Home / Whitepapers
Resources
Whitepapers.
- Free, on request
Journey-driven development: proving software against user journeys with human-governed agent crews
The method Camaan uses to build Camaan. Each change starts as a written journey, is built by a coding agent, and is done only when an end-to-end test passes and its screenshots are attached for a person to review. Includes a case study of one repository's proof record.
- Free, on request
Inside the perimeter: organisation hierarchies, single-organisation engines, engine-cloud sync and verifiable releases
How an enterprise agent platform stays inside the customer's perimeter: an organisation tree with isolation barriers, engines locked to one business unit that sync outbound only, licences verified offline, and signed releases a customer can verify in its own registry.
- Free, on request
Agents on the telephone network: a governed voice loop, SIP lines and an autoscaling speech fleet
How Camaan connects agents to chat, email and the telephone as shareable, audited channels, and what it takes to make a phone line one of them: calling rules enforced in the engine, a shared turn-taking policy, and a speech fleet that scales with demand.
- Free, on request
Durable automation and live analytic pages: workflows, schedules, event triggers, scenarios and digital twins
How Camaan runs unattended work as durable, policy-gated workflows with a database-backed scheduler that holds across engine replicas, and turns data into live analytic pages and digital twins that show each viewer only what they may see.
- Free, on request
KDL: an embeddable, governed lakehouse engine speaking the Postgres wire protocol
A description and measurement of KDL, Camaan's lakehouse engine. It stores data as Parquet files, takes small durable writes through a group-commit log, applies row policies and column masks inside the query plan, and serves clients over the Postgres protocol.
- Free, on request
Knowledge under governance: hybrid retrieval, linked storage and a code-aware knowledge graph
How Camaan's knowledge module keeps enterprise documents under the customer's control: it can index without storing the text, fuses keyword and vector search, and builds a knowledge graph under a customer-written ontology. Includes a retrieval evaluation with a negative result reported as found.
- Free, on request
One gateway, many models: capability-typed model access, cost-aware routing and policy
How Camaan puts every language-model call, from agents, workflows and outside clients alike, through one registry, one gateway and one record, with a small self-contained router that picks a model tier before dispatch.
- Free, on request
Governed agents: a runtime for policy-bounded, auditable AI agents
How Camaan's agent runtime puts every tool call through one policy-checked path and signs each outcome into a tamper-evident ledger. The paper gives the design, the invariants and where each is enforced, and what the authors do and do not claim.