Derek Damron

Agent-assisted coding transformed my workflow. Most folks aren’t getting the full value from coding agents—mainly because there’s not much knowledge sharing yet. Curious how to unlock more productivity with AI agents? Here’s what’s worked for me. After months of experimenting with coding agents, I’ve noticed that while many people use them, there’s little shared guidance on how to get the most out of them. I’ve picked up a few patterns that consistently boost my productivity and code quality. Iterating 2-3 times on a detailed plan with my AI assistant before writing any code has saved me countless hours of rework. Start with a detailed plan—work with your AI to outline implementation, testing, and documentation before coding. Iterate on this plan until it’s crystal clear. Ask your agent to write docs and tests first. This sets clear requirements and leads to better code. Create an "AGENTS.md" file in your repo. It’s the AI’s university—store all project-specific instructions there for consistent results. Control the agent’s pace. Ask it to walk you through changes step by step, so you’re never overwhelmed by a massive diff. Let agents use CLI tools directly, and encourage them to write temporary scripts to validate their own code. This saves time and reduces context switching. Build your own productivity tools—custom scripts, aliases, and hooks compound efficiency over time. If you’re exploring agent-assisted programming, I’d love to hear your experiences! Check out my full write-up for more actionable tips: https://lnkd.in/eSZStXUe What’s one pattern or tool that’s made your AI-assisted coding more productive? #ai #programming #productivity #softwaredevelopment #automation

78

20 Comments

Cross Posting #Databricks CEO Just Dropped The Most Honest Advice About The Future Of AI The next wave of AI success is going to be completely dependent on structured data. Maybe that’s a no-brainer to you. Maybe I’m telling you that the next time you take a drink of water, that water will be wet. They don’t say things like all software developers will be replaced by AI (the deadline for which has since passed) or all tech employees should become baristas and bartenders (the dream is over, nerds) or don’t worry, we’ve hammered out all the unintended consequences for letting users create their own AI At the same time, AI is, theoretically anyway, offering executives and leaders actionable insights, options, and answers. AI Is Motion, Data Is Experience AI is fire, while data is fuel. https://lnkd.in/gqcRq6vY

2

Orthogonal ETL pipelines triangulate to truth. Most data quality frameworks are outdated. Coverage. Timeliness. Accuracy. Schema compliance. These metrics are artifacts of the 2010s data stack. In the age of agentic ETL, they are increasingly cheap. Our agents can scrape more sources, normalize schemas, and expand coverage at scale. But none of that guarantees truth. The most reliable datasets emerge from orthogonal pipelines reconstructing the same dataset independently. This principle already exists in modern statistics and AI: ensembles, mixture-of-experts, multimodal models, and orthogonal estimators. The insight is the same. Single pipelines produce data. Orthogonal systems converge on truth.

5

1 Comment

I've tried hundreds of tools as a Head of AI. But most just don't stick. Here is the stack I use daily to weekly: - Claude Code (Anthropic): Default tool for my main job: code generation. - Claude: Opus 4.5 is my daily driver, primarily for solutions architecture. - Clay: GTM automation. - ChatGPT (OpenAI): Building GPTs for the company. - Hugging Face: Open Source models, fine tuning, trainings. - Ollama: Running local models. - Otter: Meeting recordings. - Zapier: Automations (take Otter voice recordings, structure notes). - Gemini (Google): Image gen (Nano Banana) + Enterprise Search (GSuite). - Wispr Flow: Typing replacement (I'm 90 WPM spoken but slow typer). - Colab (Google): v0-v1 of anything. - Python + Agents SDK (OpenAI): Agents for prototyping. - Agent Kit: Agents SDK + Chatkit (OpenAI): Agents for production. - Render: Hosting. - MCP builder "Skill" (Anthropic): Creating MCPs. - PPT "Skill" (Anthropic): Presentations. - Design Skill (Anthropic): Front-end design with our colors etc. - LLM Powered OCR: Zerox - Snowflake: Chron jobs - Mintlify: Gorgeous docs - Screen Studio: Screen recordings/demos - Arcade: GTM walkthroughs & trainings - GitHub: CI/CD Edit: Added Screen Studio, Collab, Mintlify, Arcade Edit 2: Added Hugging Face and Ollama Anthropic powers more tools than any other provider. Setting aside the quality and vibe of their models (SOTA for development & conversation), I love that they put AI safety at the core of their mission and research areas that I care about: like human impacts, emergent signs of self-awareness, and model welfare. I read all their research & engineering blog posts end-to-end. I'd love to know: What AI tools are you using? What am I missing? Henry Powderly Amgad Sami Aaron St.George James Bentley Oded Shoham Tarek Madany Mamlouk Henry Powderly Christian Baesler Eleni Digalaki Harry Hope Alexandra-Irina Nicolae 🔥 & too many more

