Prompt Engineering Workflow — My Exact AI Prompt System
prompt engineering workflow: Edmund Ng's journey spoke on governed AI, harness testing, and Vibe Coding for solo founders. Explore.
Published Updated 13 min read
vibe-codingprompt-engineeringai-workflow
prompt engineering workflow matters when you move from demo velocity to production scrutiny. This article is Edmund Ng's field notes on AI prompt system, harness discipline, and the journey toward auditable AI—written for solo founders and system rule designers who cannot afford silent regressions.
Continue with these journey spokes.
Continue with these journey spokes.
Continue with these journey spokes.
Continue with these journey spokes.
Continue with these journey spokes.
Continue with these journey spokes.
Continue with these journey spokes.
Complete Vibe Coding Guide for Non-Programmers · The Phase Document System for AI · Build with AI Without a Programming Background
On this page
- What — this approach AI — AI prompt system — prompt engineering in governed Vibe Coding
- Why — repeatable prompt workflow — workflows beat hero prompts
- When — AI prompt system — run which prompt tier
- Where — repeatable prompt workflow — prompts live (Malaysia solo stack)
- How — AI prompt system — Edmund's daily prompt loop
- 是什么 — extended AI prompt system — repeatable prompt workflow
- 为什么 — extended repeatable prompt workflow — AI prompt system
Key takeaways
- prompt engineering workflow needs written rules—not hero prompts alone.
- AI prompt system keeps demo speed from becoming production regret.
- Harness discipline connects this spoke to the wider governed production journey.
- Cross-link Phase docs, Harness retests, and written tradeoff logs before calling work done.
Takeaways above anchor the rest of this spoke.
What — prompt engineering workflow AI — AI prompt system — prompt engineering in governed Vibe Coding
Most "prompt engineering workflow AI" content teaches templates. Edmund teaches workflow architecture:
| Prompt class | Purpose | Example constraint |
|---|---|---|
| Skills / WHAT | Scope and audience | "Act as gap analyst on frozen Phase doc §3 only" |
| Constitution | Hard stops | "Never merge without diff review; never skip Framework layer" |
| Framework | Wiring and invariants | "Verify two-door paths before marking done" |
| Builder | Implementation sweep | "Fix items 1–4 in contract; no new features" |
Not prompt-pray: If the prompt invents architecture not written in Phase docs, reject the output — that is Framework-Skip with extra words.
Structured exports and harness retests matter more than demo velocity when reviewers ask for evidence.
Structured exports and harness retests matter more than demo velocity when reviewers ask for evidence.
Governed exports and harness checkpoints prevent demo velocity from collapsing under review.
In the What layer of this Act 1 Vibe Coding spoke, teams work from an operational contract—not a marketing label. Governed exports and harness checkpoints prevent demo velocity from collapsing under multi-axis review or compliance questions. A practical test for what prompt patterns survive model swaps: what is frozen before agents sweep, what gets logged at tradeoff time, and which Harness retest proves behavior instead of UI luck. Edmund Ng's field notes emphasize exportable rules and Decision Logs so six-month-later auditors can follow the chain—that is the same fast AND governed bridge Acts 1–3 teach.
Why — repeatable prompt workflow — workflows beat hero prompts
Solo founders lose weeks to context switching — new chat, new " genius prompt," forgotten Constitution. A workflow keeps:
- Same roles every session (builder vs frontier vs sub-agent lanes)
- Same entry artifact (Phase doc, dossier appendix, frozen snapshot)
- Same exit ritual (Harness spot-check, Decision Log if rules changed)
After five rebuilds, Edmund treats prompts as versioned operations on documents — not performance art.
Structured exports and harness retests matter more than demo velocity when reviewers ask for evidence.
Structured exports and harness retests matter more than demo velocity when reviewers ask for evidence.
Governed exports and harness checkpoints prevent demo velocity from collapsing under review.
In the Why layer of this Act 1 Vibe Coding spoke, teams work from an operational contract—not a marketing label. Governed exports and harness checkpoints prevent demo velocity from collapsing under multi-axis review or compliance questions. A practical test for should prompts live in phase documents: what is frozen before agents sweep, what gets logged at tradeoff time, and which Harness retest proves behavior instead of UI luck. Edmund Ng's field notes emphasize exportable rules and Decision Logs so six-month-later auditors can follow the chain—that is the same fast AND governed bridge Acts 1–3 teach.
