Urgent.News

What's breaking now, across thousands of outlets.

Tech

Why my agent returns zero memories for new vendors

The most important line of code in my accounts payable agent is the one that makes it forget everything. When an invoice arrives from a vendor we have never paid, the agent skips memory recall and returns an empty list. That looks like a missing feature. It is the feature. What LedgerMind does LedgerMind is an accounts payable decision agent. An invoice comes in, and the agent approves it, flags…

The accounts payable agent in question is LedgerMind, which makes decisions based on whether to approve, flag an exception, hold payment, or send the invoice to a human. The decision pipeline includes Invoice, Purchase Order, Goods Receipt, Memory Recall, Risk Evaluation, Decision, and Memory Retain. Memory comes from Hindsight, an open-source agent memory system.

In the case of new vendors, LedgerMind skips memory recall and returns an empty list, which appears to be a missing feature. However, it is actually an intentional design choice that helps maintain trust by not manufacturing trust for vendors with no history. A memory layer that returns something for a vendor with no history could potentially lead to trust issues, as a shared bank detail might contain memories about other vendors with similar categories, terms, and amounts.

To prevent this, LedgerMind refrains from making a recall call for new vendors. Instead, it gates new vendors by finance staff, which is the right default. While the agent does make two calls to Hindsight—one before deciding and one after—the reasoning behind these calls is carefully constrained to avoid circular evidence and ensure trustworthiness. This includes filtering raw memories to include only those that mention the vendor by name and do not include the current invoice number.

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in Tech

Beyond the game build: checking itch.io submission copy and image files

Exporting a Web build does not finish a game's submission page. Players may still lack instructions, the screenshot order may be undecided, or the supported-device description may promise more than…

  • Submission page requires additional instructions and decisions beyond game build export.
  • ITCHSUBMISSION.md outlines fields, controls, AI-use disclosure, and screenshot order.
  • JPEG image files submitted instead of required PNGs, indicating need for file correction.

One Hindsight Setting Decided Whether My Agent Could Learn Judges

Litigators know things that no case file records. Judge Murthy lets the other side have one adjournment. The second time, he says “last opportunity.” The third time, he closes the evidence and puts…

  • Litigators rely on learned rules, not documented in case files
  • Hindsight system reads documents, creates memory entries per hearing
  • Agent's observations grouped by case, not consolidated across cases

Ox2A Security Blog

Testing Windows Defender and Wazuh with Atomic Red Team Posted on septemper, 28 by Zehra Begum Introduction Building my first SIEM deployment hands-on cybersecurity journey with log aggregation…

  • Zehra Begum tested Windows Defender and Wazuh with Atomic Red Team.
  • Configured SIEM environment to capture enhanced host and network telemetry.
  • Observed raw adversary actions transforming into structured alerts in SIEM.

Newbie looking for mentorship, inspiration

Good evening, I've just joined the community on the recommendation of a fellow makerspace member. I'm involved in 2 activities right now.

  • Developing design tools for streamlined bicycles
  • Creating K-12 science education simulations
  • Seeking mentorship for skill acquisition

More from Tuesday 29 September →