Integrated Reasoning — Meta-Orchestration

Purpose: Select and orchestrate optimal reasoning pattern(s) for your problem. V2 addresses limitations of v1: adds new patterns, replaces order-dependent decision tree with weighted scoring, includes feedback loops, and fixes confidence aggregation.

Available Reasoning Patterns (9)

Pattern Selection: Weighted Multi-Dimensional Scoring

Turn discipline (all models, critical for small ones): announcing this skill or a selected pattern is NOT a response. After any announcement, continue immediately in the same turn with the pattern's actual steps and the tool calls that do the work. (Measured failure mode: a 7.5B local model announced the skill and ended its turn — three times in five runs.)

The scoring pass is silent. Dimension scores, affinity arithmetic, pattern names, and selection narration never appear in the user-facing answer — the reader sees the analysis, not the apparatus that chose it. A selected pattern's structure may appear only as content built from the problem's own facts (a hypothesis table, a criteria matrix), never as methodology narration. Announce nothing; just analyze.

Step 1: Assess Problem Characteristics

Score each dimension (1-5):

| Dimension | Score | Description |
|-----------|-------|-------------|
| **Sequential Dependencies** | _/5 | Do steps depend on previous steps? |
| **Criteria Clarity** | _/5 | Can you clearly evaluate solutions? |
| **Solution Space Known** | _/5 | Do you know the options? |
| **Single Answer Needed** | _/5 | Need ONE answer vs multiple options? |
| **Evidence Available** | _/5 | Can you gather discriminating evidence? |
| **Opposing Valid Views** | _/5 | Are there legitimate conflicting perspectives? |
| **Problem Novelty** | _/5 | Is this unprecedented in your domain? |
| **Robustness Required** | _/5 | Need to stress-test before committing? |
| **Solution Exists** | _/5 | Do you have a candidate solution to evaluate? |
| **Time Pressure** | _/5 | How constrained is decision time? (5=minutes) |
| **Stakeholder Complexity** | _/5 | Multiple parties with competing interests? |

Step 1.5: Time Pressure Fast-Path

CRITICAL: If Time Pressure = 5 (emergency/incident):

• Skip full scoring
• Use Rapid Triage Reasoning (RTR) directly
• RTR is optimized for decisions under extreme time constraints

If Time Pressure ≥ 4:

• Consider RTR unless problem is clearly sequential (use SRC) or diagnostic (use HE)
• Apply abbreviated scoring (skip orchestration considerations)

Step 2: Calculate Pattern Affinity Scores

ToT  = (Criteria × 0.35) + (SingleAnswer × 0.30) + (SpaceKnown × 0.20) + ((6-Novelty) × 0.15)

BoT  = ((6-SpaceKnown) × 0.35) + ((6-SingleAnswer) × 0.30) + ((6-Criteria) × 0.20) + (Novelty × 0.15)

SRC  = (Sequential × 0.45) + (Criteria × 0.25) + (SingleAnswer × 0.20) + ((6-OpposingViews) × 0.10)

HE   = (Evidence × 0.40) + (SingleAnswer × 0.30) + ((6-Novelty) × 0.20) + ((6-OpposingViews) × 0.10)

AR   = (Robustness × 0.40) + (SolutionExists × 0.30) + ((6-Novelty) × 0.15) + (Evidence × 0.15)
       # NOTE: AR requires SolutionExists ≥ 3, otherwise score = 0

DR   = (OpposingViews × 0.50) + (Criteria × 0.20) + ((6-Evidence) × 0.15) + (MIN(SingleAnswer, OpposingViews) × 0.15)
       # NOTE: V2.1 fix - SingleAnswer no longer penalized when OpposingViews is high

AT   = (Novelty × 0.45) + ((6-SpaceKnown) × 0.30) + ((6-Evidence) × 0.15) + ((6-Sequential) × 0.10)

RTR  = (TimePressure × 0.50) + (SingleAnswer × 0.25) + (Evidence × 0.15) + ((6-Novelty) × 0.10)
       # NOTE: RTR auto-selected when TimePressure = 5

