๐ ๐๐ฃ ๐ง๐ผ๐ผ๐น ๐๐ต๐ฎ๐ผ๐ - ๐ด๐ผ๐ ๐น๐ผ๐๐ ๐ถ๐ป ๐ฎ๐๐๐ต๐ฒ๐ป๐๐ถ๐ฐ๐ฎ๐๐ถ๐ผ๐ป ๐ฎ๐ป๐ฑ ๐ด๐ผ๐๐ฒ๐ฟ๐ป๐ฎ๐ป๐ฐ๐ฒ?!
๐ ๐๐ฃ ๐ง๐ผ๐ผ๐น ๐๐ต๐ฎ๐ผ๐ - ๐ด๐ผ๐ ๐น๐ผ๐๐ ๐ถ๐ป ๐ฎ๐๐๐ต๐ฒ๐ป๐๐ถ๐ฐ๐ฎ๐๐ถ๐ผ๐ป ๐ฎ๐ป๐ฑ ๐ด๐ผ๐๐ฒ๐ฟ๐ป๐ฎ๐ป๐ฐ๐ฒ?!
Agentic coding has become reality for developers everywhere ๐. Tools like Anthropic’s Claude Code and Amazon’s Kiro are leading the charge, boosting coding efficiency and developer experienceโas long as you stay firmly in the driver’s seat. But with great power comes challenges, especially as agentic workflows drive more tool integrations via the Model Context Protocol (MCP). Developers and teams now juggle multiple MCP servers, each with its own endpoints, authentication flows, and security requirements. This raises key issues: How do we guarantee security and compliance at scale, whether for solo devs or enterprise teams? And from a pure DX perspective, who wants to wrangle endless auth methods? ๐ฉ
๐ฏ From Chaos to Control: Building Predictable AI Agents That Get Smarter Over Time
๐ฏ From Chaos to Control: Building Predictable AI Agents That Get Smarter Over Time
โ๏ธ We need to balance Agency versus Control. We want AI systems to be super easy to use, read our minds, and just provide the answer we need. But we also need to make sure that nothing goes wrong. The more we control, the less agency we get. This is a balancing act.
Let’s focus on the control part. There are many different mechanisms to increase and guarantee control. Things like policies and guardrails come to mind. Those are obvious and powerful. I will cover them in a dedicated post.
๐ ๐ฅ๐๐ฆ๐ง ๐ถ๐ป ๐ฃ๐ฒ๐ฎ๐ฐ๐ฒ - ๐ช๐ต๐ ๐๐๐ ๐ ๐๐ฎ๐ป'๐ ๐๐ฅ๐จ๐: ๐ ๐ฅ๐ฒ๐ณ๐น๐ฒ๐ฐ๐๐ถ๐ผ๐ป
๐ ๐ฅ๐๐ฆ๐ง ๐ถ๐ป ๐ฃ๐ฒ๐ฎ๐ฐ๐ฒ - ๐ช๐ต๐ ๐๐๐ ๐ ๐๐ฎ๐ป’๐ ๐๐ฅ๐จ๐: ๐ ๐ฅ๐ฒ๐ณ๐น๐ฒ๐ฐ๐๐ถ๐ผ๐ป
Yesterday I was listening to a talk by Martin Sakowski and Martin Karrer “REST in Peace - Why LLMs Can’t CRUD” which sparked a lot of interesting discussion. ๐ญ
๐ค They observed that even with the rise of MCP, AI Agents often struggle to master their given tasks reliably, consistently, and in an efficient wayโdriving costs and potentially failing projects.
Diving into designing multi-agent systems and got lost with all the different implementation options
Diving into designing multi-agent systems and got lost with all the different implementation options? MCP (x)or A2A?! - Heikoโs and Dr. Sokratis Kartakis (any way to mention you in here just by your first name, mate?) nice article got your back. Highly recommended read! Congrats to both for being published there!
Kind of an interesting twist in IT history: Did it need the advent of AI Agents
Kind of an interesting twist in IT history: Did it need the advent of AI Agents to drive developer friendly, standardized and discoverable interfaces to systems?
Recently Model Context Protocol (MCP) got a lot of attention and traction. While this is good and exciting thing, I was wondering why this is actual needed? In a perfect & developer friendly world, it shouldnโt need another protocol just for agents, does it? AI should easily be able to use the existing interfaces, which have been built for convenience of human developers, no?