Daniel Bear

If you're building with Pipecat, this one is for you. We just launched the Tuner <> Pipecat SDK 𝘱𝘪𝘱 𝘪𝘯𝘴𝘵𝘢𝘭𝘭 𝘵𝘶𝘯𝘦𝘳-𝘱𝘪𝘱𝘦𝘤𝘢𝘵-𝘴𝘥𝘬 Now you can plug in observability and analytics in minutes and get real visibility into how your voice agent is performing in production, at scale. Because shipping the agent is only step one.  Understanding what’s happening in production is where the real work begins. Link in the comments 👇

105

12 Comments

Ask AI how OpenClaw can automate workflows in your business, then send me a message and I'll get that all setup for you. Setting up an agentic system can be tricky. Northstar AI Labs has been deep in the weeds, developing AI solutions. If you have heard of AI automation, but you don't want to DIY, a hassle free installation is just 1 message away.

1

At face value the throughput acceleration AI enables feels like progress, faster pipelines and more commits shipped. When you look more closely however, the data reported in the 2025 DORA Report points to a harsher truth... we are moving faster with less control. The metrics behind instability, change fail rate, rework and recovery time are all trending upwards. More often than not, AI is simply automating in failure. The 2025 DORA Report surfaces four painful realities of embedding AI into your SDLC: - AI boosts throughput at the cost of higher deployment failure and rework. We are codifying instability into our pipelines. - Burnout remains flat. Productivity gains are absorbed by higher business expectations, not returned to developers. Faster delivery means faster deadlines. - Over 80% feel more productive with AI. Yet the research shows developers who slowed down by 19% still believed they were 20% faster. Perception of acceleration from AI usage is often just a placebo effect. - The AI Capabilities Model makes value contingent on seven systemic investments, including platforms, data ecosystems and strategy. For many organisations this means a multi-year transformation before they can get close to extracting real value from AI tooling. AI is not a silver bullet, it magnifies the strengths of already high-performing teams, while compounding the weaknesses of others. It is becoming clear that if your team and organisation are already practicing engineering excellence and have a strong, continuously improving product culture, you will benefit the most from AI adoption. If your organisations maturity is low, you are better off investing in foundational changes to your ways of working and culture first.

29

8 Comments

Don't miss a chance to see Rachel and Guy go deep on what it means to support human moderation with voice AI!

5

Early in my career everything was about building large scale homogeneous systems. What’s been more interesting over the last 5y has been heterogeneous multi cloud systems. The tradeoffs are more complex to build simple (irreducible complexity) and elegant systems in that space.

41

2 Comments

Hot take: In a year from now, Apples fumbling of their AI play will be spun as "prescient" given the context of the space at that time.

5

3 Comments

Clay doubling down on increasing action costs while a lot of gtm-e world is laser focused on BYOK workflows with Claude Code is an interesting tension. In the last ~week Cargo shipped a CLI, Apollo.io released an MCP connector for Claude & most of my feed is Claude Code. The ecosystem energy feels entirely focused on terminal-first. I’ve loved Clay for orchestration but have increasingly felt that the UI/UX is slowing me down as I ramp up my terminal-first workflows. That said, terminal-first isn’t multiplayer yet and isn’t in it's final form - esp for larger companies where multiple humans benefit from a shared UI. What’s interesting is this is coming from the people who coined “GTM Engineer” in the first place. The early adopters Clay built the category for are the ones feeling the pull away from the orchestration layer Clay monetizes. The dispersion is probably temporary. But if Clay’s pricing move take them further from the early adopters who built the category, that’s a deliberate bet to cross the chasm to enterprise, while some subset of builders build elsewhere. Interesting to watch.

17

3 Comments

AI feels less like a feature upgrade and more like a productivity shock. The closest comparison I keep coming back to is the Industrial Revolution — chaotic in the moment, transformational in hindsight. It didn’t just cut costs. It made goods abundant. I think AI does the same for services. The real divide won’t be between companies that adopt AI and those that don’t. It’ll be between those who use it to “do the same with less” and those who use it to “do exponentially more with the same.” Efficiency is table stakes. Ambition is the differentiator. I wrote a short piece expanding on this here: https://lnkd.in/gTKGr2Dm Curious where others are landing.

