What has to be true underneath before software can safely take actions on your behalf: permissions, an audit trail, and a way back.
8 min read
The AI demo is not the risk. The permission model underneath it is, and it is the thing that decides whether the feature can ever leave the pilot group. Eight questions, product-neutral, with the answer you want to hear for each.
Generative AI answers questions; agentic AI takes actions — and actions are where trust is lost. What makes them safe in Cyril isn’t a guardrail prompt: it’s permission checks on the server, approval before anything runs, and a record of every run.
Why an AI-native platform has to be designed that way from the foundation: one data model, one context surface, one set of guarantees.
LatestThe integration tax: what five separate tools really cost
How to evaluate a business platform, and what a stack of disconnected tools actually costs. Written for the person who has to decide.
LatestHow to run a consultancy on one system: from proposal to paid invoice
Notes from building Cyril: the decisions, the failures, and what they taught us about software an agent can operate.
LatestWhat changes when your development team is an AI
For consulting firms: winning engagements, delivering them on budget and getting paid, and what the software underneath has to do at each step.
LatestHow to run a consultancy on one system: from proposal to paid invoice
One platform for sales, projects, support, docs and financials, with the AI underneath rather than bolted on. Join the waitlist to be among the first to use it.
