Dori Wilson

Tomorrow 9am PT: CL is joining Bauplan live to show how AI can safely modify data pipelines without wrecking production. Branch-level isolation + Recce's review agent catching issues before merge. Free & online. luma.com/mm3gsalo?tk=0t…

Every bad join Claude writes becomes a rule in the skills file. Every ignored existing model becomes a convention. The skills get better every time. The next run will be tighter because of everything I caught on this one.

I let Claude Code build dbt models from raw production data. It made certain tables incremental without being told. Smart inference from the data pattern. It also silently dropped rows on edge cases via inner joins. The decisions that matter are still yours.

Claude Code filtered out rows with missing org_ids instead of flagging a potential production bug. An AI made a data quality decision that should have been a human decision. And it didn't flag it. It just handled it. Read about it more here: blog.reccehq.com/i-let-claude-c…

Happy hour tonight, Nashville tomorrow. CL is speaking at DataTune on Saturday. He did 288 benchmark trials on building data agents that don't break your pipeline. I'll be at the Recce booth. Come find us!

"We are in the age of unstructured data and people are not using it enough." Not everything you need is in Snowflake. Bryan built a dataset spanning PDFs, logs, & structured data to prove it. From our Data Renegades lightning round with Bryan Bischof: youtu.be/-s6Xh5sCdLs

New Data Renegades with @wesmckinn. The pandas origin story, why he thinks 2026 is a "great wildfire" for software, & why data infrastructure might be the last thing AI can't replace. His book changed my career. This one was personal. wherever you get your podcasts.

Wes McKinney created pandas in a mouse-infested East Village apartment working 8am to midnight, seven days a week. His take on building in 2026 is just as intense. New Data Renegades drops tomorrow.

I wrote up how I build persistent context for Claude Code. How four manually pasted prompts became a single pipeline, & what happens when the AI silently picks the wrong joins on your dbt models. doriwilson.com/blog/your-ai-t…

I spent more time building skills & MCP configs for Claude Code than watching it generate dbt models. The setup is the work, not the prompt. AI-assisted analytics engineering is an infrastructure problem. Wrote about it on the Recce blog. blog.reccehq.com/i-let-claude-c…

Bryan's worst production bug: too many backpacks. Stitch Fix recommender gave someone three backpacks. System built to prevent duplicates. They lived in a weird part of latent space, close to everything. Same bug bit him twice. Check it out here: youtu.be/-s6Xh5sCdLs

@clay Good point! It’s such an interconnected role! I’ve had fun getting more into building those workflows here at Recce!

@data_dori Fair! Think there’s parts of data engineering, revops, and sales too :)

"What was GTM engineer before Clay decided to make a name for it? Well, that was a data engineer." Same work. New labels. From our Data Renegades chat with Bryan Bischof. Listen to the full episode here: youtu.be/-s6Xh5sCdLs

"Saying you are wrong is not curious. Saying why are your priors different than what the data is showing is curious." Bryan on how to work with people who resist uncomfortable data. Listen to more on Data Renegades with Bryan Bischof. youtu.be/-s6Xh5sCdLs

@AhmadibnRachid Sameee. When Bryan dropped that line I was just nodding along.

@data_dori I feel this in my bones.

"BigQuery UI feels like someone designed it to punish me. Snowflake was like, that's cute. Hold our database query." Anyone who's used these UIs felt this in their soul. More on Data Renegades with Bryan Bischof. youtu.be/-s6Xh5sCdLs

Next Data Debug SF is Tues 3/24, some speaker slots are still open! DM me if you're interested in speaking. Otherwise you can RSVP here: luma.com/lo8ogbub

Enterprise AI POCs failed their year-end reviews The fix everyone landed on: context. A context graph is a knowledge graph subset optimized for AI. The hard part: AI-generated content becomes the new context. The loop closes & now you're dealing with drift youtu.be/cgPw4SSl4Ew

Good one at Data Debug SF this week. Three talks: DuckLake without DuckDB, the builder stack for open source tooling, & what a context graph actually is. Same through-line from 3 directions: building on moving targets. Summary 🧵