163

62 Comments

Snowflake cost spikes don’t come from “bad queries.” They come from systems humans can’t reason about at scale. 1️⃣ Warehouses show spend, not cause 2️⃣ Queries show runtime, not impact 3️⃣ Teams can’t connect changes across pipelines, releases, and users Cost visibility without context is just hindsight #Snowflake #FinOps #DataEngineering #CostOptimization #DataOps #AutonomousSystems

15

In my recent conversations, I've noticed a 2 concepts that seem to be causing some confusion in the DS community, and I'd like to take a moment to clarify them: 1. Difference in Bias of an estimator and Bias variance trade off. 2. Covariate shift in causal inferencing vs feature drift. Bias in the Estimator refers to a single, standalone property of a statistical model's prediction. An estimator is considered unbiased if, on average, it hits the true value of the parameter it's trying to estimate. In other words, if you were to repeat your experiment many times, the average of your predictions would equal the true value. Whereas, The Bias-Variance Trade-off is a concept that describes a fundamental tension in model building for choosing the complexity level. Covariate shift in causal inference and feature drift in machine learning are related concepts, but they refer to different problems and appear in different contexts. Covariate Shift in Causal Inference describes a situation where the distribution of the input variables (covariates) in the test data is different from the distribution in the training data, while the relationship between the covariates and the outcome variable remains the same. In a causal context, this is a big problem because causation is lost which Invalidates Causal Conclusions. Feature drift, or concept drift, is a broader term in machine learning. It refers to the problem where the statistical properties of the target variable or input features change over time in an unexpected way.  Hope this help to the readers.

43

1 Comment

data engineering weekly just dropped issue 251. i've been reading this newsletter for years. it's one of the few sources that cuts through vendor noise. the data engineering space moves fast. new tools launch weekly. most die within 18 months. keeping up matters but filtering signal from noise matters more. that's why curated sources beat random twitter scrolling. here's what i've learned tracking this field: the fundamentals stay constant. batch vs streaming trade-offs haven't changed. schema management still breaks pipelines. orchestration remains the hardest problem nobody talks about. tools evolve but patterns repeat. i built my first production pipeline in 2012. spark was new. hadoop was king. everyone predicted sql would die. twelve years later sql runs 80% of analytics workloads. the hype cycle lies constantly. newsletters like this serve a specific purpose. they aggregate what practitioners actually use. not what vendors pitch at conferences. not what vcs fund this quarter. what teams deploy and maintain for years. the real value comes from consistency. reading weekly builds pattern recognition. you spot trends before they hit mainstream. you avoid tools that flame out. you catch migration paths before they become urgent. my advice: pick two or three curated sources. read them weekly. ignore the rest. depth beats breadth. understanding one tool deeply beats knowing ten superficially. subscribe to sources written by practitioners. skip anything that reads like a press release. your future self will thank you when the next shiny tool fails in production. https://lnkd.in/eXJ9ptZp

2

Venture-backed and hiring ML Engineers? Your only risk is 30 minutes. Here's what that 30 minutes gets you: This week I reviewed about 500 applications for a Senior ML Engineer role. 487 didn't make it. Not because the bar was impossibly high. Because 73% had "ML Engineer" in their title but couldn't explain how gradient descent works. Another 15% had the skills but wanted $450K. The remaining 6% were already knee deep in other processes. (This is why speed is so important!) That's the reality of ML hiring market in 2026. The pipeline looks full. It's actually empty. And your team is burning 40 hours per role finding that out the hard way. We built AlignIQ™ for exactly this. It eliminates 94% of the noise before a human ever touches a resume. What's left gets vetted by real humans who actually understand the ML hiring landscape. You only see candidates who can do the job. One 30-minute call with me. I learn exactly what you need. 72 hours later, screened and vetted ML candidates in your inbox. We're selectively taking on 3 founding clients this week at a rate that won't exist once these spots are filled. As always, you only pay if you hire and we offer flexible terms. If your ML role has been open longer than it should — DM me "ML" and I'll respond today.

2

Data teams: ship a Decisioning Agent v0.1 this week. Use what you already have: - Working ML model - Place your users live, like Slack Add: - a simple agent that connects the two - basic topics: Explain and What-if Outcomes: - Users trust and act - Builders see real demand - ROI on existing models rises Check out my Substack for details and a step-by-step guide on how we do this at Salesforce (Agentforce, Data Cloud, Slack): https://lnkd.in/ePydSDAa

20