STATUS: OPERATIONAL
ENGINE v1.9.87NODE: PRIMARYALL SYSTEMS NOMINAL
6
6AWAY
ENGINE

REUSABLE APPLIED INTELLIGENCE INFRASTRUCTURE

Intelligence Infrastructure
for Real Products.

Not just model calls. Evaluate. Replay. Simulate. Deploy. Observe. Govern.

Built inside the 6away ecosystem. Designed to be reused outside it.

Currently powering GCP Pro, Coherence Guru, Rotalink, 6degrees, Ritual Guru and the wider 6away ecosystem.

Access EngineTalk to 6awayaccess requires admin key · external builders welcome

THE SHAPE OF AI TODAY

Most AI systems run on hope.

TODAY

Prompt → Model → Hope

  1. 01Prompt
  2. 02Model
  3. 03Hope
6AWAY ENGINEOPERATIONAL

A full lifecycle — measurable at every step.

  1. 01Task
  2. 02Routing
  3. 03Evaluation
  4. 04Replay
  5. 05Simulation
  6. 06Deployment
  7. 07Memory

CAPABILITY PLATFORM

Reusable AI capabilities, not a rebuild every time.

Apps discover, require, and call Engine capabilities without rebuilding the AI plumbing underneath each one. The same routing, budget, retry, and observability machinery covers every capability — including ones added next quarter.

CAP-01 · voice-transcription

Voice Transcription

Transcribe audio with Whisper. Optionally extract structured fields from the transcript.

EXAMPLE USE CASES
  • Language-learning lesson scoring
  • Meeting note extraction
  • Voice-to-CRM contact capture
ENGINE OWNS

Model routing · multipart upload · retries · cost ceiling · usage logging

PRODUCT OWNS

Audio capture UX · transcript storage · pedagogy / output use

/v1/whisper/transcribe/v1/whisper/extract
CAP-02 · discovery-rank

Relationship Discovery

Turn a natural-language search into a structured intent + concept bag, then rank caller-supplied candidate profiles.

EXAMPLE USE CASES
  • CRM smart search
  • Warm-intro recommendations
  • Candidate ranking by fit
ENGINE OWNS

Intent expansion · ranking · schema validation · output sanitisation

PRODUCT OWNS

CRM data · candidate text assembly · UI for results

/v1/discovery/interpret/v1/discovery/rank
CAP-03 · coherence-gcp-state

GCP State Classification

Classify GCP Net Variance into a continuous coherence state (CS / DD / IS / AT / SS / CL / SH / FA / DS) with confidence + direction + phase.

EXAMPLE USE CASES
  • Coherence-aware market tools
  • Trading research surfaces
  • Pattern-detection downstreams
ENGINE OWNS

AI classification · longitudinal memory · schema-strict output · fallback chain

PRODUCT OWNS

Net-variance computation · chart rendering · alerts · the trading decision

/v1/coherence/gcp-state
CAP-04 · company-research

Company Research

Structured company intelligence extracted from web content and open-source signals.

EXAMPLE USE CASES
  • Sales-prep briefs
  • ABM enrichment
  • Investor-tooling backgrounders
ENGINE OWNS

Scraping orchestration · AI extraction · structured output shape

PRODUCT OWNS

CRM persistence · contact-company linking · ranking inside your product

/v1/research/company
CAP-05 · summarisation

Summarisation

Compress free-form text into a structured summary plus key-points array. Eval-handler backed for side-by-side model comparison.

EXAMPLE USE CASES
  • Lesson + meeting recaps
  • Document briefs
  • News digestion
ENGINE OWNS

Model selection · eval-supported quality bench-off · retries

PRODUCT OWNS

Source text · presentation · where the summary lives in the product

/v1/summarise
CAP-06 · contact-enrichment

Contact Enrichment

Extract structured contact information from email, LinkedIn, web, documents, Telegram or WhatsApp content the caller supplies.

