Data review flagged 99.999% row-count variance. PR was two lines. Base: 5 years of prod history. Current: 1-hour CI build. False alarms train reviewers to scroll past. That's the damage. blog.reccehq.com/session-base... #dbt #DataEngineering

90% of enterprise programmers spend their time on maintenance, not greenfield development. Michael Stonebraker's take on where AI actually earns its keep inverts the marketing narrative completely.

Michael Stonebraker was right about CODASYL. Right about NoSQL. Now he's run text-to-SQL on a real enterprise warehouse and got 10% accuracy against an 80% benchmark. The pattern is hard to ignore. blog.reccehq.com/benchmarks-l... #DataEngineering #TextToSQL #AI

Before you let agents touch your codebase, build these gates. Not because you don't trust the agent - but because you wouldn't trust anyone without them. Including yourself. blog.reccehq.com/before-you-l... #ClaudeCode #AIAgents #DevWorkflow

A wiki is something you look at. A shared AI system is something you work through. #ClaudeCode #DataEngineering #BIP blog.reccehq.com/we-didnt-set-out-to-build-a-team-ai-plugin

"Pandas in 2011 was essentially book-driven development, quite literally." @wesmckinney.com wrote features because he needed them for the book chapter. #pandasPython #DataRenegades

AI coding tools generate plausible but wrong SQL constantly. The fix isn't waiting for a smarter model. AI skills are markdown files that encode domain knowledge into coding tools. No framework, just structured text in a repo.

Our own Kent Chen wrote up the multi-agent architecture the team built for Recce's AI Data Review. Single agent kept forgetting findings as PRs got complex. Fix: orchestrator + two specialists, each with its own 200k context window.

"If I had taken three years longer to do things the right way, it would have been too late." -- @wesmckinney.com on why pandas shipped imperfect and won. #pandasPython #DataRenegades

"Arrow has the intricacy of a fine Swiss watch." The co-creator of Apache Arrow (@wesmckinney.com) on why AI agents cannot replicate decade-long infrastructure design. #ApacheArrow #DataRenegades

Starting soon: Bauplan x Recce live session on safe AI automation from branch to production. luma.com/mm3gsalo?tk=... #DataEngineering #AI

"This is bad. Why haven't you fixed this yet? I would have already fixed this today with Claude code." -- @wesmckinney.com on radical accountability for software vendors. #AIcodingagent #DataRenegades

Tomorrow 9 AM PT | Bauplan and Recce walk through a branch-to-production workflow where AI-generated pipeline changes run on isolated branches and get reviewed automatically before hitting production. luma.com/mm3gsalo?tk=...

Why did no big retailers attend the fall JavaScript conference? Every employee was locked down for Black Friday prep. Roger Magoulas sat with someone from Target to find out. No dataset would have surfaced that. 🎧 Full episode: youtu.be/z3E0Pi4XaLg #analytics #datascience

"I would just wake up and write Python code." @wesmckinney.com on the founder hours that created pandas. #DataRenegades #pandasPython

"If you have a successful career built on glazing people, I kind of hate you." Bryan Bischof on why truth-seeking is non-negotiable for data teams. #DataScience #DataCulture

The most predictive feature in the world's first coffee recommender? Favorite salad dressing. The baristas knew. Bryan Bischof on Data Renegades #DataScience #MachineLearning

"When an escalator breaks, it just becomes stairs. When your data workload fails, it's often just stale data." Scott Breitenother on why most data failures aren't as bad as they feel. #DataEngineering #DataReliability

CL Kao takes the stage at the DataTune Conf tomorrow: "A Practical Playbook for Building Data Agents (That Don't Break Your Pipeline)" 288 benchmark trials. Three context problems every data agent hits. CL and @doriwilson.com will be at the Recce booth all day. Come say hey. #DataTune

Building Recce's AI Data Review meant working around three hard limits in Claude: 200k context window, ~90k single prompt, 25k per MCP tool response. 🧵

Wes McKinney built pandas in a mouse-infested NYC apartment on founder hours. Now he runs parallel Claude Code sessions and says AI is forcing "radical accountability" on every software vendor shipping mediocre products. Full conversation: youtu.be/Uso8-yaERkE #DataRenegades #pandas #ApacheArrow

"The data team can't afford to be two years behind. You need to get that exoskeleton going now." Scott Breitenother on why full-stack data people using AI agents are the new operating model. #DataEngineering #AIAgents

New engineers at Kilo ship code on day one. MVP feature by end of week. In production the next week. "We ruthlessly hunt down bureaucracy." Scott Breitenother on Data Renegades #AIAgents #Engineering

"These technologies, they're not robots replacing us. They're exoskeletons that make us better, faster, stronger." Scott Breitenother on Data Renegades #DataEngineering #AI

Scott Breitenother jumped into every Slack thread at Brooklyn Data. It made the company fast and him the bottleneck. His fix: subscribe to replies, don't comment, check back in 3 hours. #Leadership #DataTeams

Code changes have AI review tools. Data changes don't... until now. Our own Kent Chen wrote about how the team built a multi-agent system with Claude Agent SDK and MCP that reviews data changes in every dbt PR. Orchestrator + two specialist agents using 6 Recce MCP tools.

