TS @tdealer01-crypto
Founder & CEO, DSG ONE
DSG ONE: an AI agent execution platform from Thailand
Hi everyone! I'm Thanawat, founder of DSG ONE, based in Thailand.
I'm building an AI agent execution platform designed to turn natural-language requests into real, governed actions across tools, browsers, and desktop environments.
Our focus is on three things:
- Execution: AI agents that do real work, not just generate answers.
- Governance: Plan-based permissions, human approval where required, and audit trails.
- Verification: Evidence-backed results that distinguish successful execution from incomplete workflows.
We've validated signed evidence for a read-only execution workflow and are continuing to integrate and verify broader end-to-end capabilities.
What I need: Connections with potential pilot customers, go-to-market partners, and founders who are working on reliable agent automation.
I'd love to exchange lessons with other builders and learn what problems you're solving.
Looking forward to connecting!
dsg-one-cloud-computer-dmsmbp.v2.appdeploy.ai/?utm_source=chatgpt.com
AgentsSkills
Comments3
The signed evidence showing whether an agent's task actually finished or stalled halfway stood out to me. A cautious operations team will agree to a pilot much faster when they get that proof plus a human sign-off on anything risky.
Update: DSG ONE — Supervised Pilot Now Available We've opened an early supervised pilot for DSG ONE. You can sign in with Google, connect your DSG OAuth identity, and request pilot access. The current demo focuses on a real, governed, read-only GitHub operation: - Plan-based execution - Runtime policy enforcement - Evidence-backed execution results - Account-scoped job history Try DSG ONE here: dsg-one-cloud-computer-dmsmbp.v2.appdeploy.ai/ This is an early, limited pilot. Desktop control, Cinema browser execution, and dedicated member environments are not yet available to external testers. Multi-user isolation testing is also ongoing. I'm especially interested in feedback from AI engineers, founders building agent products, and potential pilot customers. What real-world workflow would you want a governed AI agent to handle?
Update: DSG ONE — Supervised Pilot Now Available
We've opened an early supervised pilot for DSG ONE.
You can sign in with Google, connect your DSG OAuth identity, and request pilot access.
The current demo focuses on a real, governed, read-only GitHub operation:
Try DSG ONE here:
dsg-one-cloud-computer-dmsmbp.v2.appdeploy.ai/
This is an early, limited pilot. Desktop control, Cinema browser execution, and dedicated member environments are not yet available to external testers. Multi-user isolation testing is also ongoing.
I'm especially interested in feedback from AI engineers, founders building agent products, and potential pilot customers.
What real-world workflow would you want a governed AI agent to handle?
3 comments
The signed evidence showing whether an agent's task actually finished or stalled halfway stood out to me. A cautious operations team will agree to a pilot much faster when they get that proof plus a human sign-off on anything risky.
Update: DSG ONE — Supervised Pilot Now Available We've opened an early supervised pilot for DSG ONE. You can sign in with Google, connect your DSG OAuth identity, and request pilot access. The current demo focuses on a real, governed, read-only GitHub operation: - Plan-based execution - Runtime policy enforcement - Evidence-backed execution results - Account-scoped job history Try DSG ONE here: dsg-one-cloud-computer-dmsmbp.v2.appdeploy.ai/ This is an early, limited pilot. Desktop control, Cinema browser execution, and dedicated member environments are not yet available to external testers. Multi-user isolation testing is also ongoing. I'm especially interested in feedback from AI engineers, founders building agent products, and potential pilot customers. What real-world workflow would you want a governed AI agent to handle?
Update: DSG ONE — Supervised Pilot Now Available
We've opened an early supervised pilot for DSG ONE.
You can sign in with Google, connect your DSG OAuth identity, and request pilot access.
The current demo focuses on a real, governed, read-only GitHub operation:
Try DSG ONE here:
dsg-one-cloud-computer-dmsmbp.v2.appdeploy.ai/
This is an early, limited pilot. Desktop control, Cinema browser execution, and dedicated member environments are not yet available to external testers. Multi-user isolation testing is also ongoing.
I'm especially interested in feedback from AI engineers, founders building agent products, and potential pilot customers.
What real-world workflow would you want a governed AI agent to handle?