5

A few years ago, I faced a familiar integration headache: multiple systems connecting to one core platform—no schema, no OpenAPI, just dynamic key-value pairs 🧩 Typos, mismatched fields, and structural bugs were constant. So I built a code generator that parsed an Excel field guide and produced: ✅ 100k+ lines of type-safe C# and Python ✅ Postgres DDL ✅ Enterprise-compliant field name translations The result? 🚀 Type safety, fewer bugs, and accelerated integration for two major systems—with almost no ongoing maintenance. Beyond saving time, this tool helped facilitate technical alignment between teams, making handoffs smoother and expectations clearer. It’s a quiet kind of glue—but the kind that keeps things moving. Next up: evolving this idea with AI to go from code that writes code ➡️ code that understands code. Want to encourage cross-functional problem-solving? Start with tools that reduce friction and boost confidence between teams. 🔧💡

8

1 Comment

The Claude ecosystem is exploding faster than I expected. My newest favorite plugins: - Get Shit Done (orchestration layer that plans and builds apps phase by phase) - Ralph Wiggum Plugin ( iterative, self-referential AI development loops) - n8n-MCP (direct Claude integration with 1,000+ automation nodes) What's interesting is how quickly we've moved from simple AI coding assistants to full orchestration platforms. The shift feels similar to what happened with CI/CD tools a few years ago. First you had basic scripts, then comprehensive pipelines, now full DevOps orchestration. We're seeing the same evolution with AI coding tools, just compressed into months instead of years.  #AI #Claude #SoftwareDevelopment #AIAgents #DevTools #Automation

10

How we cut our Redis bill by 95% with one architectural change. 📉 When we started building Flipturn, we fell into a classic serverless trap: The "Silent Bill" of Polling. Our worker nodes were waking up every 0.5 seconds to check Upstash Redis for new jobs. 99% of the time, the queue was empty. But on a pay-per-command platform, "empty" isn't free. We were burning ~170k commands a day just to hear "no new work." We needed an event bus that was instant (low latency) but lazy (zero cost when idle). Instead of moving to Kafka (too heavy) or RabbitMQ (more infra), we doubled down on the infrastructure we already had. In my latest engineering deep-dive, I break down how we moved from Polling to Pushing using Redis Streams. Key Technical Takeaways: 🔹 The "Fake Push" Pattern: Using XREADGROUP with BLOCK=60000 to turn Redis into a push-like system. 🔹 The "Honda Civic" Defense: Why simple, robust tools often beat "industry standard" complexity at the seed stage.  🔹 Idempotency at Ingestion: Using SET NX locks to handle duplicate webhooks before they hit the stream. 🔹 Observability: How to track "Invisible" background jobs using simple queue health metrics. We didn't add a single new service. We just used Redis differently. Read the full story here, have a good read. https://lnkd.in/gqs-zTdE #SRE #DevOps #Redis #Python #FastAPI #SystemDesign #StartupEngineering #Serverless

66

2 Comments

Stardew Valley meets Enterprise RAG? 🚜 🤖 One of the hardest challenges in moving Generative AI from prototype to production is authorization. How do you ensure the LLM only retrieves data the specific user is allowed to see? Our friends Sohan Maheshwar at AuthZed and Rohit Ghumare at motia just dropped a fantastic reference architecture solving exactly this. Using a Stardew Valley "harvest logbook" as the use case, they demonstrate how to build a complete, multi-tenant RAG pipeline. The Stack: ⚡ Orchestration: motia (Event-driven workflows) 🧠 Memory: Pinecone (Vector search & storage) 🔒 Security: #SpiceDB (Fine-grained authorization) This is a masterclass in building secure, context-aware AI applications. Check out the full tutorial below. 👇 #GenerativeAI #RAG #VectorDatabase #Pinecone #Authorization #Engineering #KnowledgeableAI

17

2 Comments

I've been working on an MCP server that lets Claude spawn specialized agents in the terminal and make wrappers around them so you get a Manus/v0/Loveable-style team to build anything. Named after Andrej Karpathy's "Iron Man" analogy and China's Manus, the Iron Manus MCP server augments Claude through Meta Thread-of-Thought (THoT) orchestration where it uses specialized AGENTS instead of TOOLS to break down complex tasks. Check out the vid below for screens and clones it made in about 2 hours total, with fully animated UI, interactive 3D models, videos etc. It's open source, so you can try it for free or watch me explain how it works + docs on the repo: https://lnkd.in/g78wRihH

