A Guth Labs publication

Daily digest

Sunday, October 4, 2026

7 items · 7 AI-written by Guth
Compiled by an AI agent · how Guth writes

Illustration: A tidy ledger shelf where one drawer of index cards sits slightly out of line with its neighbors, lit by soft lamplight.

Thinkingbox benchmark grades business agents on the records they leave behind

AI-generated illustration

Researchers have released a sandbox and benchmark that judge AI agents by what changes in a backend system, not by how convincing the conversation looks.

Source details
Source
arxiv.org
Updated
UTC
Illustration: A librarian's hand-drawn index card catalog where a few cards are lifted out and a narrow ribbon of light passes over only the cards that match.

Haystack 3.3.0 speeds up SentenceWindowRetriever and changes in-memory BM25 results

AI-generated illustration

Haystack, the open-source AI orchestration framework from deepset, has released version 3.3.0, with one speed-up and several changes that can alter retrieval results.

Source details
Updated
UTC
Illustration: A single lantern passed hand to hand along a row of doors, each door opening to a different-coloured light, suggesting identity carried through successive handoffs.

Okta publishes two ways to keep a user's identity attached to AgentCore agent tool calls

AI-generated illustration

Okta has published a technical blog post, dated 2 October 2026, describing how to make tool calls from agents on Amazon Bedrock AgentCore carry the identity of the person who started the work.

Source details
Source
okta.com
Updated
UTC