Dennis Faust

Adding Document Understanding to Claude Code 📑🤖 Coding agents are awesome but they don’t natively understand docs (they kind of do, but it sucks). This limits their ability to build business applications - think about anything from a financial copilot to contract reviewer to rfp synthesizer to synthesizing PRDs. I wrote a blog to capture core patterns for adding document understanding to Claude Code - applicable to coding agents in general. This both helps Claude Code 1) get enterprise context when building apps, and 2) allows it to build more agentic, robust apps in general. 1️⃣ Add an MCP server that preindexes your file knowledge base 2️⃣ Let Claude Code loose on your filesystem with the right CLI tools for understanding files. 3️⃣ Give Claude Code context on core modules for document understanding and agentic workflows - this last step is important if you want to build “better apps in general” and not just “rule-based apps”. Blog: https://lnkd.in/g4EEFftk The blog offers general principles regardless of whether you’re using our stuff, because we fundamentally think that coding agents + docs leads to a ton of useful applications. Of course we are deeply investing in tooling in this space too (some referenced in the blog), a lot of it dependent on LlamaCloud. Check it out: https://lnkd.in/g9Wpqn7w

210

3 Comments

Today marks Six months in as SOCPAC CTO, and it somehow feels like both yesterday and six years ago. When I stepped into this role, we were behind the curve. Legacy systems, siloed data, and slow processes held us back. In just half a year, we’ve laid a Foundational Technical Architecture that gave us a modern backbone for data, AI, and autonomy. Since then, we’ve: 1. Unified our digital foundation for secure, scalable operations 2. Embedded AI and LLMs into daily workflows to speed decisions 3. Deployed containerized AI agents across all networks 4. Integrated autonomy at the edge, moving toward true man–machine teaming 5. Shifted our culture from cautious adoption to championing innovation The result? We’re no longer catching up, we’re setting the pace. What once felt like a distant goal is now part of our daily reality. All of this happened in six months, which is why it feels so surreal. It took countless late nights, cross-functional sprints, and the relentless dedication of an amazing team. I'm humbled by the trust the organization placed in me to drive this transformation, and I'm grateful to every person who rolled up their sleeves to make it real. This was truly a team effort, from the junior analysts using our new AI tools to the senior leaders who empowered us to take bold risks. And we’re just getting started. The foundation is in place, but now we get to build on it. In the next chapter, we'll be refining and scaling these capabilities, drilling deeper into AI-enhanced decision-making, and pushing the envelope on autonomous operations. The technology will keep evolving, and so will we. Our goal remains the same: give our operators a decisive edge, making it an extension of the warfighter and keep innovating responsibly. I’m humbled by what the team accomplished in such a short time, and excited for what’s next. The foundation is in place. Now we build on it. Six months down, and the journey is just beginning.

170

19 Comments

Excited to share insights from myself and Jason Barrett on building resilient systems at American Express! We've seen incredible results by shifting our focus from individual applications to customer journeys. This approach not only improves reliability but also fosters a powerful culture of cross-functional collaboration. Read more about our approach and the impact it's had on the Amex Tech Blog: https://lnkd.in/dzAzwmzv #TeamAmex #AmexTech

170

12 Comments

This is an important post from Will Larson about engineering leadership: Traditional managers stall when they shift from orchestration to leadership. You’re no longer just executing plans: you’re deciding what to work on, why, and how to communicate that path. https://lnkd.in/eFpe99fw

