Shield uses GPT-6 Astra for legacy IT portal workflows
Shield has deployed GPT-6 Astra within Forge, its AI operating system for IT services providers, to complete supported browser tasks in older portals that often lack APIs. Shield says the workflows are live across its providers with thousands of runs each month, and reports 35–40% faster average execution than legacy models, fewer failures and timeouts, and higher customer satisfaction on tickets using AI. Phone calls, on-site work, and remote-desktop tasks still require human involvement.
The deployment demonstrates GPT-6 Astra being used in production to automate interface-driven IT support work where API access is unavailable, though the reported performance and reliability figures come from Shield.
For many small and medium-sized businesses, an outsourced IT services provider handles everything from an employee locked out of their laptop to a misconfigured firewall that took the office offline.
Shield built Forge(opens in a new window), an AI operating system for IT services providers. The platform brings together business data and customer context to help providers complete IT support tasks end to end. That means its agents also need to work in the older portals technicians use every day. With OpenAI’s GPT‑6 Astra, Shield can now hand supported browser tasks to agents instead of leaving a technician to log in and finish them manually.
“The only time you should have to bring in a human technician is if you need their judgment, not because you’re blocked on access.”
—Mayank Jain, Head of Technology, Shield
Access as a bottleneck
“If a customer is locked out of their computer or there’s a phishing attack, speed is paramount,” says Jain. “Whether you’re going to solve their issue or you’re going to escalate to a human, you want to do either as fast as possible.”