52 lines
1.8 KiB
Markdown
52 lines
1.8 KiB
Markdown
|
# Roadmap
|
||
|
|
|
||
|
|
## Phase 0: Definition
|
||
|
|
|
||
|
|
- Write the project framing and library boundaries.
|
||
|
|
- Define the bounded gate schema contract.
|
||
|
|
- Document the WhetstoneDSL case study and current specialist fleet.
|
||
|
|
|
||
|
|
## Phase 1: Gate Inventory
|
||
|
|
|
||
|
|
- Enumerate candidate gates from WhetstoneDSL.
|
||
|
|
- Record output vocabulary, input shape, and downstream deterministic executor.
|
||
|
|
- Split gates into deterministic, specialist, and escalation-first candidates.
|
||
|
|
|
||
|
|
## Phase 2: Entropy Baseline
|
||
|
|
|
||
|
|
- Define a first-pass gate entropy score.
|
||
|
|
- Score the initial WhetstoneDSL gate set.
|
||
|
|
- Identify which gates are plausible at the ~800KB tier and which are not.
|
||
|
|
|
||
|
|
## Phase 3: Size Sweep
|
||
|
|
|
||
|
|
- Run fixed-data comparisons across multiple model sizes.
|
||
|
|
- Measure accuracy, calibration, confusion concentration, and latency.
|
||
|
|
- Produce the first entropy-to-tier baseline table.
|
||
|
|
|
||
|
|
## Phase 4: Core Library
|
||
|
|
|
||
|
|
- Implement gate schema loading and validation.
|
||
|
|
- Implement the decision request/response runtime.
|
||
|
|
- Implement abstain and escalation policies.
|
||
|
|
- Support pluggable inference backends.
|
||
|
|
|
||
|
|
## Phase 5: Whetstone Integration
|
||
|
|
|
||
|
|
- Expose WhetstoneDSL gates through the library.
|
||
|
|
- Replace selected MCP bounded decisions with local specialist calls.
|
||
|
|
- Log abstentions and misroutes for retraining and gate redesign.
|
||
|
|
|
||
|
|
## Phase 6: Hivemind Integration
|
||
|
|
|
||
|
|
- Feed gate failure data into Hivemind as entropy evidence.
|
||
|
|
- Use Hivemind to prioritize which high-entropy gates deserve deterministic tooling.
|
||
|
|
- Distinguish "needs a bigger model" from "needs a better tool or schema."
|
||
|
|
|
||
|
|
## Exit Criteria For Version 0
|
||
|
|
|
||
|
|
- At least one reusable gate schema format is stable.
|
||
|
|
- At least three WhetstoneDSL gates are benchmarked across size tiers.
|
||
|
|
- A baseline entropy-to-tier recommendation table exists.
|
||
|
|
- One real application can call the library instead of hard-coding model selection.
|