Recce - Making Data Productive.

294 posts

Recce - Making Data Productive. banner
Recce - Making Data Productive.

Recce - Making Data Productive.

@DataRecce

Helping data teams preview, validate, and ship data changes with confidence. https://t.co/BgSF4fEcve

The Data Pipeline Присоединился Kasım 2023
103 Подписки29 Подписчики
Recce - Making Data Productive.
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=S6…
English
0
0
0
5
Recce - Making Data Productive.
The agent also produced wrong lineage graphs. Switched from dbt's parent_map format to explicit edge lists matching Mermaid's native format. Accurate ever since.
English
1
0
0
5
Recce - Making Data Productive.
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. 🧵
English
1
0
0
15
Recce - Making Data Productive.
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:
Recce - Making Data Productive. tweet media
English
1
0
0
24
Noma Hub
Noma Hub@noma_hub·
@DataRecce It's worth digging into. The mental model shift is: stop thinking chatbot, start thinking team. Each agent has a job, memory, and communicates with the others.
English
1
0
1
0
Recce - Making Data Productive.
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
English
2
0
1
60