NDF  = (StakeholderComplexity × 0.45) + (OpposingViews × 0.25) + ((6-Criteria) × 0.15) + ((6-TimePressure) × 0.15)
       # NOTE: NDF requires StakeholderComplexity ≥ 3 to be considered

Formula Validation Rules (V2.1):

• AR returns 0 if SolutionExists < 3 (nothing to attack)
• RTR auto-triggers when TimePressure = 5 (emergency mode)
• NDF returns 0 if StakeholderComplexity < 3 (single decision-maker)
• If multiple patterns score within 0.3 of each other, use uncertainty propagation (Step 2.5)

Step 2.5: Uncertainty Propagation (V2.1)

When dimension scores are uncertain, propagate uncertainty to pattern selection:

## Uncertainty Assessment

For each dimension where you're unsure (±1 point uncertainty):

1. Calculate pattern scores at LOW end (dimension - 1)
2. Calculate pattern scores at HIGH end (dimension + 1)
3. If different pattern wins at each end → **Flag as uncertain selection**

### Handling Uncertain Selections

**If same pattern wins both ends**: Proceed with confidence
**If different patterns win**:
  - Run BOTH patterns in parallel (if time permits)
  - OR use the pattern that's more robust to being wrong
  - OR gather more information to reduce dimension uncertainty

### Uncertainty Discount
Apply -5% to final confidence for each uncertain dimension that affects the winning pattern.

Step 3: Interpret Scores

Direct Analysis (10th Pattern)

Use Direct Analysis (no specialized pattern) when all three hold:

• MAX(all pattern scores) ≤ 4.0 — no pattern is a clear fit, AND
• No dimension scored ≥ 4 — the problem has no strong characteristic a pattern is built for, AND
• Time Pressure < 4 — otherwise the fast-path applies

## Direct Analysis

**Approach**:
1. No special framework needed
2. Just think through the problem directly, step by step
3. Use common sense and straightforward reasoning
4. Appropriate for simple problems that don't need cognitive overhead

**Examples**:
- Simple factual questions
- Straightforward calculations
- Basic lookups or translations
- Problems with obvious solutions

**Confidence**: Use intuitive confidence based on problem clarity
- Clear problem + clear answer = high confidence
- Any ambiguity = document it explicitly

Direct Analysis = simple step-by-step reasoning without framework overhead.

Effort Level Mapping

After selecting the optimal pattern, set effort level:

For max effort, include "ultrathink" in the analysis prompt to enable extended thinking budget.

Execution Modes

Patterns with context: fork in their frontmatter will automatically run in isolated subagents when invoked via skills. This means:

• They get their own context window (won't bloat main conversation)
• They can't see conversation history (provide full context in the prompt)
• Results are returned as a summary

For inline execution (when you need conversation context), invoke the pattern's methodology directly without using the skill.

Patterns that fork: ToT, BoT, HE, AR, SRC, DR, AT Patterns that run inline: RTR (speed), NDF (needs conversation context for stakeholder interaction) IR-v2 itself: Always inline (orchestrates within main context)

Model-Aware Selection

When running on different models:

• Opus: All patterns available at full depth
• Sonnet: Reduce branch counts (ToT: 3 branches, BoT: 5 approaches). SRC, HE, RTR work well. DR and AT may lose synthesis quality.
• Haiku: Only RTR recommended; other patterns lose quality

Sequential vs Parallel Execution Decision

Use SEQUENTIAL when:

• Pattern B depends on Pattern A's output (e.g., BoT finds options → ToT optimizes)
• Confidence from A affects what to do in B
• Evidence from A eliminates need for B
• One pattern discovers the problem is different than expected

Use PARALLEL when:

• Patterns explore independent dimensions
• No dependency between pattern outputs
• Need ensemble confidence (run same problem through 2 patterns)
• Time allows and you want cross-validation
• Patterns are complementary (e.g., different perspectives on same problem)

Common Chains (Sequential):

BoT → ToT → AR     (explore → optimize → validate)
HE → SRC → AR      (diagnose → trace → validate fix)
AT → DR → ToT      (analogize → synthesize → optimize)
RTR → HE → ToT     (triage → root cause → proper fix)
NDF → ToT → AR     (align stakeholders → optimize → validate)
DR → NDF → ToT     (resolve concepts → negotiate politics → optimize)
AT → BoT → ToT     (find analogies → explore adaptations → select best)

