Team Learning Goal
Teach Fusion as a decision workflow.
The goal is not to show every CLI flag. The goal is to teach when a hard software decision benefits from independent model disagreement, how to ask an agent for $fusion, and how to confirm the agent waited for council output before acting.
By the end of this section, the room should understand:
- Fusion is for expensive decisions, not tiny fixes
- Local Fusion is inspired by the panel/finalizer pattern, but is not OpenRouter Fusion
- the
$fusionskill owns command details - the agent should list providers, write a prompt file, run the full configured panel, wait, and read final artifacts
- partial panel output is not the answer
- failed or quota-limited providers degrade the run instead of automatically invalidating it
- the final engineering call still comes from repo evidence
Walkthrough Depth
Essential Walkthrough
- State the core rule: use Fusion when disagreement improves the decision.
- Show good and bad examples.
- Show the local pipeline: prompt file -> panel -> finalizer ->
summary.json/final.md. - Show the
$fusionask prompt. - Show how to confirm the agent waited.
Expanded Walkthrough
Add:
- Local Fusion vs OpenRouter Fusion
- Fable/model-disappearance lesson
- provider terminal states
- degraded panel behavior
- artifact privacy boundary
Deep-Dive Walkthrough
Add:
- live prompt-file build
- provider list and dry-run
- read sample
summary.json - extract consensus/disagreement
- exercise kickoff
Talking Points
Opening:
Fusion is not "ask more models because it feels fancy." Fusion is "this decision is expensive, so disagreement is worth buying."
On partial output:
The first useful provider answer is not the council result.
On local versus hosted Fusion:
OpenRouter Fusion is a hosted product. Local Fusion is a local CLI pattern that shells out to local provider CLIs.
On Fable:
The Fable 5 shock is the lesson: do not make important workflows depend on one fragile model slug.
On final authority:
Fusion advises. The repo decides.
Live Demo Script
Use a no-edit scenario.
1. Choose The Decision
Billing webhook duplicate-processing:
provider event id guard vs invoice lock vs processing ledger.
2. Draft A Prompt File
mkdir -p .notes/fusion
cat > .notes/fusion/billing-webhook-council.md <<'EOF'
# Fusion Prompt
## Goal
Choose the safest first implementation strategy for duplicate billing webhook processing.
## Current Evidence
- paid invoice events may arrive more than once
- current handler can process the same invoice twice
- likely files:
- src/billing/webhook.ts
- src/billing/idempotency.ts
- tests/billing/webhook.test.ts
## Candidate Strategies
- provider event id guard
- invoice-level processing lock
- webhook processing ledger
## Constraints
- preserve provider contract
- avoid schema changes in first pass unless strongly justified
- preserve existing invoice state transitions
## Verification
- pnpm test billing-webhook -- --runInBand
- pnpm build
## Ask
Compare the strategies. Identify consensus, disagreement, hidden risks, missing tests,
and the first shippable slice. End with a concrete recommendation and rollback notes.
EOF
3. Preflight
fusion-high --list-providers
fusion-high --dry-run --file .notes/fusion/billing-webhook-council.md
4. Run
fusion-high --file .notes/fusion/billing-webhook-council.md
5. Confirm
Ask the agent to report:
- Fusion session
summary.jsonfinal.md- provider terminal states
- consensus
- disagreement
- chosen path
- verification
Minimal Useful Path
If 5 minutes behind, cut:
- live run
- OpenRouter benchmark numbers
- custom configs
If 10 minutes behind, cut:
- provider terminal state details
- artifact list
If 20 minutes behind, keep only:
- when to use Fusion
$fusionask prompt- wait for
summary.jsonandfinal.md - Local Fusion is not OpenRouter Fusion
Boundaries With Neighboring Sections
From Section 1:
Oracle PackX is for broad packed context and one expensive external review.
Fusion is for local independent model disagreement on a bounded decision.
From Section 5:
Prompt Builder composes before launch. Fusion can consume a prompt file produced
by any deliberate composition workflow.
From Section 6:
Section 6 compares generated implementation candidates. Fusion compares
independent critiques and strategy recommendations before implementation.
To Section 9:
Imps are narrow one-tool agents. Fusion is a council. Do not send one-tool lookup
work to Fusion.
Careful Origin Wording
Say:
Local Fusion is inspired by the OpenRouter-style panel and judge/finalizer pattern.
Do not say:
Local Fusion is OpenRouter Fusion.
Say:
OpenRouter reported strong DRACO results for Fusion on deep research tasks.
Do not say:
Fusion always beats a single model.
Say:
OpenRouter cautions that Fusion should be used selectively for hard questions.
Do not say:
Fusion replaces coding agents.
Say:
The Fable availability change is the practical lesson about fragile single-model workflows.
Do not claim a precise causal story unless the cited source proves it.
Failure Paths To Preserve
Agent skipped provider list:
fusion-high --list-providers
Agent used inline long prompt:
Ask for a prompt file and --file.
Agent started implementation early:
Stop and request summary.json, final.md, provider terminal states, consensus, and disagreement.
One provider quota-limited:
Explain degraded council behavior. The run can still be useful if final artifacts exist and the missing voice is named.
Final answer flattened disagreement:
Ask for consensus, contradictions, hidden risks, and which repo evidence decides.
Private artifact risk:
Do not paste full session artifacts. Summarize the relevant council result.
Team Checklist
Confirm the materials include:
$fusionskill path- common local source checkout
- OpenRouter inspiration boundary
- not the same product
- not for tiny fixes
- provider list first
- prompt file
- dry-run when uncertain
- full configured panel
- terminal provider states
summary.jsonfinal.md- quota non-blocking
- partial artifacts are partial
- private session store
- advisory output
- repo evidence wins
- billing webhook example
- auth/session example
- model outage fallback example
Further References
- File:
cheatsheets/10-fusion-model-council.md - Exercise:
exercises/10-fusion-model-council.md - Skill:
skills/fusion/SKILL.md - Common local source checkout:
~/dev/fusion - OpenRouter Fusion product page: https://openrouter.ai/fusion
- OpenRouter Fusion model page: https://openrouter.ai/openrouter/fusion
- OpenRouter announcement: https://openrouter.ai/blog/announcements/fusion-beats-frontier/
- OpenRouter model-disappearance post: https://openrouter.ai/blog/tutorials/keep-your-agent-running-when-models-disappear/