Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
AI Workers That Create and Operate Their Own MCP Apps
AI workers autonomously build, deploy, and operate MCP apps, showcasing a config-driven system for dynamic software creation and improvement at scale.
A platform where AI workers (tedis) autonomously build, deploy, and operate MCP apps, both internal tools and customer-facing products as ChatGPT apps. Not “AI-assisted development.” The Tedi IS the developer, the ops engineer, and the product manager.
I’ll walk through the technical build:
-
The MCP app lifecycle: A tedi takes an API endpoint, maps it to MCP tools (config-driven D1 rows, zero handler files), generates widget layouts via genUI, validates output with screenshot-based QA (Cloudflare Browser Rendering → R2), and deploys — all autonomously.
-
131 tools, one universal handler: Every MCP tool is a database row. Adding a tool = inserting a row. No code, no deploy.
-
Persistent memory for improvement: Tedis carry a semantic knowledge graph (Brain MCP: Upstash Vector + D1) so each app they build is better than the last. Patterns, gotchas, and architecture decisions compound across sessions.
- MCPMCP is the open-source standard for securely connecting AI agents (like LLMs) to external tools, data, and enterprise workflows.The Model Context Protocol (MCP) functions as a standardized integration layer: think of it as a USB-C port for AI applications. Developed and open-sourced by Anthropic, this protocol allows large language models (LLMs) to access real-time context and execute actions via external tools like GitHub, Jira, or proprietary databases . It uses a simple JSON-RPC interface to define tools, schemas, and endpoints, which enables AI agents to perform complex, state-changing tasks—such as creating a GitHub issue or running a test script—rather than just generating text . MCP is essential for building agentic AI systems that can autonomously pursue goals and operate within defined safety and permission boundaries .
- Cloudflare WorkersDeploy serverless code instantly on Cloudflare's global network, executing with zero cold starts via V8 isolates for ultra-low latency.Cloudflare Workers is your serverless compute platform: run JavaScript, TypeScript, or WebAssembly directly on Cloudflare's global edge network. Leveraging the V8 engine and its isolate architecture ensures near-instant startup (zero cold starts), delivering ultra-low latency to users in over 330 cities. Use Workers to deploy fast edge logic—from custom API gateways and request routing to modifying responses and running AI inference—without managing a single server.
- Cloudflare D1Cloudflare D1 is a serverless relational database built on SQLite that replicates data globally to minimize latency for distributed applications.D1 brings SQL to the edge by leveraging SQLite (the world's most deployed database engine) and integrating it directly into the Workers ecosystem. It eliminates the need for complex connection pooling or manual regional provisioning: you define your schema, and Cloudflare handles the storage and replication. With features like Time Travel for point-in-time recovery and a generous free tier (5 million rows read per day), it is the go-to choice for developers building high-performance, data-driven apps without the overhead of traditional RDS management.
- Cloudflare R2Cloudflare R2: S3-compatible object storage engineered for zero egress fees, eliminating the 'data tax' for developers.R2 is a globally distributed object storage solution built to challenge traditional cloud providers by offering zero egress fees. This core feature ensures you can move data freely, avoiding vendor lock-in and unexpected bandwidth costs. It maintains full Amazon S3 API compatibility, guaranteeing seamless migration and integration with existing tools and workflows. R2 leverages Cloudflare’s global network (330+ data centers) for low-latency access and integrates natively with Cloudflare Workers, allowing you to build high-performance, serverless applications right at the edge.
- Upstash VectorA serverless vector database designed for high-speed similarity search with zero infrastructure management.Upstash Vector provides a serverless index for storing and querying high-dimensional embeddings with sub-10ms latency. It automates the embedding process through native integrations with providers like OpenAI, Hugging Face, and Cohere (eliminating manual vectorization steps). The platform supports metadata filtering and namespaces to ensure precise data retrieval for RAG applications. You pay only for active requests and storage: the free tier includes 10,000 requests per day, making it an efficient choice for developers moving from prototype to production.
Compose Email
Loading recent emails...