Common Parallel Combinations:

BoT || AT          (parallel exploration from different angles)
ToT || DR          (optimize while synthesizing trade-offs)
HE branches        (test multiple hypotheses simultaneously)
AR attack vectors  (stress-test from multiple directions at once)

Full Reasoning Chain: Input → Output

Complete end-to-end flow for IR-v2 orchestration:

1. **Problem Input**
   └─→ Receive problem statement, constraints, and context

2. **Score 11 Dimensions**
   └─→ Sequential Dependencies, Criteria Clarity, Solution Space Known,
       Single Answer Needed, Evidence Available, Opposing Valid Views,
       Problem Novelty, Robustness Required, Solution Exists,
       Time Pressure, Stakeholder Complexity

3. **Fast-Path Check**
   └─→ TimePressure = 5? → RTR immediately (skip remaining steps)

4. **Pattern Selection**
   └─→ IR-v2 calculates affinity scores for all 9 patterns
   └─→ Apply validation rules (AR needs solution, NDF needs stakeholders)

5. **Direct Analysis Check**
   └─→ Top pattern ≤ 4.0, no dimension ≥ 4, TimePressure < 4? → Direct Analysis (no framework)

6. **Orchestration Decision**
   └─→ Single pattern > 4.0? → Use that pattern directly
   └─→ Top 2 within 0.5? → Consider multi-pattern orchestration
   └─→ Top 3 within 0.3? → Apply uncertainty propagation first
   └─→ Decide: Sequential or Parallel execution?

7. **Pattern Execution**
   └─→ Apply selected pattern(s) using their methodologies
   └─→ Track confidence and key findings

8. **Checkpoint (15 min)**
   └─→ Progress check, pattern fit check, new information check
   └─→ Re-evaluate and potentially switch patterns if needed

9. **Handover (if multi-pattern)**
   └─→ Transfer context via .reasoning/ directory
   └─→ Preserve insights from completed pattern
   └─→ Set up next pattern with full context

10. **Synthesis (if multi-pattern)**
    └─→ Combine findings from all patterns
    └─→ Resolve conflicts, identify agreements

11. **Confidence Aggregation**
    └─→ Single pattern: use internal confidence
    └─→ Multi-pattern: apply agreement analysis
    └─→ Apply uncertainty discounts if applicable

12. **Output**
    └─→ Deliver answer with reasoning trail
    └─→ Document confidence level and key uncertainties
    └─→ Provide actionable recommendations

Multi-Pattern Orchestration

When to Orchestrate

• Top 2 patterns within 0.5 points AND
• Problem is high-stakes (consequences matter) AND
• Time budget allows (>45 minutes available)

Orchestration Patterns

Sequential Orchestration (most common):

1. Use exploration pattern first (BoT, AT)
2. Use optimization pattern second (ToT, HE)
3. Use validation pattern last (AR, SRC)

Parallel Orchestration (when patterns are complementary):

• Run 2 patterns independently
• Compare conclusions
• Use agreement/disagreement to calibrate confidence

Nested Orchestration (when patterns address different aspects):

• Apply different patterns to different sub-problems
• Synthesize at the end

Orchestration Decision Table

| NDF | ToT | Sequential: NDF (get buy-in) → ToT (optimize within agreed bounds) | | NDF | DR | Sequential: DR (resolve conceptual tension) → NDF (negotiate stakeholders) | | BoT | NDF | Sequential: BoT (explore options) → NDF (negotiate which to pursue) |

RTR Orchestration Rules:

• RTR is typically a STARTING pattern, not an ending one
• After RTR stabilizes situation, follow up with deeper analysis
• RTR → HE for incident root cause analysis
• RTR → ToT for revisiting decision with more time

NDF Orchestration Rules:

• NDF typically FOLLOWS technical analysis (know options before negotiating)
• BoT → NDF: Explore space, then negotiate which options to pursue
• NDF → ToT: After stakeholder agreement, optimize implementation
• DR → NDF: Resolve conceptual tensions first, then stakeholder tensions