When — AI prompt system — run which prompt tier
| Trigger | Prompt tier |
|---|---|
| New feature unit | Skills prompt → draft Phase 0 goals |
| Before codegen | Constitution check prompt on non-goals |
| Implementation wave | Builder prompt bound to READY-FOR-BUILDER section |
| Pre-merge | Frontier audit prompt on frozen snapshot (multi-axis review lanes) |
| Incident or surprise pass | Root-cause frontier prompt — POST phase of 10/80/10 spirit |
Skip hero prompts when you have not written non-goals — you will optimize the wrong thing beautifully.
Structured exports and harness retests matter more than demo velocity when reviewers ask for evidence.
Structured exports and harness retests matter more than demo velocity when reviewers ask for evidence.
Governed exports and harness checkpoints prevent demo velocity from collapsing under review.
In the When layer of this Act 1 Vibe Coding spoke, teams work from an operational contract—not a marketing label. Governed exports and harness checkpoints prevent demo velocity from collapsing under multi-axis review or compliance questions. A practical test for how to build a this approach: what is frozen before agents sweep, what gets logged at tradeoff time, and which Harness retest proves behavior instead of UI luck. Edmund Ng's field notes emphasize exportable rules and Decision Logs so six-month-later auditors can follow the chain—that is the same fast AND governed bridge Acts 1–3 teach.
Where — repeatable prompt workflow — prompts live (Malaysia solo stack)
Edmund keeps prompts next to Phase folders and Cursor rules — not scattered in chat exports. Malaysia/APAC builders with small teams benefit: anyone joining mid-project reads the same role prompts tied to the same docs.
Public blog stays abstract — no internal repo paths. Pattern: prompt header → artifact link → output contract → forbidden actions.
Structured exports and harness retests matter more than demo velocity when reviewers ask for evidence.
Structured exports and harness retests matter more than demo velocity when reviewers ask for evidence.
Governed exports and harness checkpoints prevent demo velocity from collapsing under review.
In the Where layer of this Act 1 Vibe Coding spoke, teams work from an operational contract—not a marketing label. Governed exports and harness checkpoints prevent demo velocity from collapsing under multi-axis review or compliance questions. A practical test for what prompt patterns survive model swaps: what is frozen before agents sweep, what gets logged at tradeoff time, and which Harness retest proves behavior instead of UI luck. Edmund Ng's field notes emphasize exportable rules and Decision Logs so six-month-later auditors can follow the chain—that is the same fast AND governed bridge Acts 1–3 teach.
In the Where layer of this Act 1 Vibe Coding spoke, teams work from an operational contract—not a marketing label. Governed exports and harness checkpoints prevent demo velocity from collapsing under multi-axis review or compliance questions. A practical test for what prompt patterns survive model swaps: what is frozen before agents sweep, what gets logged at tradeoff time, and which Harness retest proves behavior instead of UI luck. Edmund Ng's field notes emphasize exportable rules and Decision Logs so six-month-later auditors can follow the chain—that is the same fast AND governed bridge Acts 1–3 teach.
How — AI prompt system — Edmund's daily prompt loop
Morning — orient (5 min):
- Open current Phase document — confirm goal / non-goals / verification
- Skills prompt: "Summarize gaps vs yesterday's residual list only"
Build block — execute (bounded):
- Builder prompt references exact section IDs — "Implement §4.2; do not touch §5"
- Diff review against contract — reject scope creep
Audit block — frontier (scheduled):
- Freeze snapshot — frontier prompt: gap / contradiction / overclaim lanes (see multi-axis review)
- Merge findings to shared marker doc — frontier decides, builder sweeps
Close — governance (non-optional):
- Harness spot-check — at least one invariant test
- If architecture choice made: Decision Log sentence — considered A, chose B, because C
Artifact first → Role second → Prompt third → Output contract fourth
Structured exports and harness retests matter more than demo velocity when reviewers ask for evidence.
