Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
LangGraph Tool Call Middleware
This talk details a production middleware pattern using LangGraph to intercept and correct hallucinated workflow IDs in LLM tool calls before execution.
Live walkthrough of a production middleware pattern that intercepts LLM tool calls before execution to inject correct workflow IDs, preventing hallucinated values.
The demo covers:
The problem: LLMs hallucinate workflow IDs when calling n8n tools via MCP
The solution: WorkflowInjectorToolNode wrapping LangGraph’s ToolNode to intercept and modify tool calls
Implementation details: how to modify AIMessage.tool_calls before execution, handle edge cases, and maintain compatibility with LangGraph’s tool matching
Trade-offs: when to use middleware vs. prompt engineering vs. tool design
Includes real code from a production agent system, showing the interception logic, error handling, and integration with LangGraph’s checkpointing system.
Soforce system status indicates initialization; technical specifications are currently loading.
- LangGraphA low-level orchestration framework for building long-running, stateful, and cyclic multi-agent systems using a graph-based architecture.LangGraph is the specialized, low-level runtime for developing complex AI agents, extending the LangChain ecosystem to handle intricate, stateful workflows. It models the agent's logic as a directed graph: nodes represent actions (LLM calls, tool use), and conditional edges dictate the flow, enabling critical features like cycles (loops) for iterative reasoning. This graph-based approach ensures durable execution, allowing agents to persist through failures and resume operations. Key capabilities include comprehensive memory management via a shared state object and built-in human-in-the-loop functionality (interrupts) for external oversight. This robust framework is trusted by production teams at companies like Klarna and Replit for deploying scalable, resilient agent architectures.
- LangChainThe open-source framework for building and deploying reliable, data-aware Large Language Model (LLM) applications.LangChain is the essential framework for engineering LLM-powered applications: it simplifies connecting models (like GPT-4 or Claude) to external data, computation, and APIs. The platform provides a modular set of components—Chains, Agents, Tools, and Memory—allowing developers to quickly build complex workflows like Retrieval-Augmented Generation (RAG) pipelines and sophisticated conversational agents. Its Python and JavaScript libraries, combined with LangChain Expression Language (LCEL), offer a standardized interface for rapid prototyping and moving applications to production with confidence.
- 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 .
- n8nn8n (pronounced 'n-eight-n') is the fair-code workflow automation platform: it gives technical teams the power of custom code (JavaScript/Python) via a visual, node-based editor.This is n8n: a powerful, self-hosted workflow automation platform designed for developers and technical teams. It uniquely blends the speed of a no-code UI with the flexibility of custom code, allowing users to build complex, multi-step automations that other tools cannot handle. With 400+ integrations and native AI capabilities, n8n ensures you maintain full control over your data and deployment (on-prem or cloud). For example, you can build a workflow to automatically pull data from a private API, transform it with a custom Python script, and push the results to both Salesforce and a Slack channel, all from a single visual canvas.
- PostgreSQLPostgreSQL (Postgres): The world's most advanced, open-source object-relational database (ORDBMS), built for reliability and extensibility.PostgreSQL is the premier open-source ORDBMS, proven over 35+ years of active development. It adheres strictly to ACID properties (Atomicity, Consistency, Isolation, Durability), ensuring data integrity for mission-critical workloads. Key features include robust SQL compliance, Multi-Version Concurrency Control (MVCC), and superior extensibility (e.g., custom data types, functions in multiple languages). Advanced capabilities like native JSON/JSONB support and the PostGIS extension (geospatial data) make it a powerful, flexible choice for complex enterprise applications.
Related projects
Langdock
Berlin
This talk covers achieving GDPR compliance and the process of setting up and optimizing Retrieval-Augmented Generation (RAG) for…
Breaking the Chains - an organization-theoretical approach to creating LLM applications
Berlin
Explore an organization-theory-inspired approach to building intuitive LLM applications. This project simplifies prototyping mid-to-large scale LLM pipelines with…
Coding with AI: What Works & What Doesn't
Manchester Nh
Learn practical AI coding assistant dos and don'ts, avoiding slowdowns. See a live demo of a self-learning agent…
AgentMon: Building Step-Level Tracing + Expert Review for PydanticAI Agents
Cologne
This talk details building AgentMon: a framework for structured tracing of PydanticAI agent steps, persistence, augmentation, and a…
Backpressure helping Claude code to learn from mistakes
Cologne
See how a Rust CLI tool called keel enables AI coding agents to learn from mistakes by enforcing…
Should You Obey Your AI Reviewer?
Brussels
Learn how to hide LLM non-determinism and quantitatively optimize accuracy for AI code review systems, a crucial learning…