Parallel Pattern Execution

When top 2 patterns score within 0.3:

• Use built-in parallel subagent execution (multiple Task tool calls)
• Each pattern runs in its own forked context
• Merge results using agreement analysis

When to Parallelize

Parallel execution is appropriate when independent reasoning paths can run concurrently without blocking each other:

Parallel Orchestration Patterns

Parallel Configuration

parallel_config:
  max_concurrent_patterns: 3      # Max patterns running simultaneously
  max_concurrent_branches: 8      # Max branches within a single pattern
  merge_strategy: "consensus"     # "consensus" | "voting" | "aggregation" | "best-of-n"
  timeout_per_branch_ms: 60000    # 60 second timeout per branch
  early_termination_threshold: 0.95  # Stop early if confidence exceeds this

Configuration Guidelines:

• Use max_concurrent_patterns: 2 for typical orchestration
• Use max_concurrent_branches: 8 for BoT exploration
• Increase timeout_per_branch_ms for complex sub-problems
• Lower early_termination_threshold (e.g., 0.85) when speed matters more than certainty

Merge Strategies

Merge Strategy Selection:

If robustness critical → "consensus"
If options are mutually exclusive → "voting"
If findings are additive → "aggregation"
If racing for speed → "best-of-n"

Integration with .reasoning/ Protocol

For the full .reasoning/ handover protocol (directory structure, branch templates, protocol rules), see the parallel-execution skill.

Feedback Loop: 15-Minute Checkpoint

After 15 minutes of applying selected pattern:

## Checkpoint Evaluation

### Progress Check
- [ ] Have I made meaningful progress toward goal?
- [ ] Is my confidence increasing?

### Pattern Fit Check
- [ ] Am I fighting the methodology?
- [ ] Have I discovered new problem characteristics?

### New Information
- [ ] Has the problem changed?
- [ ] Do my characteristic scores need updating?

### Decision
If 2+ checks FAIL:
  → PAUSE: Re-score characteristics
  → If different pattern scores highest: SWITCH
  → If same pattern: Continue with awareness

If all checks PASS:
  → Continue current pattern
  → Set next checkpoint at 30 min mark

Confidence Aggregation (Fixed)

V1 Problem: Additive confidence boosting was statistically invalid.

V2 Approach: Agreement-based bounded adjustment.

Single Pattern Confidence

Use the pattern's internal confidence score (per its methodology).

Multi-Pattern Confidence

## Multi-Pattern Synthesis

### Raw Scores
- Pattern A conclusion: [Answer A] at [X]% confidence
- Pattern B conclusion: [Answer B] at [Y]% confidence
- Pattern C conclusion: [Answer C] at [Z]% (if used)

### Agreement Analysis

**FULL AGREEMENT** (same conclusion):
- Final Confidence = MIN(MAX(X, Y, Z) + 5%, 95%)
- Rationale: Independent paths converging increases trust

**Confidence Bounds**:
- Floor: 10% (never report lower confidence)
- Ceiling: 95% (never report higher confidence)

**PARTIAL AGREEMENT** (2/3 agree):
- Final Confidence = (AVG of agreeing × 0.7) + (disagreeing × 0.15)
- Must document the disagreement
- Consider: Why does one pattern disagree?

**NO AGREEMENT** (different conclusions):
- Final Confidence = MIN(X, Y, Z) - 10%
- This is a FEATURE not a bug - disagreement reveals complexity
- Action: Either (a) gather more information, or (b) present trade-offs to stakeholder

### Shared Assumption Discount
If patterns share significant assumptions, apply -5% adjustment.
(Same LLM, same problem framing, same information = shared blind spots)

Pattern Limitations Reference

Tree of Thoughts (ToT):

• Requires clear evaluation criteria
• Deep recursion may overfit to evaluation function
• Fixed branching can force artificial distinctions

Breadth of Thought (BoT):

• Cannot truly be "exhaustive"
• 8-10 branches may not cover solution space
• Returns multiple options requiring further decision

Self-Reflecting Chain (SRC):

• Limited by weakest step in chain
• Backtracking is costly
• Assumes linear dependency structure

Hypothesis-Elimination (HE):

