The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
I build custom Model Context Protocol (MCP) servers that connect your data sources, APIs, databases, and AI tools into a secure, scalable environment. Your MCP server enables AI agents to retrieve information, execute actions, and communicate with your systems through structured tools and resources.
I use advanced technologies including TypeScript, Node.js, Python, MCP SDK, FastAPI, Express.js, Pydantic, PostgreSQL, Supabase, MongoDB, Redis, LangChain, LlamaIndex, OpenAI API, Anthropic Claude API, Google Gemini API, Docker, Docker Compose, Postman, GitHub Actions, AWS, Azure, Google Cloud, and DigitalOcean.
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Related posts
I am a technology-focused professional interested in artificial intelligence, data management, and digital solutions. I aim to help businesses improve efficiency, organize information, and achieve their goals through reliable, innovative, and detail-oriented work.
🚀 Expanding My Expertise in AI Engineering with Claude and the Anthropic API
I'm excited to share that I've successfully completed the Claude with the Anthropic API certification!
This learning experience helped me explore modern AI development concepts, including Claude API integration, prompt engineering, AI agents, agentic workflows, Claude Code, Retrieval-Augmented Generation (RAG), and AI evaluation techniques.
As a Salesforce Developer and Administrator, CRM Consultant, and Software Developer, I'm particularly interested in using AI to build smarter applications, automate repetitive business processes, and help companies manage their data more efficiently.
My goal is to combine AI capabilities with custom CRM systems, websites, mobile applications, and business software to create practical solutions that solve real-world problems.
I'm looking forward to applying these concepts to future projects and continuing to grow in AI engineering and intelligent automation.
🔗 Verify my certificate: https://verify.skilljar.com/c/mjq7dg9v9oy8
#ArtificialIntelligence #ClaudeAI #AIEngineering #AgenticAI #Automation #SoftwareDevelopment
The evals part pairs well with Salesforce work. In CRM automation the hard part is proving the agent updated the right record, so building eval habits early will save a lot of rework.
Building software with AI requires more than a good prompt.
I've been developing my own Autonomous Engineering Harness to structure how I build software with AI.
The idea is simple: instead of relying on AI to generate code one task at a time, I wanted a more structured process that connects specifications, task planning, implementation, code review, and QA.
The harness organizes the workflow into clear stages:
- Specifications: define what needs to be built.
- Task planning: break requirements into manageable units.
- Implementation: coordinate AI-assisted development.
- Review: check the result against the intended requirements.
-QA: validate the software before considering the work complete.
The goal isn't to make AI autonomous for the sake of it. It's to make AI-assisted engineering more structured, repeatable, and easier to validate.
I'm applying this approach to my own projects and continuing to refine the framework as I learn what works in practice.
I wrote more about the approach, the engineering decisions behind it, and how the framework works on my website.
Read the full story: https://yitsymosqueda.com/autonomous-engineering
I'd carry acceptance criteria from the spec into QA as explicit checks, with a result attached to each one. When the spec changes mid-build, does the workflow flag which completed tasks and QA results need to be revisited?