Architecture

How Brainstorm Reactor thinks.

The quality of AI output depends on process design, not prompt engineering skill. Brainstorm Reactor shifts control: away from prompting, toward designing cognitive recipes.

200+Methods
84+Recipes
63Workflows
3Model Slots
4Personas
6Patterns
Prompt Architecture

One stream.
Five composable layers.

Every API call builds a system prompt from five independent layers. The same recipe step produces fundamentally different results depending on persona, context, and method. Library of 200+ frameworks.

01

Persona

Cognitive stance — analytical, creative, adversarial, or curatorial

02

Method

One of 200+ thinking methods, injected as a structured instruction

03

Context

Pinned content + pruned history (full, last_step, or none)

04

Slot

Model selection — LOGIC, CREATIVE, or SEARCH per step

05

Output

Structured nodes, streamed in real-time with transparent reasoning

Multi-Model Orchestration

Three slots.
Heterogeneous composition.

Each recipe step declares the required cognitive slot. Analytical work goes to reasoning models, research to web models, synthesis to generative models — all in one workflow.

SLOT_LOGIC

Analytical Reasoning

Reasoning models (o1, o3-mini, Gemini Flash Thinking)

TRIZ analysis, contradiction detection, scoring, validation, adversarial audit

SLOT_CREATIVE

Ideation & Synthesis

Generative models (Claude Sonnet, GPT-4o, Llama 4)

Brainstorming, storytelling, concept synthesis, solution architecture, copywriting

SLOT_SEARCH

Evidence-Based Research

Web models (Perplexity Sonar, Gemini with grounding)

Patent research, competitive analysis, market research, state of the art

Orchestration Patterns

Six ways to orchestrate thinking.

From selective amnesia to parallel swarms — every recipe is built on composable execution patterns.View all recipes

PATTERN A

Shadow Pass & Selective Amnesia

Sequential steps with precise context scopes. Using 'last_step' context mode allows the engine to completely forget original user prompt bias (selective amnesia) for a clean synthesis.

BaselineVISIBLESilent PassSILENTMain TaskAMNESIAfull ctxfull ctxlast_step

e.g. TRIZ Express, Elevator Pitch

PATTERN B

Parallel Swarm & Synthesis

Simultaneous adversarial execution of multiple agents with divergent directives. A centralized synthesizer compiles their outputs from a compressed XML matrix.

SpawnLogicCreativeResearchΣSynth

e.g. MAD Engine, Ergodic Hive

PATTERN C

Autonomous Critique & Revise (Aletheia)

An autonomous feedback loop where an auditor step evaluates outputs against constraints, running backward jumps with pruned context (Context Collapse) until passing.

GenerateAI CheckNextPassFail → Retry

e.g. Aletheia Engine, TRIZ v9 MAX

PATTERN D

User Decision Branching (Router)

Workflow pauses at defined decision points. Using keyword matching on quick-reply buttons (with optional D2 Split Router), the user directs the flow dynamically along specialized branches.

PAUSEInputPath APath BOption 1Option 2

e.g. Dilemma Decoder, Branching Demo

PATTERN E

Unconditional Forward Jump

A converging execution flow where multiple parallel branches or slots automatically jump forward to a single consolidation step using empty routes.

BranchPath APath BConvergencejump forwardjump forward

e.g. Split Router, Configurator Suite

PATTERN F

Epistemic Anchor (Auto-Pin)

Pins foundational outputs to the persistent '<pinned_context>' layer. Subsequent steps can access this baseline directly, even when operating with selective amnesia.

Anchor Stepauto_pinStep 2Step 3last_step<pinned_context>

e.g. Data Baseline, Core Compiler

HYBRIDS

Composable Patterns

Patterns can be freely combined. Real recipes are hybrids:

  • C+BAutonomous swarm — parallel agents + self-correction
  • D+BBranching swarm — user decision → specialized swarm
  • C+DCopilot / Autopilot — user switches between manual routing and autonomous loop
Transparency

Glass Box UI.

Every AI response is fully transparent. No black box. See what the model thought before it wrote — inspect structured data and debug raw output — all in real-time.

Agent labels show which specialist is active during multi-step recipes. The Cognitive Protocol reveals the model's internal reasoning process before a single word of output appears.

Rendered
Thinking
JSON
Raw
Rendered

Formatted output — clean, structured, actionable

Thinking

Native reasoning trace from the model's thought process

JSON

Structured node data — parseable, exportable

Raw

Unprocessed model output for debugging

Showcase

TRIZ v8 Orchestrator.

5 specialized agents. 3 model slots. 2 context modes. The flagship recipe demonstrates full orchestrator capacity.

#1System Analysis

Decompose the problem into components, functions, and contradictions.

SLOT_LOGICctx:full
#2Logic Engine

Apply the TRIZ contradiction matrix. Generate solution directions.