136

5 Comments

AI at Spotnana isn’t a side project or flashy add-on. It’s at the heart of how we build. Over the past year, we’ve made a key shift across our PODs: instead of asking “How would I solve this?”, we now ask “How would AI solve this faster, safer, and with the customer at the center?” That change has transformed how we work. We’re seeing 5x the impact with less effort, because AI isn’t just sprinkled in, it’s baked into our roadmaps, reviews, and metrics. Our stack reflects this mindset: Claude Code (Anthropic) drives backend and agentic workflows, while Cursor powers frontend changes and smart refactors. And with AI Monday demos, teams share wins, live demos, and playbooks turning individual breakthroughs into company-wide momentum. The results are huge. Integrations that once took months now go live in days. Engineers spend less time on grunt work and more time solving hard problems. Things we thought were impossible in the legacy travel stack are now shipping in weeks. What we’re learning: - AI is a multiplier when paired with strong engineering judgment. - It has to live in your product roadmap, not a lab on the side. - The real wins come from habits and workflows, not shiny models (they help big time though). - Travel tech is being rewritten, and AI-first engineering is the catalyst. A big thank you to all Spotters worldwide who’ve embraced this change. The progress we’ve made together is incredible. If you're an engineer or product leader fired up about rewiring critical infra with AI, hit me up. The travel stack's getting a full rewrite, and we're leading the charge. #AIInnovation #TravelTech #Spotnana

128

2 Comments

So which models produce HTML that has the least accessibility errors, and at what cost? Mapped it out here (bottom left is the best). This is helpful for understanding which models are most compliant for those with disabilities and do it efficiently. Qwen and Gemini 2.5 Flash lead the pack. Hat tip to Ben Ogilvie for pointing me to this: aimac.ai

50

2 Comments

Today I am excited to announce Digger’s BIGGEST update ever Project OpenTaco - The Open Standard for Terraform automation. With OpenTofu, where Digger is a founding member, the community already has a credible open-source CLI alternative to BSL-licensed Terraform. But as we all kno that only solves half the problem. The CLI helps teams avoid lock-in, but it doesn’t address governance or collaboration challenges at scale. Project OpenTaco builds on this foundation, without taking an opinion on which IaC language is used, giving teams a path to adopt more Infrastructure-as-Code with a TACOs that is open, self-hostable, and free from licensing traps or per-resource pricing. We believe that it this is “Terraform’s backstage moment”. Backstage became the open standard for Internal Developer Portals, we believe Project OpenTaco will do the same for IaC automation, setting the standard, driving adoption, and making closed platforms unnecessary. The future of IaC is open, and we’re building it brick by brick. Check out our roadmap and sign up for updates, we’d love any and all feedback! Link in the first comment ->

98

11 Comments

Maxim Fateev's blog is a must read ... It's direct talk from his experience. "After spending over two decades building orchestration solutions. I’ve seen the patterns, I’ve tried the different approaches, and I’ve watched the industry rediscover the same lessons over and over" So many parallels to why Infrastructure as Code won over the gazillions of visual infra layout tools ... https://lnkd.in/gB_G3ijA Temporal Technologies

49

2 Comments

As always, excited to share with you what's new at Causely! This week’s release delivers sharper answers now and smarter postmortems later. Here's some of what we recently shipped: 🗃️ Root Cause Prioritization Real-time ops are our core, but reliability engineering is also about iterative improvement and a growth mindset. You can now sort by symptom count (largest blast radius) or duration (longest active) in the UI or API to determine which reliability work items should be prioritized in your next sprint. 🪄 "Ask Causely" Enhancements You’ve been able to interact with Causely in natural language — in our UI or directly in Slack or Microsoft Teams — for several weeks, and we’re making it smarter every week. The latest upgrades let you access more metrics across more entities (including disks), view summarized trends over time for faster analysis, and quickly get up to speed on your own environment if you’re new to the team. ⚙️ Multi-Tenant Grafana Labs Mimir Support Bring metrics from multiple Mimir tenants directly into Causely’s real-time causal analysis, without duplicating data or breaking workflows. This enhances our system's ability to spot cross-team, cross-environment issues and eliminate blind spots. By the way, did you know? Causely already auto-discovers database dependencies (Postgres, MySQL, MongoDB, Cockroach Labs, and more), represents them as services in your topology, and can pinpoint if/when they are the cause of observed anomalies in other services across your environment. As an added benefit, if you add direct Postgres/MySQL integration, Causely will even tell you which specific queries are slow. If any of this interests you, go sign up for a demo or free trial on our homepage or shoot me a message - I'm happy to speak with you directly!

57

3 Comments