with dedicated identity management per session.
- Webhook-Driven Integration: ServiceNow webhooks trigger agent processing; ITSM status updates maintain awareness.
06 · Cost Analysis
Investment breakdown
$53,465.42
Annual (12 months)
⚡ All infrastructure costs are fully offset by AWS sandbox credits — covering API calls to Bedrock, AgentCore Runtime, and DynamoDB operations. Effective net cost: $0.
Monthly cost breakdown by service
| Service | Monthly Cost (USD) | % of Total |
| Amazon Bedrock | $2,744.28 | 61.8% |
| Amazon API Gateway | $599.74 | 13.5% |
| Amazon CloudWatch | $326.35 | 7.4% |
| Amazon Bedrock AgentCore | $206.90 | 4.7% |
| Amazon DynamoDB | $172.28 | 3.9% |
| Amazon S3 | $51.09 | 1.2% |
| AWS Lambda | $0.59 | <0.1% |
| Total | $4,438.48 | 100% |
07 · Project Plan
Full timeline
| Phase | Duration | Start | End | Status |
| First MVPs | — | 2025 | Dec 2025 | ✅ Validated |
| Q1 2026 Enhancements | ~90 days | Jan 2026 | Mar 2026 | ✅ Completed |
| Architecture Design | 30 days | 20 Apr 2026 | 20 May 2026 | In Progress |
| Delivery / Build | 100 days | 20 May 2026 | 30 Sep 2026 | Planned |
| Testing & Validation | 50 days | 30 Sep 2026 | 16 Oct 2026 | Planned |
Phase 1 — Architecture Design (30 days)
Rebuild from the ground up — unify both MVPs under a single supervisor, design AI Voice Agent voice flows, define API contracts for all agents, establish DynamoDB data models, configure AgentCore Memory and Gateway, and lay the groundwork for plug-and-play agent onboarding.
Phase 2 — Delivery / Build (100 days)
Build end-to-end orchestration flow with multi-account AWS support. Channels added incrementally — web chat first, then ServiceNow ITSM bridge, then AI Voice Agent voice. All agents on AgentCore with native + MCP tools, Bedrock Knowledge Bases integration.
Phase 3 — Testing & Validation (50 days)
End-to-end validation across all channels with real scenarios, AI accuracy testing against MVP baseline, load testing, multi-account security review, observability verification, and production deployment for managed clients.
08 · Business Value
Operational transformation
| Metric | Current State | AgentOps Phase 1 | AgentOps Full |
| L1 Response Time | Minutes to hours | Seconds (AI analysis) | Seconds, 24/7 |
| Support Availability | Business hours | Business hours (triggered) | 24/7/365 autonomous |
| Volume Capacity | Baseline | +40–60% | 5x baseline |
| Engineer Time on L1 | ~100% | Reduced (draft review) | ~40% (60% freed) |
| Knowledge Capture | Individual / ad-hoc | Bedrock Knowledge Bases | Continuous learning KB |
| Operating Model | Reactive | Semi-automated | Fully proactive |
Value for the business
- Multi-Channel Customer Experience: Customers choose how they engage — web chat, phone call, or ticket — with consistent quality and shared context across all channels.
- Revenue Growth: Scale customer base 5x without proportional cost increase.
- Talent Optimization: 60% of support engineering capacity redirected to proactive consulting, innovation, and feature development.
- Competitive Differentiation: AI-powered support with specialized agents and voice-first interaction differentiates the offering.
- Knowledge Compounding: Every resolved interaction — regardless of channel — enriches the knowledge base, making future resolutions faster.
- Client Retention: Faster response times and proactive service improve satisfaction and reduce churn.
- Serverless Economics: Pay-per-use infrastructure scales automatically with demand.
09 · Risk Considerations
Risks & mitigations
| Risk | Mitigation |
| AI response accuracy | Return-to-control for critical actions, full CloudWatch observability, continuous KB updates. |
| Cost overrun on Bedrock | On-demand pricing with monitoring, cross-region inference, token budget controls, potential shift to AWS Support Enterprise Experience. |
| Knowledge base staleness | Bedrock Knowledge Bases auto-enriched, automated refresh pipelines, version-controlled docs. |
| Multi-account security | AgentCore Identity managed auth, cross-account IAM validated in Q1 2026, least privilege, Secrets Manager. |
| Integration complexity | ServiceNow webhook integration planned, secure validation, complete audit logging. |
| New channels (voice, web) | AI Voice Agent + Nova Sonic are managed services with native AgentCore Gateway (MCP) integration; Return-to-Control provides a proven escalation path to human agents; channels share the same supervisor and KB, minimizing divergence. |
| Timeline risk (100-day build) | Two MVPs validated with real clients, core agent logic proven, phased delivery, parallel development. |
| Agent routing accuracy | Two specialist agents validated independently, supervisor design informed by AWS training on multi-agent patterns, continuous improvement through KB. |
10 · Conclusion
A strategic investment
Telefónica Tech's AgentOps represents a strategic investment in AI-driven operational transformation, built on a proven foundation. Two independent MVPs — Cost Assistant and Observability Agent — have already validated that specialized AI agents can deliver 80% faster information retrieval for real clients, with AgentCore, Strands SDK, and Bedrock from day one. The production architecture unifies these validated agents into a full multi-channel serverless platform — web chat, voice, and ITSM — all sharing the same supervisor and knowledge base.
⚡ At $53,465/year in infrastructure costs — fully offset by AWS sandbox credits (net cost: $0) — the production deployment delivers 5x support capacity across three channels, 60% talent reallocation, automatic knowledge capture, and a fundamental shift from reactive to proactive service delivery.
The foundation is proven. The Q1 2026 enhancements are underway. The production architecture is designed. The business case is clear: automate the routine, meet customers on every channel, capture the knowledge, unleash the talent, and scale without limits.