Governed exports and harness checkpoints prevent demo velocity from collapsing under review.
In the How layer of this Act 1 Vibe Coding spoke, teams work from an operational contract—not a marketing label. Governed exports and harness checkpoints prevent demo velocity from collapsing under multi-axis review or compliance questions. A practical test for should prompts live in phase documents: what is frozen before agents sweep, what gets logged at tradeoff time, and which Harness retest proves behavior instead of UI luck. Edmund Ng's field notes emphasize exportable rules and Decision Logs so six-month-later auditors can follow the chain—that is the same fast AND governed bridge Acts 1–3 teach.
是什么 — extended AI prompt system — repeatable prompt workflow
Governed builders treat written rules, frozen snapshots, and harness retests as production requirements—not optional polish after a green demo. Edmund Ng's journey from non-programmer Vibe Coding to auditable AI systems shows why structure beats model churn when stakeholders ask how you decided, what you rejected, and what evidence you can export tomorrow.
Governed builders treat written rules, frozen snapshots, and harness retests as production requirements—not optional polish after a green demo. Edmund Ng's journey from non-programmer Vibe Coding to auditable AI systems shows why structure beats model churn when stakeholders ask how you decided, what you rejected, and what evidence you can export tomorrow.
Structured exports and harness retests matter more than demo velocity when reviewers ask for evidence.
Governed exports and harness checkpoints prevent demo velocity from collapsing under review.
In the 是什么 layer of this Act 1 Vibe Coding spoke, teams work from an operational contract—not a marketing label. Governed exports and harness checkpoints prevent demo velocity from collapsing under multi-axis review or compliance questions. A practical test for how to build a this approach: what is frozen before agents sweep, what gets logged at tradeoff time, and which Harness retest proves behavior instead of UI luck. Edmund Ng's field notes emphasize exportable rules and Decision Logs so six-month-later auditors can follow the chain—that is the same fast AND governed bridge Acts 1–3 teach.
为什么 — extended repeatable prompt workflow — AI prompt system
Governed builders treat written rules, frozen snapshots, and harness retests as production requirements—not optional polish after a green demo. Edmund Ng's journey from non-programmer Vibe Coding to auditable AI systems shows why structure beats model churn when stakeholders ask how you decided, what you rejected, and what evidence you can export tomorrow.
Governed builders treat written rules, frozen snapshots, and harness retests as production requirements—not optional polish after a green demo. Edmund Ng's journey from non-programmer Vibe Coding to auditable AI systems shows why structure beats model churn when stakeholders ask how you decided, what you rejected, and what evidence you can export tomorrow.
Structured exports and harness retests matter more than demo velocity when reviewers ask for evidence.
Governed exports and harness checkpoints prevent demo velocity from collapsing under review.
In the 为什么 layer of this Act 1 Vibe Coding spoke, teams work from an operational contract—not a marketing label. Governed exports and harness checkpoints prevent demo velocity from collapsing under multi-axis review or compliance questions. A practical test for what prompt patterns survive model swaps: what is frozen before agents sweep, what gets logged at tradeoff time, and which Harness retest proves behavior instead of UI luck. Edmund Ng's field notes emphasize exportable rules and Decision Logs so six-month-later auditors can follow the chain—that is the same fast AND governed bridge Acts 1–3 teach.
Summary
prompt engineering workflow on Edmund Ng's journey means shipping with AI prompt system, harness retests, and evidence-friendly decisions—not one-off prompts. Models change; written rules, exportable snapshots, and governance patterns endure.
Governed builders treat written rules, frozen snapshots, and harness retests as production requirements—not optional polish after a green demo. The journey from non-programmer Vibe Coding to auditable AI shows why structure beats model churn when stakeholders ask how you decided, what you rejected, and what evidence you can export tomorrow.
How to build a prompt engineering workflow
Edmund Ng treats each long-tail question as a production gate: freeze the spec, log the tradeoff, and prove behavior with Harness retests—not demo clicks alone.
Governed builders treat written rules, frozen snapshots, and harness retests as production requirements—not optional polish after a green demo. The journey from non-programmer Vibe Coding to auditable AI shows why structure beats model churn when stakeholders ask how you decided, what you rejected, and what evidence you can export tomorrow.
