Harika Chebrolu
Engineering Agentic AI Systems at Enterprise Scale
Bengaluru, India
Actions
Chebrolu Bala Sai Harika is a Senior Software Engineer at Netskope, building production multi-agent AI systems that serve engineering teams at enterprise scale. Her work focuses on agent orchestration, intelligent routing, and tool integration using open standards and open models.
She has experience in AI agent architecture, including multi-agent orchestration with Google ADK, tool integration via Model Context Protocol (MCP), RAG pipelines with FAISS and sentence-transformers, and provider-agnostic LLM deployment with LiteLLM and Ollama. Her interests span agentic AI systems, cloud-native platforms, and DevOps intelligence — with a current focus on making multi-agent systems production-ready through efficient routing, observability, and modular design.
She has presented her work at international conferences and industry events, including Open Source Summit + ELC Europe 2026 (Prague) and IBM ISDL AI Storage Day, where her talk on Multi-Agentic AI for Ceph Infrastructure was selected from 35+ submissions. She previously led the design and build of a multi-agent orchestrator coordinating 27 contributors across 5 specialized AI agents at enterprise scale.
Area of Expertise
Topics
94% Accuracy, 40% Adoption: Why We Rebuilt Our Agent Around Trust, Not Intelligence
Our CI/CD agent diagnosed flaky tests with 94% accuracy. Engineers used it 40% of the time. The answer wasn't "it's wrong"—it was "I don't trust it enough to act on it."
This talk shares how we rebuilt our agent around trust—and why MCP's design patterns solve problems we spent months figuring out. (github.com/chebroluharika/agentic-ai-cicd-bot)
THE GAP: Our assistant parsed 10,000+ line logs across 500+ daily builds. Engineers still debugged manually because they couldn't see WHY.
TRUST PATTERNS (now in our MCP tools):
• Reasoning as Output: Not "retry" but "Found 3 similar failures, all resolved by retry. Confidence: 89%"
• Confidence Calibration: 90%+ = act. 60-90% = verify. <60% = guessing.
• Graceful Degradation: Uncertain? Say "I don't know" and suggest what to check.
• Correction Loops: One-click feedback. Adoption +34% with engineer ownership.
MCP ENABLES TRUST BY DEFAULT:
Structured responses force transparency. Schema validation prevents hallucinations. These patterns are now MCP-native in our toolkit.
RESULTS:
• Adoption: 40% → 87%
• Resolution: 23 min → 5 min
• NPS: -12 → +67
7 MCP Servers, 50+ Tools, Zero Duplicate Code: A 5-Minute Architecture Tour
We had a problem: every new integration meant writing the same code twice—once for our React dashboard, once for our AI assistant. JIRA, TestRail, Jenkins, GitHub—the duplication was unsustainable.
MCP changed everything. In this lightning talk, I'll show how we built 7 MCP servers that now power both our dashboard AND our AI agents from a single source of truth. 50+ tools, used daily by Dev, QE, and Management teams.
In 5 minutes, you'll see:
- The architecture: FastAPI as a unified backend → MCP Servers → External APIs (JIRA, TestRail, Jenkins, GitHub, GSheets, Release Calendar, Risk Predictor)
- The pattern: Thin MCP tools that call centralized APIs—one integration, two consumers
- Real metrics: 10+ hours/week saved per engineer; release tracking, regression monitoring, and production health checks unified.
- Why MCP wins: AI agents and dashboards evolve independently while sharing the same data layer.
We eliminated duplicate code, reduced maintenance burden, and shipped faster. All code is open source.
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top