Super Intelligence — the expert council, explained

SI convenes a panel of 16–32 modeled experts to argue about your question and hand you an attributed verdict. There are 242 slash commands under the hood, but the system routes for you — you only need to remember one.

9expert teams
389modeled experts
72specialist cells
242slash commands
1command you need: /SI

Start here 90% OF USES

1

Just ask

The front door. It infers which teams, which verb, and which dials fit your question, confirms in one line, and runs.

/SI "should we build the export feature or buy a vendor tool?"
2

Say it in the prompt — no flags needed

The dials are inferred from your wording: “make them argue” turns on debate rounds, “in depth” turns on full detail, “be brutal” routes to Roast.

/SI "kill the v1 UI or keep maintaining both? make them argue it out"
3

Scope to one team

Already know the domain? The team front doors work the same way — plain English in, verb and dials inferred.

/SI-PD "review this onboarding flow, be brutal"
That is the entire user manual: /SI (or /SI-<Team>) followed by plain English. Everything below this point is how it works under the hood, plus power-user shortcuts for when you want exact control.

How the orchestrator works

Every command follows the same pipeline: infer the verb → route to teams → select the panel → approve → run. The front door first maps your wording to a verb (an intent table: “A or B” → Decide, “tear this apart” → Stress-Test, and so on — if two genuinely fit, it asks one quick question). Team routing is done by a local embedding model that scores your prompt against each team's profile and specialist cells (no cloud call). Single-domain questions auto-delegate to that team; multi-domain questions get a cross-team panel with seats split proportionally to relevance.

Three details worth knowing:

MechanismWhat it means for you
Productive conflict pairing30% of an expert's selection score comes from how well they clash with others already on the panel. The roster is built to disagree, not to echo.
Confidence-tiered approvalWhen the pick is obviously right you get a one-line summary and it proceeds. When it's ambiguous or high-stakes, you get an approve / edit / re-pick gate.
Stance validationEvery claim in the output traces to that expert's documented public stances (with source URL) or is labeled [extrapolated]. Over 25% extrapolated triggers a low-grounding warning.

The --debate flag

By default each expert speaks once and the verb synthesizes (fast, cheap). With --debate, the orchestrator runs the panel as reacting rounds before handing results to the verb. The round protocol lives in exactly one place — the orchestrator — so all 130 debate-capable verbs share the same mechanics.

ModeCostWhenExample
(no flag)Cheapest — single passDefault. Quick takes, routine reviews./SI-Decide "ship Friday or wait for the fix?"
--debateModerate — rounds run in-sessionContested calls where positions should be tested against each other./SI-Decide --debate "sunset the v1 API or support both?"
--debate=fullExpensive — one subagent per expert per roundHigh-stakes, irreversible decisions only./SI-Decide --debate=full "migrate all customers to the new platform?"

Copy-paste debate examples

# You never need the flag — saying it in the prompt works:
/SI "keep building the custom dashboard or adopt the vendor one? make them argue it out"

# Debate on each verb that supports it:
/SI-Decide       --debate "build the integration in-house or buy the connector?"
/SI-Tradeoff     --debate "monorepo vs polyrepo for a six-person team"
/SI-Analyse      --debate "what does on-device AI mean for our roadmap?"
/SI-Review       --debate "review docs/pricing-proposal.md"
/SI-Pre-Mortem   --debate "we migrate billing to the new provider next quarter"
/SI-Post-Mortem  --debate "the launch missed signup targets by 60%"
/SI-Stress-Test  --debate "our plan to deprecate the v1 API in 90 days"
/SI-Plan         --debate "roll out SSO to every enterprise customer this quarter"
/SI-Design       --debate "notification service fanning out to email, chat, and in-app"
/SI-Debug        --debate "p99 latency tripled after the deploy but CPU is flat"
/SI-Defend       --debate "we should stay on SQLite instead of moving to Postgres"
/SI-Re-Analyse   --debate --prior notes/pricing-analysis.md --evidence "competitor cut prices 30%"
/SI-Full-Cycle   --debate "evaluate and decide on the new vendor platform"   # heaviest combo — it will warn first

# Team-scoped versions take it too:
/SI-PD-Decide    --debate "infinite scroll or pagination for the activity feed?"
/SI-Eng-Design   --debate "event bus vs direct service calls for order processing"
/SI-GRC-Stress-Test --debate "our data-retention policy before the audit"

Vote and Roast deliberately don't take the flag — a binary tally and a one-liner roast have nothing to debate.