What prompt patterns survive model swaps
Edmund Ng treats each long-tail question as a production gate: freeze the spec, log the tradeoff, and prove behavior with Harness retests—not demo clicks alone.
Solo founders in Malaysia and APAC often face professional scrutiny early. Externalizing Phase documents, Decision Logs, and smoke tiers before the demo invitation arrives is cheaper than rebuilding trust after a silent regression reaches a customer walkthrough.
Should prompts live in phase documents
Edmund Ng treats each long-tail question as a production gate: freeze the spec, log the tradeoff, and prove behavior with Harness retests—not demo clicks alone.
Role separation matters: builder models may sweep diffs, but frontier models should audit frozen snapshots. Mixing those hats in one chat thread is how teams lose reproducibility and inherit context debt that no IDE upgrade fixes.
FAQ
What is prompt engineering workflow?
Edmund Ng answers with structure first: freeze specs, separate builder and frontier roles, and prove behavior with Harness—not demo clicks. Written rules, Phase documents, and Decision Logs let teams explain tradeoffs months later without reconstructing chat history.
Governed builders treat written rules, frozen snapshots, and harness retests as production requirements—not optional polish after a green demo. The journey from non-programmer Vibe Coding to auditable AI shows why structure beats model churn when stakeholders ask how you decided, what you rejected, and what evidence you can export tomorrow.
How to build a prompt engineering workflow?
Edmund Ng answers with structure first: freeze specs, separate builder and frontier roles, and prove behavior with Harness—not demo clicks. Written rules, Phase documents, and Decision Logs let teams explain tradeoffs months later without reconstructing chat history.
Solo founders in Malaysia and APAC often face professional scrutiny early. Externalizing Phase documents, Decision Logs, and smoke tiers before the demo invitation arrives is cheaper than rebuilding trust after a silent regression reaches a customer walkthrough.
What is prompt patterns survive model swaps?
Edmund Ng answers with structure first: freeze specs, separate builder and frontier roles, and prove behavior with Harness—not demo clicks. Written rules, Phase documents, and Decision Logs let teams explain tradeoffs months later without reconstructing chat history.
Role separation matters: builder models may sweep diffs, but frontier models should audit frozen snapshots. Mixing those hats in one chat thread is how teams lose reproducibility and inherit context debt that no IDE upgrade fixes.
What is should prompts live in phase documents?
Edmund Ng answers with structure first: freeze specs, separate builder and frontier roles, and prove behavior with Harness—not demo clicks. Written rules, Phase documents, and Decision Logs let teams explain tradeoffs months later without reconstructing chat history.
Governed builders treat written rules, frozen snapshots, and harness retests as production requirements—not optional polish after a green demo. The journey from non-programmer Vibe Coding to auditable AI shows why structure beats model churn when stakeholders ask how you decided, what you rejected, and what evidence you can export tomorrow.
Why does AI prompt system matter for solo founders?
Edmund Ng answers with structure first: freeze specs, separate builder and frontier roles, and prove behavior with Harness—not demo clicks. Written rules, Phase documents, and Decision Logs let teams explain tradeoffs months later without reconstructing chat history.
Solo founders in Malaysia and APAC often face professional scrutiny early. Externalizing Phase documents, Decision Logs, and smoke tiers before the demo invitation arrives is cheaper than rebuilding trust after a silent regression reaches a customer walkthrough.
When should teams freeze specs before agent sweeps?
Edmund Ng answers with structure first: freeze specs, separate builder and frontier roles, and prove behavior with Harness—not demo clicks. Written rules, Phase documents, and Decision Logs let teams explain tradeoffs months later without reconstructing chat history.
Role separation matters: builder models may sweep diffs, but frontier models should audit frozen snapshots. Mixing those hats in one chat thread is how teams lose reproducibility and inherit context debt that no IDE upgrade fixes.
About the author
Edmund Ng — Malaysia-based solo founder, AI systems architect, and system rule designer. He ships governed AI with Vibe Coding, harness engineering, and auditable evidence chains. About · Projects · LinkedIn.