Implicit root
Global route priors, operator gates, shared availability, and collective evidence.
CareerVector operatorBlueprint · careervector.blueprint-graph/v5
Graph explorer
Twenty composable top-level diagrams plus recursively nested 21×21 semantic layers. Nodes descend; boundary arrows cross to neighbours.
Nested layer 2 · control · feedback · privacy
LLM routing address layers
An address names interacting scopes. Each prefix contributes to the result; narrowing the address specializes rather than replacing broader policy.
- Implicit root to Workspace: add
- Workspace to Capability: add
- Capability to Stage: add
- Stage to Consumer: add
- Consumer to Instance?: optionally add
- Instance? to Implicit root: bounded upward projection
Workspace
One person’s declared preferences, keys, consent, budget, and learned fit.
Private workspaceCapability
Extraction, evaluation, salary, tailoring, or explanation behavior.
CareerVector routerStage
A stable step within the capability pipeline and its quality/latency trade-off.
CareerVector routerConsumer
The semantic caller whose output contract and tolerance shape route utility.
CareerVectorInstance?
Only a stable recurring configured object, such as one evaluation column; never an attempt.
Workspace01 · policy · as-built Implicit root Global route priors, operator gates, shared availability, and collective evidence.
CareerVector operator02 · boundary · as-built Workspace One person’s declared preferences, keys, consent, budget, and learned fit.
Private workspace03 · process · as-built Capability Extraction, evaluation, salary, tailoring, or explanation behavior.
CareerVector router04 · process · as-built Stage A stable step within the capability pipeline and its quality/latency trade-off.
CareerVector router05 · perspective · as-built Consumer The semantic caller whose output contract and tolerance shape route utility.
CareerVector06 · boundary · as-built Instance? Only a stable recurring configured object, such as one evaluation column; never an attempt.
Workspace
Flows
- Implicit root → Workspace add
- Workspace → Capability add
- Capability → Stage add
- Stage → Consumer add
- Consumer → Instance? optionally add
- Instance? → Implicit root bounded upward projection
Canonical architecture note
Open note ↗CareerVector
Product outcome
Help a person understand the market, manage opportunities, improve their materials, decide where to invest effort, and collaborate with trusted people and agents. Documents and AI are means; the private career-intelligence workspace is the product.
Authorities
- D1/Yjs owns workspace state, collaboration, CV/CL trees, notes, jobs, preferences, and application activity.
- R2 owns private workspace files and large artifacts.
- JobCache Core supplies shared public role/ad knowledge through a strict seam.
- Smart Routing selects among Included AI, consented Local AI, and user-provided AI within declared preferences, feasibility, quality, and zero-operator-cost constraints.
Invariants
- CareerVector is permanently free to users.
- Private candidate and workspace activity is not monetized.
- One workspace serves one person while supporting trusted collaboration.
- Product-local identity and private state remain below the privacy seam.
- Explicit user AI preferences are gates or policy, not suggestions for the router to erase.
- No AI success or quality is fabricated where no honest outcome signal exists.
Current state
The collaborative workspace, shared app/API/MCP foundations, document engine, job tracking, adaptive LLM routing, BYOK, and corpus seam exist in substantial form. Product experience, Local AI adoption, outcome learning, and several radar workflows continue to evolve.
Completion evidence
Human and agent journeys over the same workspace truth, offline/realtime convergence, privacy and erasure tests, honest AI-route explanation, and no-paywall product behavior.