Guidepost Solutions is an investigations, compliance and risk consultancy based in New York, and its more than 250 professionals include former prosecutors, intelligence officers and special agents. Its teams run internal investigations, independent monitorships, compliance reviews and security consulting for corporate, government and institutional clients.
Much of that work involves privileged or confidential material, and many engagements limit where client data can go. The firm now runs Hebno on top of open-weight models it hosts itself, so client data stays inside Guidepost.
“Our investigations and monitorships run on some of our clients’ most sensitive material. Keeping it on our own servers is what let me say yes to AI, and it’s what our clients’ counsel want to hear.”
Allison Spagnolo
Chief Privacy Officer, Deputy General Counsel and Senior Managing Director, Guidepost Solutions
The challenge
Investigators faced long document reviews and tight reporting deadlines. The firm had blocked public AI tools and had no approved alternative. Any tool it chose had to let the privacy team show clients and regulators where data went, under GDPR and US privacy law.
The firm considered building its own tool. That project was scoped at close to a year and several engineers.
Why Hebno
Hebno is the interface on top of the models Guidepost hosts itself, and confidential matter work runs only on those models.
Single sign-on, matter-level permissions and usage logs were ready for the privacy, legal and IT teams from the start.
How the team uses Hebno
Investigators use Hebno for document review, background and due diligence research, and drafting investigation and monitorship reports. The privacy and legal teams use it to search internal guidance and answer client security and privacy questionnaires.
The result
The firm went live in under two months, compared with the year an internal build would have taken. Most of the firm was using Hebno weekly within the first quarter, and each person saves around 7 hours a week.
