agentic ai · multi-agent orchestration

Autonomous Customer Support & Action Engine

A production-shaped support platform where agents don't just answer — they route, retrieve, act, verify their own work, and escalate to a human when the stakes are high enough to deserve one.

designed and developed by

Nikhil Chary Sriramoju

Every layer earns the word "agentic"

A2A multi-agent delegation via Agent CardsRouterSupervisorNode
Background agent that self-escalates SLA breaches with no user promptProactiveSLAAgent
Self-correction — captures tool tracebacks, repairs its own arguments, retriesActionExecutorNode
Self-verification — a critic agent checks the executor's work before replyingVerificationCriticNode
CNN classifies uploaded damage photos, feeds the verdict back into planningapp/vision/
Hybrid retrieval — dense embeddings + BM25, cross-encoder re-rankedknowledge_base.py
Dynamic tool discovery over JSON-RPC, HTTP and stdio transportsmcp/client.py
Semantic cache skips the whole graph on near-duplicate questionssemantic_cache.py
High-value actions pause for human approval, resume from a checkpointinterrupt_before
PII scrubbed — regex and NER — before every LLM call and every log linepii_sanitizer.py

One message, five agents, one verified answer

01 RouterSupervisorNode reads Agent Cards, delegates by intent
↓ image attached?
02a VisualInspectionNode CNN classifies the damage photo
02b PolicyRAGNode hybrid retrieval over support policy
↓
03 ActionExecutorNode calls MCP tools · retries and self-corrects on failure
↓ high-value or destructive?
— Human approval queue graph pauses, resumes from Postgres checkpoint on decision
↓
04 VerificationCriticNode checks the executor's own output before it reaches the user
running in parallel — ProactiveSLAAgent polls the approval queue on its own schedule and escalates anything left pending too long, independent of any chat turn.

Tech stack

orchestration & protocols

LangGraph AsyncPostgresSaver Model Context Protocol A2A Agent Cards

retrieval & vision

BM25 Dense embeddings Cross-encoder reranking PyTorch CNN

backend & data

FastAPI SQLAlchemy 2.0 async Postgres Redis

observability & ops

OpenTelemetry LangSmith DeepEval Docker Compose

Up and running in one command

# clone, then: cd docker OPENAI_API_KEY=sk-... docker compose up --build # brings up the API, Postgres, Redis, # a mock MCP tool server, and an OTEL collector curl http://localhost:8000/healthz

Full setup, local (non-Docker) instructions, and production hardening notes are in the repository README.