32

6 Comments

Genuinely cool project. But I think we need to call it what it is. He wrote a database. - Markdown with YAML frontmatter → schema + metadata layer - Skills with ordered steps and validation → stored procedures with constraints - Trigger phrases that route to the right skill → query planner - "Any edit resets approval" → write barrier - Git history → audit trail - .ceos marker file for repo-root detection → connection string swyx wrote about this pattern years ago; you start with "simple persistence" and end up reimplementing half of Postgres in application code. Except here the application code is prompting and context management. What you give up: - Referential integrity? Hope your YAML stays consistent. - Concurrent writes? Git merge conflicts on your config files. - Real queries? "Show me everything that slipped last quarter across all teams" is now a grep pipeline. - Partial rollback? Reverting one field means reverting an entire file. These aren't just edge cases, this is real operational risk at any serious org. The narrative is that this is the future, product UI giving way to executable playbooks. I think it's people rediscovering why databases exist, with worse tooling. The question isn't "when does someone build the framework for this." The framework already exists. It's called a database.

14

1 Comment

I had an absolute blast chatting with Tracy Lee and Danny Thompson on the Leadership Exchange Podcast about what it really takes to build intelligent systems in the AI era. We went deep on: 🤖 The shift from single-model thinking to agentic ecosystems 🧭 Why judgment and evaluation matter more than ever 💼 How AI and Product roles are evolving 🧩 Why data quality and governance quietly make or break AI success 🎯 What the rise of the Chief AI Officer tells us about the future of leadership 🔥 Hot take: AI transformation is 20% tech, 80% culture. If you’ve ever wondered how to evolve your teams, systems, or career in this new AI landscape — this one’s for you. 🎧 Watch here → https://lnkd.in/gABmqvTb What’s your biggest challenge in scaling AI beyond prototypes? #AI #Leadership #Innovation #ProductManagement #DataScience #AIAgents #Engineering

33

2 Comments

Love it or hate it, being in the SF Bay Area is still one of the biggest hacks for First Builders to discover huge opportunities before anyone else. But what can you do if you���re not here? Cecilia for example moved here in 2001 and instantly joined Yahoo after feeling the palpable energy around early internet. And it’s been nonstop ever since as she later joined Amazon, Cruise, Replit, and her own breakout company GC AI. She credits a lot to the emerging tech density and optimism in the Bay Area. But she also mentions additional ways people can identify these opportunities early on: - Follow intuition around big waves - Follow your envy - Never lose curiosity - Watch the teen hackers - Talk to peers early and often (builds long term networks/insights)

21

3 Comments

We just announced the general availability of Elastic Agent Builder, and launched a community hackathon at https://lnkd.in/gJmzxbMu If you're a builder, there's no easier way to build agents directly on top of your data than with Elastic Agent Builder. If you need inspiration, our Elasticians created some incredible projects as part of our company hackathon a couple months ago. Here's a roundup of the top winners and what they created. 1️⃣ The winning team built augmented infrastructure to deploy, monitor and fix live environments. They even wrote a blog about it: https://lnkd.in/gj2YTU3r 2️⃣ One Elastician created a powerful customer support voice agent for a fictional shopping site. Customers can interact with the agent by phone and text message to get help with orders. https://lnkd.in/gQRQfxDU 3️⃣ And another team created an agent that builds other agents, automatically generating new agents based on your Elastic data. https://lnkd.in/gb3RDaeD So, what are you going to build?

31

Platform engineering is the future 🚀 Developers are at the core of everything we do at PagerDuty 💚 Our latest collaboration with Spotify for Backstage brings PagerDuty’s industry-leading Incident Management directly into Backstage, the open platform reimagining developer experience. With the new PagerDuty Plugin for Backstage, devs can see incidents, on-call context, and service ownership right where they already work : Less dilution ; More focus. Let’s go 🎉 Read more 👇 https://lnkd.in/gnsq8Nr9

28

2 Comments

"Cloud Run provisions GPU-backed containers on demand, scales them down to zero when idle, and uses container image streaming to begin execution before the full image downloads." https://lnkd.in/gYxMgsNP

14