EXAMPLE USE CASES
  • Lead-capture pipelines
  • CRM auto-fill
  • Inbox-to-contact extraction
ENGINE OWNS

Source-specific prompts · schema validation · output sanitisation · per-source routing

PRODUCT OWNS

Source data · contact storage · dedup · ownership rules

/v1/enrich/v1/enrich/email/v1/enrich/linkedin/v1/enrich/web/v1/enrich/document
CAP-07 · observations

Observations (App → Engine)

The reverse channel. Apps periodically send 'this is what happened' under a registered domain adapter — recommendation accepted, follow-up completed, ritual finished, habit logged. The Engine validates and persists; outcome and correction land alongside to become evidence.

EXAMPLE USE CASES
  • Tell the Engine which recommendations the user actually accepted
  • Record the lifecycle of a ritual / lesson / workout / outreach action
  • Mark which AI-authored outputs the user corrected
ENGINE OWNS

Adapter registry · event validation · workspace-scoped persistence · admin observability

PRODUCT OWNS

Which signals to send · payload shape inside the adapter contract · when to fire

/v1/observations/v1/adapters
CAP-08 · platform-governance

Model Routing · Evaluation · Replay · Deployment Governance

Capabilities run through a governed chain as they mature onto it: provider routing, evaluation against alternative models, replay against historical traffic, and shadow / canary deployment.

EXAMPLE USE CASES
  • Ship AI features without prompt-and-hope
  • Compare a new model on real workload before flipping production
  • Roll back instantly when quality degrades
ENGINE OWNS

Provider routing · fallback · workspace budget · per-call observability · canary auto-stop

PRODUCT OWNS

Nothing — these are infrastructure-level guarantees every consumer inherits for free

/v1/status/v1/capabilities

ECOSYSTEM FEEDBACK LOOP

Apps consume capabilities. Apps send observations back.

The loop is the point. Real workload validates capabilities; observations turn into evidence; evidence sharpens the surfaces every app consumes. Deterministic today; the learning layer is under construction.

N-01
App
Real user action happens.
N-02
Signals
The app describes what happened.
N-03
Observations
Sent to the Engine as a structured event.
N-04
Evidence
Observation + Outcome + Correction.
N-05
Understanding
Funnels, rates, patterns — deterministic.
N-06
Better Capabilities
The Engine's surfaces sharpen over time.
N-07
Better Apps
Apps consume the sharper surfaces. Loop closes.

Every application does three jobs.

JOB-01
Revenue

Apps own their customer, their product, their pricing. The Engine never gets between an app and its users.

JOB-02
Validation

Real workload validates Engine capabilities. Production traffic exposes what evals can't see.

JOB-03
Engine Improvement

Observations from real usage become the evidence the Engine learns to understand — deterministically first, intelligently later.


DOMAIN ADAPTERS

One contract per domain. One Engine for all of them.

Each product connects through a domain adapter — a small declarative bundle that tells the Engine what signals the product emits and what privacy posture applies. The Engine doesn't care that one app is relationship intelligence and another is daily rituals; it sees the same observation shape across all of them.

WHAT AN ADAPTER DECLARES

F-01Signals
F-02Entities
F-03State ontology
F-04Recommendation actions
F-05Feedback events
F-06Privacy boundaries
ADP-01 · coherencega
Coherence Guru

Relationship and meeting outcomes. The first adapter wired in production.

8 signals·3 entities
First adapter wired (v1.79.12)
ADP-02 · gcp-proga
GCP Pro

Market coherence-state predictions and the actual subsequent behaviour.

3 signals·2 entities
ADP-03 · learnlanguagebeta
LearnLanguage.guru

Lesson outcomes — answer submissions, mastery transitions, session lifecycle.

3 signals·3 entities
ADP-04 · fitlogcandidate
Fitlog

Workout outcomes and load progressions — sanity check for non-conversational domains.

3 signals·3 entities
ADP-05 · ritualbeta
Ritual Guru

The densest behavioural-state stream: rituals, meditation, reflection, mood / energy / focus / sleep / HRV, habits.

10 signals·5 entities
Densest observation stream

OBSERVATION → EVIDENCE

Observation is what happened. Evidence is what it means.

An observation is the raw event: a recommendation accepted, a habit completed, a ritual finished. Evidence is what that event becomes once the outcome arrives — and once any correction the user made gets attached to it. The Engine accumulates evidence; aggregation comes first, intelligence comes later.

