Capabilities snapshot
Vera operates within a declared capability snapshot. She can't use tools, network access, or system resources that aren't explicitly permitted by operator policy — even if asked.
Core AI Persona
Meet Vera
Vera is the AI mind inside Voxera OS. She plans, routes, and executes — always within the constraints you set. She isn't a chatbot. She's a structured task planner constrained by policy, approval gates, and deterministic prompt ordering.
"Vera asks before she acts."
Reliability constraints
How Vera stays grounded
Policy + approval gate
Every risky action goes through the approval gate before execution. Vera surfaces the reason and scope; the operator decides allow or deny. No action bypasses the gate.
Deterministic prompt ordering
Vera's planning loop uses a fixed prompt structure — no improvisation on the system prompt. The planning context is traceable and inspectable via artifact bundles.
Today
What Vera can do right now
Write notes and daily check-ins
Queue a natural language goal — "Write a daily check-in with priorities and blockers" — and Vera structures a note, writes it, and records the artifact. No free-form improvisation.
Run system status checks
System status missions query your environment and return a structured summary. Vera uses the system.status skill — no ad-hoc shell execution.
Queue and route structured missions
Vera can plan a multi-step mission from a high-level goal, break it into steps, and route each step through the approval gate before executing.
Classify brain fallback reasons
When a provider fails, Vera classifies why — TIMEOUT, AUTH, RATE_LIMIT, MALFORMED, NETWORK — and surfaces the reason in voxera queue health and voxera doctor.
Generate incident bundles
On request, Vera packages queue state, job artifacts, and system snapshot into a structured handoff folder — ready for review or escalation.
Follow approval-gated automation
Vera executes structured workflows where each risky step is explicitly approved by the operator before it runs — no batch auto-approval.
Planned
What Vera will become
Voice loop
Respond to "Hey Voxera" and handle voice-first commands through the same approval-gated queue. STT/TTS integration planned for v0.3.
Richer mission planning
Structured planning previews with explicit operator confirmation pathways — see exactly what Vera intends to do before any step runs.
Signed skill catalog
Signed skill bundles so operators know exactly what Vera is allowed to do — and can verify it. No unsigned skill execution.
Under the hood
Vera is built on a tiered brain system with deterministic fallback handling and structured prompt ordering. The planning loop is inspectable via artifact bundles.
Engineering details — brain architecture
Brain tier system: primary, fast, reasoning, fallback — each independently configurable per provider. OpenRouter, Gemini, OpenAI-compatible, and local Ollama are all supported.
Fallback classification: when a provider fails, the failure reason is classified into one of: TIMEOUT, AUTH, RATE_LIMIT, MALFORMED, NETWORK, UNKNOWN. The reason persists in health.json and surfaces in voxera queue health.
Prompt ordering: Vera's planning loop uses a fixed prompt structure. The system prompt, capability snapshot, and job context are composed in deterministic order. No runtime improvisation on the system prompt.
Fast path: common write operations (note writes, file writes) use a deterministic fast-path that emits exactly one files.write_text step — no cloud planning required.
See Vera in action
Run the 5-minute demo
Queue a job, watch Vera plan it, approve the execution, and inspect the audit artifact — in a single voxera demo session.