Productivity Conf for Devs and Tech Leaders

Managing Context in AI Coding Assistants: Achieve Better Results with Fewer Hallucinations

This talk demonstrates how developers can get the most out of AI coding assistants by effectively managing the context they provide. Through practical examples with three popular assistants—Aider, Cursor, and Windsurf—I’ll show how to configure global and local context, manage it in real-time, and overcome common limitations. Attendees will also learn how to extend the assistants’ capabilities with a centralized knowledge service to maximize their productivity and accelerate software delivery.

This talk has been presented at Productivity Conf for Devs and Tech Leaders, check out the latest edition of this Tech Conference.

FAQ

The founder is Tim Kitchens.

MCP is a protocol designed to integrate external world contexts into AI coding tools, allowing seamless interaction with knowledge management tools like Confluence and project management tools like Jira.

Conduit is an MCP tool developed by Tim Kitchens for personal use, allowing AI coding assistants to interface with knowledge management and project management tools such as Confluence and Jira.

MCP enables AI tools to integrate external contexts, such as project management data and knowledge from Confluence and Jira, transforming AI-driven software development by maintaining flow and efficiency.

Current AI coding tools often require manual context integration, such as copying and pasting information from chatbots or relying on limited built-in tools, which may not seamlessly integrate all necessary knowledge sources, especially those requiring authentication.

The demo showcases how MCP with Conduit is used to address a bug report, add features, and manage tasks within Jira and Confluence, highlighting the seamless integration of external contexts into AI coding workflows.

Tim Kitchens uses tools such as Cursor, WinSurf, and AIDER, along with MCP tools like Conduit, to integrate and manage external contexts in AI coding workflows.

MCP Inspector is used to debug MCP servers in a local development environment, helping developers reproduce and address issues effectively.

MCP allows for the creation, movement, and closure of Jira issues, as well as the retrieval of Confluence page contents, facilitating seamless collaboration and task management.

The future challenge is not AI capabilities but rather the integration of the right tools into workflows to effectively harness AI potential.

productivity

Tim Kitchens

20 min

27 Mar, 2025

Comments

Video Summary and Transcription

Today's Talk discussed integrating context into AI coding tools using the MoloContext protocol (MCP). The demos showcased the use of Conduit, an MCP tool, for bug tracking and feature addition in software development. The Talk also highlighted the use of Fetch in Cursor to summarize GitHub issues and create Jira bug reports. It demonstrated how Conduit can be used to manage issues, make code changes, and perform Git commits. Additionally, it explored the integration of Conduit with Windsurf to add a user interface for the conduit application. The Talk also touched upon implementing MCP in the AIDER AI coding system and using MCP and Windsurf for Conduit integration. Overall, it emphasized the importance of context and choosing the right tools for efficient software development workflows.

Video transcription and chapters available for users with access.

Check out more articles and videos

We constantly think of articles and videos that might spark Git people interest / skill us up or help building a stellar career

AI and Web Development: Hype or Reality

JSNation 2023

24 min

AI and Web Development: Hype or Reality

Top Content

Kyle Simpson

Software Engineer, Public Speaker, and Teacher

The Talk discusses imposter syndrome and reframes it as being a professional imposter. It emphasizes the importance of sharing and starting, embracing imposterism, and building inclusively for the web. The speaker shares personal experiences of being an imposter in various technical disciplines and highlights the significance of accessibility. The Talk concludes with the idea of building a collective RPG game to remove excuses for not making things accessible.

builders and founders productivity mental health

Improving Developer Happiness with AI

React Summit 2023

29 min

Improving Developer Happiness with AI

Watch video: Improving Developer Happiness with AI

Senna Parsa

Solutions Engineer at GitHub

GitHub Copilot is an auto-completion tool that provides suggestions based on context. Research has shown that developers using Copilot feel less frustrated, spend less time searching externally, and experience less mental effort on repetitive tasks. Copilot can generate code for various tasks, including adding modals, testing, and refactoring. It is a useful tool for improving productivity and saving time, especially for junior developers and those working in unfamiliar domains. Security concerns have been addressed with optional data sharing and different versions for individuals and businesses.

developer experience artificial intelligence tooling productivity best practices

VS Code Can Do That!

JSNation Live 2021

28 min

VS Code Can Do That!

John Papa

Microsoft

The Talk covers various tips and features of using VS Code, including the command palette, Zen mode, external terminals, and debugging. It also highlights advanced editing and refactoring features, Git integration, and the use of dev containers. The speaker demonstrates how to set up a dev container for a Python app, run code in a container, and create and configure dev containers. The benefits of using dev containers are also discussed, such as eliminating manual configuration, handling dependencies, and facilitating team-based development.

devtools productivity

Maximize Productivity with AI Agents

Productivity Conf for Devs and Tech Leaders

25 min

Maximize Productivity with AI Agents

Tejas Kumar

Author of the "Fluent React" bestselling book, software engineer with 23 years of experience, and host of the developer-loved ConTejas Code podcast.

I'm Tejas Kumar, a software developer with over 20 years of experience. AI agents are defined as entities that act on behalf of users or groups to produce specific effects. Agents consist of an orchestration layer, a language model, and tools represented as JSON functions. Langflow is an open-source tool that allows users to build their own AI agents by connecting language models and tools. Composio is a tool that enhances agent capabilities by offering integrations and apps, such as Google Calendar integration. MCP (Model Context Protocol) is a way to share context with models and extend their capabilities. It allows functions to be made available to models over standard input/output or an HTTP endpoint. MCP can be used with GitHub to perform various tasks like searching and fixing code issues. The Talk covered the basics of AI agents, building agents with Langflow and enhancing them with Composio, and using MCP with GitHub. The speaker encouraged audience questions and exploration of these concepts.

productivity automation