Agent systems
Design and implementation of agents with prompts, tools, memory, business rules, and evaluation fixtures.
PythonGoogle ADKVertex AI/Geminitool callingprompt regression
Production AI agents on GCP
I am Rashid Azarang. I build the software layer that lets language models use tools, read business records, run in cloud runtimes, and leave a trace after they act.
The work combines Python, Google ADK, Agent Registry, Vertex AI/Gemini, Cloud Run, CI/CD, observability, IAM, Secret Manager, MCP, and versioned agent artifacts.
What I build
The shape is practical: agents that call tools, touch business data, and can be deployed, tested, versioned, and reviewed.
Cloud delivery
Cloud-native packaging, deployment, private access, and release paths for agent services.
GCPCloud RunDockerCI/CDAzure DevOpsAgent Registry
Governed actions
Tool contracts, API integrations, observability, secrets, identity, and evidence trails for agent work.
MCPAPIsobservabilityIAMSecret Managerevidence
Selected work
A few public systems and case studies that show the same pattern in different environments.
MCP gateway
MetaMCP
Gateway work for reducing and exposing MCP tool surfaces.
MCP server
Airtable MCP
Airtable bases, tables, records, and schema exposed through MCP.
Python agent
Airtable AI Agent
Python workflows using Airtable tools and business records.
Business workflow
Cotizera Agents
Quote intake, PDF generation, WhatsApp follow-up, and pipeline updates.
Runtime work
WebHarness
A macOS runtime for web apps with filesystem, SQL, vault, MCP, agents, and packaged distribution.
Evidence layer
Mentu Protocol
Ledgers, hashes, commitments, and evidence for agent actions.
Data and operations
Agents only become useful when the records underneath them are clean, queryable, and close to the workflow.
Data platform
Dataware
Managed warehouse and MCP access for business data across 50+ integrations.
Dataware
GreenLight
Supabase warehouse with MCP, non-technical access, and issue detection.
Dataware
HWG and TecAssured
Claims, documents, 13 collections, relational warehouse, materialized views, and indexes.
Case study
From Sync Bridge to Data Warehouse
Syncs reduced from 45 to 60 minutes to 13 to 20 minutes. Error rate under 1 percent.
Case study
Building an Enterprise Analytics Platform
MongoDB to PostgreSQL, React dashboard, ETL, 18,000+ dealers, and 50,000+ claims.
Review links
Google sources
Google Cloud
Agent Registry overview
Catalog for agents, tools, MCP servers, and endpoints.
Google Cloud
Register MCP servers
External MCP servers require registration and a manual toolspec.
Google Cloud
Host MCP servers on Cloud Run
Cloud Run supports remote MCP servers over Streamable HTTP.
Google ADK
ADK Agent Registry integration
ADK can fetch MCP toolsets from Agent Registry.