alchen.eth (@thealchen) header
alchen.eth (@thealchen) profile picture

Engineering @ Splunk

NYC
Joined December 2007
Photo by alchen.eth (@thealchen)Photo by alchen.eth (@thealchen)Photo by alchen.eth (@thealchen)Photo by alchen.eth (@thealchen)Photo by alchen.eth (@thealchen)Photo by alchen.eth (@thealchen)Photo by alchen.eth (@thealchen)Photo by alchen.eth (@thealchen)Photo by alchen.eth (@thealchen)
Software factories. Evals. Code Quality. Jev. These were some of the topics covered at the @aiDotEngineer NYC conference last month. The conference was directed mainly at the engineers and builders who are trying things on the edge.
1
1
48
๐Œ๐ฒ ๐ญ๐š๐ค๐ž๐š๐ฐ๐š๐ฒ: the C-suite are simply dealing with a different set of problems than the engineers, unsurprisingly. Cost control, change management, risk.
1
3
๐‘‡โ„Ž๐‘’ ๐‘“๐‘’๐‘ค ๐‘คโ„Ž๐‘œ ๐‘๐‘Ž๐‘› ๐‘ก๐‘Ÿ๐‘Ž๐‘›๐‘ ๐‘™๐‘Ž๐‘ก๐‘’ ๐‘๐‘’๐‘ก๐‘ค๐‘’๐‘’๐‘› ๐‘Ž๐‘”๐‘’๐‘›๐‘ก ๐‘’๐‘›๐‘”๐‘–๐‘›๐‘’๐‘’๐‘Ÿ๐‘–๐‘›๐‘” ๐‘๐‘Ÿ๐‘œ๐‘๐‘™๐‘’๐‘š๐‘  ๐‘Ž๐‘›๐‘‘ ๐‘กโ„Ž๐‘’ ๐‘œ๐‘Ÿ๐‘”-๐‘ค๐‘–๐‘‘๐‘’ ๐‘๐‘Ÿ๐‘œ๐‘๐‘™๐‘’๐‘š๐‘  ๐‘ค๐‘–๐‘™๐‘™ ๐‘ค๐‘–๐‘› ๐‘กโ„Ž๐‘’ ๐‘‘๐‘Ž๐‘ฆ.
3
๐Ÿซ• Customermaxxing > Tokenmaxxing. It's the unsexy compliance/security processes that gets AI to production faster at banks. 3 pillars are CVE remedation, disaster recovery, and zero leakage. Grateful for the opportunity #AIEngineerNY @aiDotEngineer @swyx youtube.com/watch?v=Bz1HFxQAโ€ฆ
1
2
9
2,363
Last time I saw myself in the paper was when my middle school jazz band played at our local senior citizens center. Coolest conference swag @aiDotEngineer @swyx @karasilverman
1
4
554
๐ŸฅŒ Current thinking, skills, and open questions for capturing relevant customer context into a wiki ๐Ÿงต
1
152
On the engineering side, we've already set up a system to automatically update the README on our repos with mermaid diagrams and architecture based on latest commits. I think something like this should exist for customer context, but a repo doesn't feel like the right substrate.
1
13
Experimenting with OpenWiki from @LangChain and DeekWiki from @cognition to see how these frameworks may be able to help.
14
These are the typical places where bugs, feature requests, and nuances about the customer's k8 cluster and deployment are discussed. But stepping back a bit, GItHub PRs and Claude sessions where our engineers and PMs are investigating customer issues, drafting specs, and making
1
9
key product decisions are also good sources of context. You could connect our wiki agent or whatever with the GitHub MCP to search for relevant PRs for the customer in question, but that seems a but clunky.
5