AI architecture

Why an AI-native platform has to be designed that way from the foundation: one data model, one context surface, one set of guarantees.

Posts
5
Latest
Written by
The Cyril team

9 min read

The integration tax: what five separate tools really cost

Licences are the smallest line. Here is an open, assumption-by-assumption model of what it costs to run sales, support, docs, projects and finance in five separate systems — including the line that has only existed since AI arrived.

More on AI architecture

4 more posts

Letting AI act safely needs one audit log, not five

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.

6 min readAlso in Agents and trust

Every record explains itself: the ai_context serializer

Cyril gives its core records an ai_context serializer — a deterministic, schema-aware view built for the model, not the database. It’s the unglamorous core of what makes AI grounding actually work.

5 min read

Other topics

All posts

Agents and trust 2

What has to be true underneath before software can safely take actions on your behalf: permissions, an audit trail, and a way back.

LatestWhat to ask an AI vendor about permissions

Choosing software 8

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

Build log 1

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

Running a consultancy 4

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

Cyril is opening early access

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.

A colleague walking a teammate through notes pinned to a whiteboard in a bright office