> ## Content Index
> Fetch the complete content index at: https://www.ai-360.online/llms.txt
> Use this file to discover other available public pages before exploring further.

# Northern Trust reports a measured onboarding-agent case
- URL: https://www.ai-360.online/northern-trust-reports-a-measured-onboarding-agent-case/
- Published: 2026-11-12T11:36:00.000Z
- Updated: 2026-11-13T11:36:46.000Z
- Description: Northern Trust and Microsoft say data preparation fell from about two and a half weeks to three days, with a 96.5% first-pass F1 score and human review of outputs, reasoning and exceptions.
- Author: AI-360
- Tags: News, BFSI

Northern Trust and Microsoft [say data preparation](https://news.microsoft.com/source/2026/11/09/northern-trust-and-microsoft-frontier-company-collaborate-to-transform-client-onboarding-through-ai?ref=ai-360.online) fell from about two and a half weeks to three days, with a 96.5% first-pass F1 score and human review of outputs, reasoning and exceptions. The figures are company-reported.

Northern Trust and Microsoft have described a jointly developed agent that prepares institutional client-onboarding data before go-live. Northern Trust says the work reduced data preparation from roughly two and a half weeks to three days and achieved a 96.5% first-pass F1 score.

Those are company-reported figures rather than an independent benchmark. The more useful detail is that analysts review outputs, reasoning and exceptions while the system is still operating in a bounded implementation stage. Errors in source data can be corrected before the agent reaches a client-facing or production decision.

---

[Execution Level Governance- What audit-ready agent governance actually looks likeDavid Girvin, founder and CEO of Assury argues that model-in-the-loop review, AI governing AI, is fundamentally unreliable for regulated environments: even the best-performing models miss a meaningful share of violations, the reviewing model is typically provided by the same vendor being reviewed, and prompt injection or context poisoning can compromise both the acting agent and its supposed overseer simultaneously. He makes the case for deterministic, architecturally enforced controls instead, walking through Assury's approach of autonomy zones, session risk accumulation, and credential starvation, which lets a compromised agent be cut off from its tools instantly rather than relying on time-boxed access. The conversation touches on why David is sceptical of just-in-time credentialing as a solution for agent security more broadly, since agent sessions don't run on predictable human timescales, along with the current gap between how identity and security vendors are pitching agent protection and what he sees happening at the execution layer in practice. He also discusses the compliance and audit implications of probabilistic decision-making, arguing that regulated industries will increasingly need tamper-evident, hash-chained audit trails that can withstand scrutiny from auditors and regulators who are only beginning to understand agentic risk, and reflects on a named frontier lab's own published framework as an example of the gap between research and practitioner reality. Elsewhere, David reflects candidly on building a bootstrapped security company in an increasingly crowded market, why he turned down aggressive VC funding to stay in control of the product, and what a credible third-party assessment of his own gateway would need to look like given that Assury sits directly in the execution path for every customer's agents.![](https://storage.ghost.io/c/b5/36/b536821c-5870-4f52-b9ef-106719725971/content/images/icon/favicon-1a30b5a9-f520-4a0a-b9ca-0591463061a7.ico)BrightTALK![](https://storage.ghost.io/c/b5/36/b536821c-5870-4f52-b9ef-106719725971/content/images/thumbnail/image_1107713-635f4c0d-7644-4997-bc81-2e7ac2736797.png)](https://www.brighttalk.com/webcast/21039/674139?ref=ai-360.online)