Send us a text

This week, Kevin McDonnell and Garry Trinder explore the world of coding agents and how they could change software development. They run through what coding agents are along with the importance of context, memory, and specifications in using AI tools effectively. Also, they think about how you need to change habits and also touch on the challenges faced by junior developers in adapting to AI technologies, the role of personality in AI agents, and the future of work with AI. This isn't just the joy of agents though, this is about the need for security and ethical considerations when integrating AI into development processes, while also encouraging developers to embrace the potential of AI to enhance productivity and creativity.

Takeaways:

• Coding agents represent the next leap in development tools.
• Understanding the context and instructions is crucial for effective use of coding agents.
• Memory in coding agents can enhance their effectiveness and personalization.
• Specifications and guidelines are still important in the age of AI.
• Junior developers should balance learning coding principles with using AI tools.
• AI can automate repetitive tasks, freeing up time for developers.
• The personality of AI agents can enhance user experience and engagement.
• Skills in AI can create repeatable processes for developers.
• The impact of AI on junior developers raises concerns about learning and understanding code.
• Security and ethical considerations are vital when using AI agents.

Links:

Github Copilot CLI - https://github.com/features/copilot/cli/

Claude Code - https://claude.com/product/claude-code

Patrick Rogers power of Coding Agents - https://www.linkedin.com/posts/patrick-rodgers-b6a05610_i-love-to-write-code-ive-been-a-programmer-activity-7422672723191058432--Ob_

Shipping at Inference Speed - https://steipete.me/posts/2025/shipping-at-inference-speed

Claude Skills - https://support.claude.com/en/articles/12512176-what-are-skills

Anthropic Skills Repo - https://github.com/anthropics/skills/tree/main/skills/slack-gif-creator

Open Code - https://opencode.ai/

Moltbot Soul - https://github.com/openclaw/openclaw/blob/main/docs/reference/templates/SOUL.md

Moltbot - https://moltbot.you/

Moltbook - the first agent social network? - https://www.moltbook.com/

https://www.moltbook.com/post/ef3ea419-6c29-4046-9946-d636efe972ea

Be careful with Moltbot/Clawdbot:

https://www.linkedin.com/posts/elishlomo_security-activity-7421867291459391490-a0B1/

https://x.com/theonejvo/status/2015401219746128322

https://x.com/borjitaea/status/2015745063909839091?s=46

Send us a text

Happy new year to you all! In this episode, Zoe and Kevin take a short look at what happened with Copilot and with themselves in 2025, a short view on what they think and hope will happen with Copilot and AI in 2026 but focus most of the time on digging into the latest Microsoft Future of Work report that their science team has been making for the last 5 years. They explore themes such as AI judgment, collaborative AI, and the implications of inequality in the workplace amongst other things.

Takeaways

• Agent 365 has the potential to greatly impact organizational efficiency and control.
• Simplification in Copilot Studio and Chat enhances user experience and accessibility.
• Agents play a crucial role in simplifying complex AI functionalities.
• Fireside chats and workshops have been key highlights in community engagement.
• Recognition through awards fosters motivation and visibility in the tech community.
• The Future of Work report provides valuable insights into AI's impact on labor markets.
• AI judgment and perception can affect workplace dynamics and relationships.
• Collaborative AI is essential for enhancing teamwork and productivity.

Key links

Future of work report

Tailwind news

Salesforce refocussing roles

Jamie Teevan's keynote at ESPC

Send us a text

In this episode of Copilot Connection, Kevin McDonnell and Garry Trinder discuss the latest developments from the Ignite Conference. They delve into the renaming of Azure AI Foundry to Microsoft Foundry, the new features of the Foundry portal, and the integration of Claude models. The conversation also covers the importance of experimentation with language models, updates on the Teams SDK, and the nuances of the Agent 365 SDK. In this conversation, Garry and Kevin delve into the latest advancements in Microsoft 365, focusing on Agent 365, MCP servers, and the integration of low-code solutions. They discuss the potential of natural language processing in enhancing user interactions, the significance of declarative agents, and the importance of responsible AI practices, particularly in the context of red teaming. They may also chuckle at renames more than they should...

Takeaways

• Renaming products often indicates a broader vision beyond their original scope.
• The new Microsoft Foundry portal simplifies the process of managing AI agents.
• Publishing agents to Teams and Copilot has become more streamlined and user-friendly.
• Claude models are now integrated into the Microsoft ecosystem, enhancing AI capabilities.
• Experimentation with different language models is crucial for optimizing performance.
• Understanding the purpose of each tool in the Microsoft ecosystem is key to effective use.
• The Teams SDK has been rebranded, reflecting its expanded functionality.
• The Agent 365 SDK builds on existing frameworks to enhance agent capabilities.
• MCP servers need to be exposed for use.
• Low code options are available for MCP management.
• Declarative agents are evolving with TypeSpec innovations.
• Red teaming is essential for testing AI agents.
• Responsible AI practices are crucial in agent development.
• User feedback is vital for improving Microsoft technologies.
• MCP is becoming a standard for data interaction.

Links
Ignite Book of News

Azure AI Foundry is now Microsoft Foundry

Deploy and use Claude models in Microsoft Foundry - Microsoft Foundry | Microsoft Learn

Teams AI Library is now Microsoft Teams SDK

Microsoft Graph is Work IQ....

Agent 365 SDK

MCP Management Server

Kevin's example of MCP in Copilot Studio

Type spec GA

Connected agents

Red Teaming agent

Copilot APIs