"The team still exists, but it's not five humans, it's one human and four agents." Scott Breitenother on why the unit of productivity has changed. #DataEngineering #AIAgents

Bryan Bischof's hot take: self-serve data analytics is the hype trend most likely to derail. "People are selling third base. I'm still on first base." #DataEngineering #Analytics

New episode of Data Renegades is live Scott Breitenother built a 100-person data consultancy, watched himself become the bottleneck, and rebuilt everything at Kilo Code Their data team is one person plus four AI agents.

"I shit you not. I found one where it gave three backpacks." Bryan Bischof on the production bug where out-of-distribution items sat near the null vector and showed up in every recommendation. #MachineLearning #DataScience

"Saying 'you are wrong' is not curious. Saying 'why are your priors different than what the data is showing' is curious." Bryan Bischof on Data Renegades #DataScience #DataCulture

Happy Valentine's Day to everyone who spent this week falling back in love with their data stack. Five days. Five companies. No slides. No safety nets. Thank you Greybeam, dltHub, Database Tycoon, & bauplan for doing this with us and shipping in front of an audience.

"The best analytics asks more questions than it answers." Roger Magoulas on why dashboards shipped is the wrong success metric. The real measure is whether the work generates questions worth investigating. 🎧 www.heavybit.com/library/podc... #dataengineering #analytics

An AI agent tried to write to production. The lakehouse said no. Day 5 of Data Valentine Challenge: @BauplanLabs brought the finale. Aldrin let Claude Code build his entire pipeline from scratch — on transactional branches that caught every mistake 🧵

"The best code is the code you don't write. Or in this case, the code you delete." Day 4 of Data Valentine Challenge: Database Tycoon ran a live dbt makeover. Stephen volunteered his NYC transit project. Chloe walked the lineage and cut everything dead.

"We didn't write a single line of Python." Day 3 of Data Valentine Challenge: Ashish from dltHub walked through the workspace workflow — GitHub API to DuckDB to reports, no code. One command. One prompt. Pipeline runs 🧵

"Why don't these numbers match?" Kyle from @greybeam_ai opened Day 2 of Data Valentine Challenge with a scenario every data person knows too well. The fix? Query Snowflake, Google Sheets, and raw APIs, all in one SQL statement. 🧵

A feed broke. Roger Magoulas didn't notice. Tim O'Reilly called it out. His fix: a weekly "Synced" email confirming data freshness. Then he added insights. Soon it went company-wide. 🎧 Full episode: youtu.be/z3E0Pi4XaLg #dataengineering #datateams

Tell your agents you love them. Seriously. 💕 CL opened Data Valentine Challenge with 300 benchmark trials testing emotional framing on coding agents. The question: what happens when you add "you totally got this, take your time, love you" to every prompt? 🧵

Phone numbers are seven digits because humans retain about four things plus or minus three. Roger Magoulas on why 47-tab dashboards don't work. Stakeholders will remember none of it. 🎧 www.heavybit.com/library/podc... #analytics #dataviz

What percentage of your data team's time goes to pipeline maintenance versus exploratory analysis? Roger Magoulas argues the ratio determines whether you generate insight or just keep the lights on. 🎧 youtu.be/z3E0Pi4XaLg #dataengineering #datateams

Want a better data stack + love fun data-pun stickers? Join the Data Valentine Challenge Feb 9–13 🦾 Attend all 5 webinars + 1 social post = get a sticker. Signup here: reccehq.com/data-valenti... #DataEngineering #DataQuality

Next week: Fall in love with your data 💕 The Data Valentine Challenge 💘 5 days, 5 companies, 5 real fixes Data teams are drowning. You need quick wins. 30-60 -min daily challenges that actually move the needle. Recce • Greybeam • dltHub • Database Tycoon • Bauplan Details soon 👀 #DataEngineering

LLMs are non-deterministic. But the code they generate is deterministic. Roger Magoulas: prompt for SQL that monitors your pipelines. Run the code. Sidestep the hallucination problem. 🎧 Full episode: www.heavybit.com/library/podc... #llm #dataengineering

"I had casually said, I think I could build a data warehouse in 90 days. My boss said, OK, go to it." Listen to Roger Magoulas on how curiosity and chance encounters beat formal training. 🎧 youtu.be/z3E0Pi4XaLg #dataengineering #analytics #bigdata

Data engineers are so buried in pipeline maintenance, feed monitoring, and DAG management that they cannot shift into insight mode. All reaction. No anticipation. Roger Magoulas on how the value gets crowded out.

Mode raised 80 million over 10 years and resisted being called a BI tool until the market forced consolidation. Lesson: technical tools drift toward BI because wall-to-wall deployments require value for non-technical users. #BITools #DataEngineering

New episode of Data Renegades podcast is live with guest Roger Magoulas. He coined the term "big data" and has 30 experience years of building data teams. Check it out on your favorite podcast app, youtube, or directly here: www.heavybit.com/library/podc...

Benn predicts BI tools get displaced by LLMs analyzing support tickets, not by better dashboards. Execs already decide based on customer stories they heard, not numbers. AI just makes qualitative analysis scale. #AI #DataEngineering Watch the full clip: youtube.com/shorts/vZjaL...

Mode's product strategy: Don't average 50 customer opinions into a Frankenstein feature set. Find the single most opinionated user who gets it and build exactly what they want. Character beats consensus. #ProductStrategy #DataEngineering