Todd Radel

Build a multi-agent system using WRITER + Strands Agents 🚀 We recently released our WRITER Strands Agents SDK integration. It was great diving head-first into developing some of our associated developer docs, examples GitHub repository, and creating my first WRITER engineering blog post. 🥳 To show you just how powerful this combo is, here’s a quick walkthrough of a multi-agent system that: ✅ Uses WRITER’s Palmyra X5 foundation model as the central orchestrator managing a multi-agent system via Strands Agents SDK   ✅ Leverages Palmyra X5 to classify and route queries to domain-specific agents that use Palmyra Creative, Palmyra Fin, or Palmyra Med   ✅ Connects each specialized agent to prebuilt tools via Strands Agents utilities, including calculator, web_search, and file tools to support their prompted tasks Dive in, test it out, and let us know what you think!   Further reading/resources: 📚 Blog article: https://lnkd.in/gJExZdV6 📖 Getting started guide: https://lnkd.in/gbXxF4gQ 💻 Examples repo: https://lnkd.in/g8shNNKn

57

5 Comments

This is the new insider risk nobody wants to admit: Your co-workers aren’t pasting secrets, PII, or code into ChatGPT or Copilot because they’re reckless or evil. They’re doing it because they’re slammed, under pressure, and trying to get work done 10 minutes faster. One paste. Outside the org. Immediately. No alert. No audit trail. No “oops, take that back.” This isn’t sabotage. It’s normal work behavior + new tools that don’t follow the old rules. Every company is dealing with this right now, whether they know it or not. I’m dropping a link in the comments to a short (demo filled) webinar where I walk through exactly how to shore up "workers just be workers" attack.

99

5 Comments

I saw a post this week that didn’t sit right with me. An executive was publicly calling out an engineer for a bug. The post gained a lot of momentum. The comments were filled with people trying to diagnose the issue. Maybe that was the plan, to get the hits. But it sure doesn’t help the culture layer of the system. The story was framed as a lesson about “thinking like a founder,” who had to work over a weekend to resolve the bug. What stood out wasn’t the bug or the engineer. It was how quickly the analysis stopped. When we stop at the third why, it sounds like this: The engineer didn’t think hard enough. But if we keep digging, the picture changes: Why #4: The compliance step was “mostly theater,” so it didn’t feel worth questioning. Why #5: The system had no safety net. There was no design check, no fail-safe, no resilience for unexpected inputs. At that point, the weekend wasn’t ruined by one engineer. It was ruined by the way the system was designed. Failures rarely belong to one person. They live upstream, left of testing, left of the bug, in the way we design, review, and reward work. Leaders don’t level up their teams by calling them out. They level them up by calling them up, by building systems where humans can succeed and resilience is built in. Because the real goal isn’t to act like a founder. The real goal is to design systems where everyone can go home for the weekend.

412

70 Comments

Lately I’ve been thinking about what great technical management looks like. The best analogy I’ve found isn’t from tech. It’s from a Michelin kitchen. A chef de cuisine doesn’t just "manage". They set the menu, **taste every plate**, lead service, train the brigade, run inventory, negotiate with suppliers, and jump on the line when the heat’s on. They’re administrative and **deeply culinary**. People follow them BECAUSE they can cook, not because they are great with people. tl;dr: This is the blueprint for EMs! Make sure every manager in your company thinks like a chef! The customer must have a great, standardized, rewarding experience EVERY SINGLE TIME! # What great chefs do → what great tech managers do ## Menu & vision - Chefs design the menu end-to-end. - Managers work with the team on a clear technical vision and roadmap: architecture, quality bar, tradeoffs. ## Taste everything - Chefs calibrate the palate of the team. - Managers calibrate "engineering taste": design reviews, code reviews, help reach or make tech decisions. ## Mise en place - Chefs enforce standards so service flows. - Managers enforce engineering standards such as testing, CI, on-call hygiene, observability. This is key to make delivery flow. ## Train the brigade - Chefs teach technique and judgment. - Managers mentor with activities like pairing, helping with postmortems or creating growth plans. ## Run the pass - Chefs expedite during service under pressure. - Managers lead incidents, make crisp calls, keep outcomes and morale high. ## Suppliers & costs - Chefs handle vendors, budgets, margins. - Managers handle vendors, capacity, budgets, and the “efficiency of taste”, while making decisions such as build vs. buy or scope vs. value. ## Jump on the line - Chefs still cook. They are responsible for R&D, new dishes and covering gaps. - Managers stay hands-on enough to be credible by creating prototypes, doing spikes, pairing on hairy PRs, reading code or shipping small fixes when it truly helps. # Disclaimer I'm not saying the Engineering Manager as a Chef is the only possible way or even the best way for your scenario. Just sharing that in my experience it has provided the best results. # Conclusion If you want to follow this path, here’s the uncomfortable bit: in both worlds, staying technical isn’t optional. BEING TECHNICAL IS NOT OPTIONAL for a chef! So it is also not be optional for an engineering manager with this mindset. The team needs to see that your judgment comes from lived technical depth and not just from management discipline. Let me be 100% clear: you don’t have to out-code your senior ICs. But you do need current, working knowledge of your stack, constraints, and craft so your decisions land and your standards stick. If you want a team that aspires to excellence, be the kind of manager whose “food” they want to taste! Lead with vision. Set the bar. Teach the craft. And keep your hands close enough to the stove to feel the heat.

46

4 Comments

One of the most underrated but impactful applications for AI is structuring unstructured content. Structure - or metadata - enables querying, filtering, and automating content workflows, unlocking content management at scale. This is one of our key focus areas with Box AI, and one that I find many of our customers are particularly excited about. In my latest piece for The AI Journal, I explore how AI is unlocking a new frontier of metadata-driven workflows at scale, allowing us to intelligently work with our content in brand new ways.  Link to my article in the comments.

202

11 Comments