Failure paths are explicit
Retries, fail-fast gathers, budget fallbacks, and bounded review loops are becoming part of the workflow model instead of hidden control flow.
Language
AI patterns as syntax.
Voss is a small AI-native language that compiles to readable Python. The core move is turning recurring AI workflow code into explicit constructs the compiler and runtime can reason about.
agent Classifier {
ctx(token_budget: 1000) {
intent = ask "Classify this request" probable<string>
if intent @ 0.80 {
return intent.value
}
fallback "unknown"
}
}Recent direction
More workflow, less ceremony.
The language track is tightening the parts of agent work that usually leak into prompts: failure behavior, editor ergonomics, and context budgets.
Editor help is arriving
Formatting, completions, hover text, and go-to-definition make .voss files easier to read and maintain in normal editor workflows.
Context stays budgeted
The roadmap treats long-running context as a budgeted resource: recent work stays detailed, older work is summarized, and savings must be measurable.
Runtime constructs
Inside one agent.
The pieces Voss treats as first-class instead of framework convention — confidence, context, routing, budget, and concurrency.
probable<T>
Confidence belongs in the type system
Model calls return values with confidence attached. Gates like `intent @ 0.80` make trust explicit instead of burying it in app code.
ctx
Prompt windows are scoped resources
Context blocks define token budgets, inputs, compression, and eviction as part of the program structure.
match similar
Semantic routing is declarative
Route by meaning with embedding indexes prepared ahead of runtime, not by sprinkling ad hoc similarity calls through handlers.
within budget
Cost limits are control flow
Budgets and fallbacks are explicit language constructs, so overruns have a designed path instead of a surprise bill.
spawn / gather
Agents compose like concurrent tasks
Parallel agent work, timeouts, and fallbacks are written directly, with the runtime owning lifecycle and coordination.
Coordination spec
Across a whole team.
The same language scales up from one agent to an engineering organization. Roles, principles, gates, and memory become declared, compiler-checked coordination — so a team run is shorter and clearer than the equivalent Python.
principles { }
Engineering culture as config
Declare the principles every agent inherits — smallest diff, no claim without evidence, stay in scope. They compile to immutable config and are recorded in the audit.
team "name" { }
The roster is the source of truth
Roles, scope, budget, tools, and model tier compile to a frozen team config. The EM can only dispatch to declared roles, and scope can never widen past the ceiling.
gate done { }
Completion has requirements
A done gate names what must hold before a card ships: tests passed, independent review, evidence references. Agents can't mark their own work done.
memory { }
Institutional knowledge has a home
Point decisions, sessions, and semantic memory at durable paths so context — and the session tree — survives across runs.
gate done {
require tests_passed
require independent_review
require evidence_refs
}
memory {
decisions: ".voss/decisions"
sessions: ".voss/sessions"
semantic: ".voss-cache/semantic"
}