Trusted2Act
by Gravitee
Prod is the best eval | Austin Parker, Director of AI Strategy…
About this podcast
AI agents are already hard at work. They're moving money, touching customer data, all at machine speed. And CEOs want more of them, driving efficiency across the org—yesterday.
But who owns these agents? Who sets the rules, makes sure they don't go rogue, and has a plan for when they do? Every deployment eventually runs into the same question: can these agents be trusted?
So teams deploying AI agents are facing this dichotomy: ship fast enough to stay ahead, govern well enough to stay accountable.
Trusted2Act brings both imperatives together. Each week, host Tim Tyler sits down with the platform leaders, security architects, and AI champions actually running agents in production. They dig into how those agents are deployed, where the boundaries are drawn, and how teams hold their agent workforce to the same standard as their human workforce.
Join Tim each week as he explores how to build systems that create agents you can trust.
Episodes
- Prod is the best eval | Austin Parker, Director of AI Strategy, Honeycomb | Ep. 6 · 30 min · Episode 6When agents first started querying Honeycomb through its hosted MCP server, one query came back as a JSON blob large enough to crowd out everything else the model needed to do…
- Why Are We Still Governing AI Like Software? | Ep. 5 · 22 min · Episode 5Tim Tyler opened his AI Engineer talk in San Francisco by reading a job description to the room: no ID, no manager, access to important systems through shared passwords, work…
- Individual agents for individual controls | Dogan Akbulut, Co-founder and CTO, DSALTA | Ep. 4 · 19 min · Episode 4DSALTA’s customers keep asking for one button that writes their whole compliance documentation set. Dogan Akbulut tells Tim Tyler his team could build it, and that it wouldn’t be…
- How to give agents more autonomy and still know who acted | John Gren, Director of Product Management, Gravitee | Ep. 3 · 26 min · Episode 3John Gren wanted an agent to read Jira, compare product requirements against existing tickets, and find gaps in the roadmap. The API key he gave it could write. Soon colleagues…
- What expanding an agent pilot actually authorizes | Anita Ganti, Co-founder and COO, KAVIA AI | Ep. 2 · 19 min · Episode 2A team runs a pilot where an agent reads a codebase, generates a targeted change, and deploys it after a human reviews it. The pilot works, so the team asks to expand. Anita…
- Six questions to answer before an agent goes into production | Linus Håkansson, Chief Product and Technology Officer, Gravitee | Ep. 1 · 28 min · Episode 1Linus Håkansson asked his desktop agent to help with a busy week, and it deleted a bunch of his calendar invitations. It was allowed to. He'd connected it to Google Calendar over…
- Welcome to Trusted2Act · 1 minAI agents are already moving money and touching customer data at machine speed, and CEOs want more of them. But who owns those agents, who sets the rules, and who has a plan for…