SLOT_LOGICctx:last_step
#3Patent Swarm

Research existing solutions, patents, and analogous domains.

SLOT_SEARCHctx:last_step
#4Solution Architect

Synthesize all insights into concrete, actionable concepts.

SLOT_CREATIVEctx:full
#5Adversarial Audit

Identify weaknesses, risks, and unintended consequences.

SLOT_LOGICctx:full

Context Pruning

Steps 2 & 3 use last_step — the model focuses on the distilled output, not the full history.

Slot Diversity

Analysis → reasoning models. Research → web models. Synthesis → creative models. No single model does everything.

Adversarial Close

Step 5 sees the full context but uses a reasoning model — maximum scrutiny on the entire proposal.

White-Label Implementation

Real-World Validation: AI Swimcoach.

The physical optimization of hydrodynamics (via TRIZ heuristics) and the algorithmic monitoring of acute training loads (ACWR) execute on the exact same deterministic multi-model orchestration as a complex enterprise SaaS audit.

Why does an AI process engine built for corporate strategy prove its logical depth at the edge of the pool? Because high performance relies on universal laws. Our fully white-labelable platform powers, among others, the independent /swimcoach dropzone. The Reactor encapsulates its cognitive power server-side, allowing seamless injection into any existing business framework.

01 / Diagnostics

Socratic Diagnostics

Automated onboarding and mapping of the problem space until a stable level of understanding is reached.

02 / Load monitoring

ACWR Load Control

Algorithmic injury prevention calculating the acute-to-chronic workload ratio in real time.

03 / Segmentation

USRPT Micro-Sets

Mathematical segmentation of volume into short intervals to safeguard biomechanical stroke integrity.

Scientific Foundation

Why cognitive architecture beats mega-prompts.

In March 2026, the Kimi team published the paper Attention Residuals — a mathematical proof of a problem that Brainstorm Reactor already solves architecturally at the process control level.

Neural Level (Kimi)

PreNorm Dilution

In deep networks, residual connections accumulate. Essential early information gets diluted by noise from middle layers — deeper layers lose access to the original signals.

Application Level (Reactor)

Context Contamination

In standard chats, context accumulates message by message. By the time a model reaches step 6, the original problem is diluted in the noise of iterative intermediate steps.

Symmetry 01

Skip Connections → Epistemic Anchor

Kimi: Later layers skip accumulated noise and directly access early, clean layers (Attention Residuals).

Brainstorm Reactor: The Epistemic Anchor preserves extracted facts from step 1 via auto-pinning. Later agents with context_mode: last_step work only with the distilled output — the ground truth remains directly accessible via <pinned_context>.

Symmetry 02

Block Compression → Swarm Synthesis

Kimi: Layers are grouped into blocks and compressed into a single vector. Later layers see only the clean summary, not the raw individual steps.

Brainstorm Reactor: When parallel agents work (Pattern F), a synthesizer step compresses the outputs into a dense XML aggregate. Subsequent steps process only this node — not the individual agent responses.

Symmetry 03

Deep & Narrow → Microsteps

Kimi: Networks with Attention Residuals reach their optimum with deeper, narrower architectures — shallow networks stagnate.

Brainstorm Reactor: Many tightly focused steps (deep & narrow) beat few overloaded mega-prompts (shallow & wide). When the engine handles navigation and context pruning, the model can concentrate 100% of its parameters on pure transformation.

Intelligence in complex systems doesn't emerge from endlessly accumulating data, but from targeted noise reduction — regardless of whether the system is a neural network or a cognitive pipeline.

Source: Kimi / Moonshot AI, Attention Residuals (March 2026) · View benchmark results →

Infrastruktur & Sicherheit

Unabhängig. Souverän. DSGVO-nativ.

Die Brücke zwischen maximaler Modellfreiheit und kompromissloser Datensicherheit. Der Brainstorm Reactor kapselt seine kognitive Leistung serverseitig und schützt geschäftskritische Daten vor unbefugtem Abfluss.

EU-native Infrastruktur

Die gesamte Kernplattform und alle Datenbanken werden ausnahmslos in der Europäischen Union (Deutschland und Irland) betrieben.

Zero Data Retention

Verarbeitung ausschließlich über geschäftliche B2B-Schnittstellen. Eingaben und hochgeladene Dokumente sind vertraglich streng vor dem KI-Modelltraining geschützt.

Datenschutz-Gateway (opt-in)

Optionale Echtzeit-Maskierung. Filtert personenbezogene Daten (PII) automatisch auf EU-Servern heraus, bevor Anfragen verarbeitet werden.

Ausfallsicheres Routing

Provider-unabhängiges Modell-Routing (OpenAI, Anthropic, Google, DeepSeek). Fällt ein KI-Anbieter aus, läuft deine Prozess-Pipeline nahtlos weiter.

Methods think ahead. Think along. Think further.

200+ methods. 84+ recipes. Three model slots — ready to steer.

Start Now