“Spent a lot of time on catching errors in production, like finding out how we can create feedback loops of, hey, we messed up this table, how do we create a better tabular representation?”

The a16z Show · The Missing Infrastructure for AI Agents: Documents | Reducto’s Adit Abraham

Play from 6:59
6:59

Audio streams from the publisher’s own feed. Verbatim does not host or copy it.

What was described

implemented production feedback loops that automatically detect and correct table extraction errors

Said nearby on the same subject

“A collective SaaS product … community … you and your other SMEs in the background … the user feedback loop that you can create in that scenario.”
NC
Nick Coleman
Lawyerist Podcast ·
Why it worked Share this moment
“Agents can be better at structured extraction than humans… if you have a harness where the agent is not only extracting the information but correcting itself, reviewing its outputs, you kind of get to unbalance that in the favor of perfect accuracy”
♫
Said on The a16z Show
“Prompt bloat… there was an error in the code, it kept causing it to loop… retries reused all those tokens again… they changed it and it was off the list”
JW
Jason Ward
Agentic Conversations (formally mlops.community) ·
Why it worked Share this moment
“If there’s a problem … we’re going to fix it right then … we have this feedback loop … we’re going to fix that week.”
NC
Nick Coleman
Lawyerist Podcast ·
How they work Share this moment

Moments like this, every Monday

The strongest new moments on your topics, in the speakers' own words. Free for three topics.

No card. No password. One-click unsubscribe.

Track a competitor?

Pro watches up to 25 names or phrases and emails you the morning after they are said.

See Pro, $29 a month

Verbatim quotes a short extract and links to the episode; the episode belongs to its publisher. Remove a show.