Skip to content

Cairn Documentation

AI Pipeline

Every ⌘K command flows through a 5-stage pipeline before reaching your review screen.

1Router (Haiku 5.5)
2Context Assembly
3Specialist (Sonnet 5.5)
4Validator
5User Review

Models

The router is Claude Haiku 5.5, chosen for speed: it only decides which specialist answers and what context it needs. Specialists run on Claude Sonnet 5.5 by default. With your own Anthropic key, Profile → AI Providers → Default Model can switch them to Claude Opus 5.5 for heavier decompositions; high-quality 3D models always use it.

Each call says how much the model should think before it answers (its effort) rather than setting a temperature, which the current models don't take:

EffortUsed forWhy
lowRouting, the semantic check, the interview, property suggestions, image digestsQuick classification and turns you wait on
mediumEvery specialist, simulations, document exportThe reasoning behind a proposal
highHigh-quality 3D modelsGeometry rewards the extra thought

Thinking counts toward a reply's length limit, so Cairn leaves room for it on top of what the reply needs. Cairn reads only the reply's text; the thinking itself isn't shown or stored.

When Claude Declines

Claude's safeguards can decline a request, most often one that reads like weapons, malware or biological work. On Sonnet 5.5 and Opus 5.5, Cairn turns on Anthropic's server-side fallback: a declined request is retried on the model Anthropic recommends for it, the reply continues where the first one stopped, and the proposal's pipeline steps in Change Review name the model that answered. If the router declines, Cairn picks the specialist by keywords instead and the specialist gets its own turn.

If the request is still declined, nothing is proposed and the palette says which safeguard declined it, for example “Claude’s cybersecurity safeguards declined this request. Rephrase it, or say more about what the system is for.” A safety-critical system described plainly (a battery's thermal cutoff, a vehicle's braking) is ordinary engineering; saying what the system is for usually settles it.

Usage and cost count every attempt, each at its own model's rates: after a fallback, the declined attempt is billed as well as the one that answered. A decline before any output is billed only in some categories, so Cairn's estimate can run a little high there.

The Validator

The validator renames ids the model already has (an AI numbers from 001), completes what a specialist left out that Cairn can fill in (a data type's category, a unit it names), and then runs the same guard that decides Apply. Anything the guard would refuse is an error on its operation in review, and the specialist is asked once more with the errors named. A plan of several steps is renamed step by step, so two steps that took the same new id each keep their own references. The trace above the review names each step, its model and its time.

When a Request Fails

A failed request is titled for what failed: the AI couldn't be reached, it declined, its reply couldn't be read, or no step of a plan produced a change. A plan whose steps all failed ends there, with each step named, rather than open an empty review. A plan that reaches your monthly allowance midway stops and shows the allowance, with when it resets. While a request runs, the AI buttons in the lenses say Cairn is still working instead of queuing another.

Specialists

The router selects the right specialist based on your request:

SpecialistTriggersDescription
ArchitectDecompose, add subsystems, restructureFunctional and physical decomposition. Creates 3-6 children with property seeding and interface suggestions. Max 16K tokens.
RequirementsGenerate requirements, add constraintsRequirements elicitation from node descriptions. Generates functional, performance, and safety requirements with acceptance criteria.
InterfacesDefine interfaces, add signalsInterface and signal definition between nodes. Identifies data flows, power buses, command channels, and protocol selection.
BehaviorDefine states, create state machineState machine design with guards, actions, and transition conditions. Generates operating mode state machines. Max 12K tokens.
VerificationAdd tests, verification methodsVerification planning — test, analysis, demonstration, inspection methods linked to requirements.
OperationalGenerate use cases, operational scenariosOperational scenario modeling — use cases with actors, preconditions, postconditions, and ordered step sequences. Generates 3-6 focused scenarios per request, naming actors exactly as the model’s external actors are named.
BriefWrite or update the brief, document a nodeWrites the brief's 8 sections (purpose, capabilities, modes, architecture, interfaces, constraints, verification, risks), only those asked for. Locked sections are kept as written, and each section it writes is stamped with what it was written from.
CausalityAssess maturity, readiness, TRLAssesses the technology maturity of a node and every stone of its Pyramid of Causality: a stage, confidence and evidence for each. Never changes a stage a person set, and patches only the maturity parameters.
NarrativeWrite or update the narrative, systemigram, mainstayTells how a node's parts work together over the links Cairn derives from the model: picks the mainstay, a reading direction, role and verb for each link, and writes the sentence and cards. Everything it returns is checked against the links before review.
DendriticSuggest alternatives, trade-offs, what else was consideredSuggests 1-3 plausible alternatives for how a node is built, set aside with an engineering prune reason, first principle, decision type, phase and the part each was weighed against. Standard ChangeSet review.
GeneralCatch-all for unclassified requestsFallback specialist for requests that don't match a specific domain. Routes to the most appropriate action.