THE EQUATION
Observation+Outcome+Correction=Evidence

Deterministic today. The learning layer is under construction; AI enters in a future, named phase.

RULE-01
No uncontrolled self-learning

Today the Engine accumulates evidence. Aggregation and pattern discovery are deterministic and explicit. The learning layer is under construction; AI enters in a future, named phase.

RULE-02
No cross-workspace sharing

Every observation is workspace-scoped. Adapter declarations pin sharedAcrossWorkspaces = false. Cross-domain inference, if it ships, gets its own consent surface.

RULE-03
Apps stay in control

Each product owns its CRM data, its UX, its decisions. The Engine never reads an app's database, never renders product UI, never persists caller-owned business data.


GOVERNANCE · SAFETY · SUBSTRATE

The substrate that keeps the loop safe.

This is the substrate capabilities run on. Provider routing, evaluation, replay, simulation, shadow-then-canary deployment with auto-stop. Memory, a status contract, a typed SDK.

MOD-01

Multi-Provider Routing

Route across Claude, GPT, Gemini, Infercom, MiniMax and local models without changing application code.

claudegptgeminiinfercomminimaxlocal
MOD-02

Evaluations

Compare models on structured tasks. Measure quality, latency, reliability, schema validity and cost — before production.

qualitylatencyreliabilityschemacost
MOD-03

Replay & Regression

Replay real production requests against new models. See exactly what changes before deployment.

requestcandidatediffverdict
MOD-04

Simulations

Test routing strategies against historical traffic. Estimate cost, latency, reliability and fallback behaviour without touching production.

historicalpolicyestimatereport
MOD-05

Shadow & Canary Deployments

Run a candidate model alongside the incumbent. Promote only when the candidate proves itself on real workload.

shadowcanarypromoteroll-back
MOD-06

Auto-Stop Safety

Canary deployments freeze themselves when divergence, error rate, or cost cross declared thresholds. No operator action required.

thresholdfreezealert
MOD-07

Memory

Track behaviour over time. Understand state persistence, transitions, volatility and provider disagreement — without giving memory control of routing.

persistencetransitionsvolatilitydisagreement
MOD-08

Status API

App-facing health + capability contract. Workspace-aware. Surfaces degraded flags so callers can render fallbacks before failure.

healthcapabilitiesdegradedrate-limit
MOD-09

SDK

Hand-written TypeScript client — no zod / drizzle dependencies. Typed helpers for stable contracts. Copy-pasteable into any app repo.

typedretrieserrorsdiscovery

FOR BUILDERS

Plug in once. Use every capability.

The Engine is provisioned per workspace. Same API key serves every capability. New capabilities show up in your catalog the moment they ship.

  1. 01
    Create a workspace
    One-time setup. Sets the budget + provider policy.
  2. 02
    Get an API key
    Workspace-scoped X-API-Key. Same header every /v1/* endpoint uses.
  3. 03
    Discover capabilities
    GET /v1/capabilities → live catalog, workspace-aware.
  4. 04
    Call through the SDK
    engine.transcribeAudio(...) / engine.discoveryRank(...) / postTask<T>.
  5. 05
    Send observations
    engine.recordObservation(...) — tell the Engine what happened. Best-effort, never blocks.
  6. 06
    Monitor evidence + reliability
    Workspace dashboards, evals, replay, shadow deployments, observation rollups (admin surface).
Access EngineTalk to 6awayexternal builders welcome

PHILOSOPHY

Intelligence requires governance.

Most AI products are built around models.
6away Engine is built around decisions.

PILLAR
Measurement
PILLAR
Comparison
PILLAR
Deployment
PILLAR
Observation
PILLAR
Improvement

…before trust.


ECOSYSTEM

Currently powering.

NODE-01
GCP Pro
NODE-02
Coherence Guru
NODE-03
Rotalink
NODE-04
6degrees
NODE-05
Ritual Guru
NODE-06
LearnLanguage.guru
NODE-07
Echo.guru
NODE-08
DreamDiary.guru

…and future realities inside the 6away ecosystem.


ENTER THE ENGINE

Not an AI model.

A system for understanding, testing and deploying intelligence.

Built inside the 6away ecosystem. Designed to be reused outside it.

Access EngineTalk to 6away