The command grammar

Every command follows one pattern. Once you know it, you know all 242:

/SI[-Team][-Verb] "your prompt" [flags]

# no team, no verb  →  /SI "..."              routes everything for you
# verb only         →  /SI-Decide "..."       cross-team panel, that verb
# team + verb       →  /SI-PD-Decide "..."    one team's roster, that verb
# team only         →  /SI-PD                 prints that team's roster

The 9 teams

CodeTeamExpertsReach for it when the question is about…
PDProduct & Design56product strategy, UX, design systems, user research, what to build
/SI-PD "infinite scroll or pagination for the activity feed?"
EngEngineering70architecture, code, infrastructure, reliability, security engineering
/SI-Eng "event bus or direct service calls for order processing?"
AIAI59models, agents, ML systems, evals, AI safety and capability
/SI-AI "fine-tune a small model or prompt a frontier one for triage?"
DataData & Analytics29pipelines, metrics, experimentation, analytics engineering
/SI-Data "is this A/B test result real or peeking bias?"
FinFinance47budgets, unit economics, valuation, capital allocation
/SI-Fin "does annual prepay discounting actually improve our cash position?"
TradeTrading46markets, risk models, derivatives, market microstructure
/SI-Trade "stress-test our exposure if rates jump 100bps"
GRCRisk & Compliance30governance, privacy, regulatory exposure, audit, controls
/SI-GRC "review our data-retention policy before the audit, be brutal"
StratStrategy29competitive positioning, market entry, long-range bets
/SI-Strat "enter the SMB segment or double down on enterprise?"
GTMSales, GTM & Marketing23pricing, positioning, launch, pipeline, growth
/SI-GTM "usage-based pricing or seats for the new tier?"

The verbs, grouped by what you want

Every card has two tabs — flip to Examples for a ready-to-paste command per verb.

Make a call

  • Decide — pick between options, named dissent
  • Tradeoff — A-vs-B scored on 4–7 dimensions
  • Vote — yes/no tally on a binary question

Examine

  • Analyse — multi-lens read of a topic
  • Review — critique a doc, PR, or design
  • Re-Analyse — rerun a prior analysis with new evidence
  • Debug — ranked root-cause hypotheses + test order

De-risk

  • Pre-Mortem — what kills this in 12 months
  • Post-Mortem — 5-whys root cause after a failure
  • Stress-Test — adversarial attack, no diplomacy
  • Roast — one cutting line per expert
  • Defend — steelman a position properly

Build

  • Plan — phased plan with owners and risks
  • Design — architecture pass, per-decision attribution
  • Full-Cycle — review → analyse → mitigate → decide (heavy, ~5× latency)

Talk to the experts (team-scoped only)

  • Ask <slug> — 1-on-1 with one expert in their voice
  • Huddle <cell> — one specialist cell synthesizes
  • Meeting — the entire team convenes
  • Read <slug> — print an expert's profile

Team admin (rarely needed)

  • Orchestrate — panel selection only (verbs call this for you)
  • Recruit — propose new experts for a gap
  • Refresh — update stale expert profiles
  • VoiceCheck / Verify — quality checks on voices and citations

Flags (all optional — plain-English wording in the prompt sets the same dials)

FlagEffectExample
--deepFull per-expert detail. Default output is the short tier: verdict + top dissents, ~10–20 lines./SI-Analyse --deep "our churn doubled in Q2"
or just say “in depth” in the prompt
--debate / --debate=fullReacting rounds before synthesis (see above)./SI-Decide --debate "kill or keep the v1 UI?"
or just say “make them argue”
--no-orchestrateSkip selection; use the whole team./SI-PD-Review --no-orchestrate "the new onboarding flow"
--cells a,b / --personas x,yHand-pick the scope; skips orchestration./SI-GRC-Analyse --cells privacy-data-protection "chat-log retention"
/SI-Strat-Decide --personas michael-porter,roger-martin "enter the SMB market?"
--coco-offUse the standalone selector instead of CoCo's context-aware routing./SI-Decide --coco-off "A or B?"

Cheat sheet — situation → command

You're thinking…Type
“I don't know who should look at this”/SI "…"
“A or B?”/SI-Decide "A or B?"
“This is a big, contested call”/SI-Decide --debate "…"
“Tear this plan apart before I commit”/SI-Stress-Test "…" or /SI-Pre-Mortem "…"
“Review this PR / doc / design”/SI-Eng-Review <path> (or PD/GRC flavor)
“Why did this fail?”/SI-Post-Mortem "…" · “What's broken?” → /SI-Debug
“Plan this out” / “architect this”/SI-Plan "…" / /SI-Design "…"
“What would Ann Cavoukian say?”/SI-GRC-Ask ann-cavoukian "…"
“Who's even on these teams?”/SI (no args) or /SI-PD for one team
“Be brutal”/SI-Roast "…"

System health AUDITED + REPAIRED 2026-06-11

Full structural audit of the live installation, with every finding fixed the same day. Verdict: the orchestrator is working, all known gaps closed.

CheckResult
All 242 command files installed and loadingPASS
Every file path referenced by commands resolvesPASS
Embedding router meta_select.py live-testedPASS — correct team + cell scores returned
All 9 team registries consistent; cross-team listings resolve; every expert file on disk registered and selectablePASS — 0 broken references, 0 orphans
Debate wiring: protocol in exactly 10 orchestrators, 117 team verbs + 13 cross verbs forward the flag, Vote/Roast cleanPASS — matches design exactly
Generators portable (env-overridable repo path, no dead-checkout references); team metadata derived live from registriesPASS
27 experts (incl. Porter, Rumelt, Marks) were invisible to selection — root cause was broken YAML frontmatter; repaired deterministically and re-registeredFIXED 2026-06-11
ROSTER.md generated for all 6 missing teams (new build_roster_md.py, regenerable from registries)FIXED 2026-06-11
validate_all_generic.py runs team-aware from the repo root; generator metadata drift eliminatedFIXED 2026-06-11