5.6 KiB
Prompt Policy and Change Control — Guardrails and Fix Patterns
🧭 Quick Return to Map
You are in a sub-page of Governance.
To reorient, go back here:
- Governance — policy enforcement and compliance controls
- WFGY Global Fix Map — main Emergency Room, 300+ structured fixes
- WFGY Problem Map 1.0 — 16 reproducible failure modes
Think of this page as a desk within a ward.
If you need the full triage and all prescriptions, return to the Emergency Room lobby.
A governance fix page for prompt stability, approval flows, and change control.
Use this page when uncontrolled prompt edits, hidden overrides, or missing approval gates destabilize your RAG or reasoning pipeline.
When to use this page
- Prompts are edited directly in production without sign-off.
- Fine-tuned prompts drift from documented baseline.
- Multi-agent pipelines apply different prompt rules with no central approval.
- No version history or rollback path exists for prompt changes.
- Waivers for unsafe prompt edits lack expiry or owner.
Acceptance targets
- Prompt policy coverage ≥ 0.95 across live agents, RAG steps, and evaluation sets.
- ΔS(question, retrieved) ≤ 0.45 after prompt edits (no semantic drift).
- λ_observe remains convergent across 3 paraphrases and 2 seeds.
- Each prompt edit has recorded owner, approval, and expiry date.
- Version rollback possible in under 60 seconds.
Typical breakpoints and WFGY fix
-
Live edits destabilize outputs
→ retrieval-traceability.md
Require citation schema and provenance anchors before prompt rollout. -
Hidden prompt injection bypasses control
→ prompt-injection.md
Enforce structural schema locks to prevent drift into unsafe states. -
Baseline prompts vanish after fine-tuning
→ policy_baseline.md
Require reference to immutable baseline for audit and rollback. -
Conflicts between agents (different policies in orchestration)
→ Multi-Agent Problems
Use role namespaces and explicit prompt slots to enforce alignment. -
No audit trail for prompt changes
→ audit_and_logging.md
Require immutable logging of who changed what, when, and why.
Minimal governance checklist
- Immutable baselines — Store canonical prompt versions in a controlled repo.
- Approval required — Every change must be signed off before rollout.
- Waivers expire — Unsafe or experimental prompts must auto-expire.
- Rollback path — 1-click restore of previous prompt version.
- Drift checks — Run ΔS/λ probes after every edit; block rollout if drift > 0.45.
- Audit logs — Immutable records joinable to governance lineage.
🔗 Quick-Start Downloads (60 sec)
| Tool | Link | 3-Step Setup |
|---|---|---|
| WFGY 1.0 PDF | Engine Paper | 1️⃣ Download · 2️⃣ Upload to your LLM · 3️⃣ Ask “Answer using WFGY + <your question>” |
| TXT OS (plain-text OS) | TXTOS.txt | 1️⃣ Download · 2️⃣ Paste into any LLM chat · 3️⃣ Type “hello world” — OS boots instantly |
Explore More
| Layer | Page | What it’s for |
|---|---|---|
| Proof | WFGY Recognition Map | External citations, integrations, and ecosystem proof |
| Engine | WFGY 1.0 | Original PDF based tension engine |
| Engine | WFGY 2.0 | Production tension kernel and math engine for RAG and agents |
| Engine | WFGY 3.0 | TXT based Singularity tension engine, 131 S class set |
| Map | Problem Map 1.0 | Flagship 16 problem RAG failure checklist and fix map |
| Map | Problem Map 2.0 | RAG focused recovery pipeline |
| Map | Problem Map 3.0 | Global Debug Card, image as a debug protocol layer |
| Map | Semantic Clinic | Symptom to family to exact fix |
| Map | Grandma’s Clinic | Plain language stories mapped to Problem Map 1.0 |
| Onboarding | Starter Village | Guided tour for newcomers |
| App | TXT OS | TXT semantic OS, fast boot |
| App | Blah Blah Blah | Abstract and paradox Q and A built on TXT OS |
| App | Blur Blur Blur | Text to image with semantic control |
| App | Blow Blow Blow | Reasoning game engine and memory demo |
If this repository helped, starring it improves discovery so more builders can find the docs and tools.