• Requires discriminating evidence
• Can only find causes in the hypothesis set
• Time-sensitive (may not suit exploration)

Adversarial Reasoning (AR):

• Requires existing solution to attack
• Can be demoralizing if overused
• May miss non-adversarial failure modes

Dialectical Reasoning (DR):

• Requires genuinely opposing valid views
• Synthesis isn't always possible
• Can be slower than just deciding

Analogical Transfer (AT):

• Analogy quality varies widely
• Source domain may mislead
• Requires creativity in finding parallels

Rapid Triage Reasoning (RTR):

• Sacrifices depth for speed
• May miss optimal solution (accepts "good enough")
• Requires follow-up analysis for important decisions
• Not suitable when time is actually available

Negotiated Decision Framework (NDF):

• Requires multiple genuine stakeholders
• Time-intensive (relationship building takes time)
• May produce suboptimal technical solutions for political acceptance
• Doesn't help when one party has absolute authority

Quick Selection Guide

"I need to find the BEST option among known choices"
  → Tree of Thoughts

"I need to explore ALL possible approaches"
  → Breadth of Thought

"I need to trace through a logical chain step by step"
  → Self-Reflecting Chain

"I need to find THE CAUSE of something"
  → Hypothesis-Elimination

"I need to VALIDATE a solution before committing"
  → Adversarial Reasoning

"I'm stuck between two valid but opposing approaches"
  → Dialectical Reasoning

"This problem is novel - no one has solved it in my domain"
  → Analogical Transfer

"I need to decide RIGHT NOW (minutes, not hours)"
  → Rapid Triage Reasoning

"Multiple stakeholders with competing interests must agree"
  → Negotiated Decision Framework

"I'm not sure which to use"
  → Score the dimensions (Step 1)

--- Parallelism Quick-Reference ---

"Top 2 patterns scored within 0.3"
  → Run both in parallel, merge with "consensus" or "voting"

"Need to explore many options fast"
  → Use BoT with max_concurrent_branches: 8

"Testing multiple hypotheses"
  → HE with parallel evidence gathering

"Need diverse perspectives on same problem"
  → MoA pattern: parallel expert personas

"Running parallel but need to merge"
  → consensus (high-stakes) | voting (exclusive) | aggregation (additive) | best-of-n (speed)

Before delivering — mechanical leak scan

Run a literal text search over the user-facing answer for: every pattern name and abbreviation in the table above (ToT, BoT, SRC, HE, AR, DR, AT, RTR, NDF and their full names), "affinity", "dimension score", "scoring the", "confidence aggregation", "checkpoint", "pattern". Every hit is rewritten as content or deleted; deliver only at zero unrewritten hits. A hypothesis list, a criteria matrix built from the question's own stated criteria, or a confidence statement about the answer itself ("~85% this is the cause") are content — they stay.

Example Application

Problem: "Design our company's approach to AI governance"

Characteristic Scoring

Pattern Affinity Scores

• ToT: (3×.35)+(4×.30)+(2×.20)+(1×.15) = 2.80
• BoT: (4×.35)+(2×.30)+(3×.20)+(5×.15) = 3.35
• SRC: (2×.45)+(3×.25)+(4×.20)+(1×.10) = 2.55
• HE: (2×.40)+(4×.30)+(1×.20)+(1×.10) = 2.30
• AR: 0 (SolutionExists=1 < 3, nothing to attack yet)
• DR: (5×.50)+(3×.20)+(4×.15)+(4×.15) = 4.30
• AT: (5×.45)+(4×.30)+(4×.15)+(4×.10) = 4.45 ← Highest
• RTR: (2×.50)+(4×.25)+(2×.15)+(1×.10) = 2.40
• NDF: (3×.45)+(5×.25)+(3×.15)+(4×.15) = 3.65

Recommendation

Primary: Analogical Transfer (4.45) - Look at how other governance challenges were solved Secondary: Dialectical Reasoning (4.30) - Innovation vs caution tension needs synthesis

Orchestration: AT → DR → AR

1. Use AT to find analogous governance frameworks (environmental, financial, medical)
2. Use DR to synthesize the innovation/caution tension
3. Use AR to stress-test the proposed governance approach