AxWise
Cognitive context · evidence-aware decisions · agent and team fit

Give agents the context to solve the right problem.
Choose the right agent or team.

AxWise turns a goal into an evidence-backed execution brief: who the work is for, what outcome matters, what is known or uncertain, and which capabilities the work requires. It returns that context, an execution persona, and a ranked agent or team through a standalone API.

Use AxWise inside your own product or agent stack. Or connect it to Orqaly, where AxWise decision intelligence complements Orqaly's governed execution, monitoring, and delivery.

Open-source cognitive engine
$git clone https://github.com/AxWise-GmbH/axwise-flow-oss.git
AxWise Decision API
Contract v1.0
// GOAL ROUTINGVALUE OF INFORMATION
POST /api/orqaly-axwise/v1/orchestration/decisions

AxWise evaluates ambiguity, evidence sufficiency, consequence, and the value of more information. It chooses direct, evidence-assisted, bounded research, or human clarification before expensive research begins.

DECISION INPUTDOMAIN-NEUTRAL
- Goal: Reduce damage at warehouse handoffs
- Stakeholder: declared, not yet verified
- Evidence: insufficient for execution
- Candidate agents: authenticated Orqaly catalogue

The same contract works for operations, research, sales, services, compliance, or software goals. It does not assume the answer is code.

// IMMUTABLE DECISIONHTTP 201
{
  "routing_mode": "research_assisted",
  "status": "pending_research",
  "research_job": { "status": "queued" },
  "requires_orqaly_authorization": true
}

Every recommendation is advisory. Orqaly revalidates tenant ownership, agent availability, policy, approval, budget, and tool access before execution.

// INTERACTIVE COGNITIVE DECISION TRACE

From vague goal to grounded recommendation

Explore illustrative, domain-neutral scenarios. AxWise decides whether more research is valuable, resolves the customer and ideal executor, ranks existing Orqaly agents, and returns a trust-aware handoff. Orqaly's Consilium and workflow engine act downstream.

ILLUSTRATIVE SCENARIO

Warehouse Operations

Regional distribution · Germany
Goal context: Reduce damage and late departures during shift handoffs without slowing dispatch.

The goal names the symptom, but the problem owner, decision-maker, evidence, and best executor still need to be resolved.

ILLUSTRATIVE EXECUTOR PROFILES
M
Mara
Goal-specific fit
Operations Discovery Lead
Best fit while the customer context and operational facts are still hypotheses.
Fit signals: Stakeholder discovery · Evidence synthesis · Pilot design
L
Leon
Goal-specific fit
Warehouse Process Specialist
Best fit once verified operational evidence establishes the problem and constraints.
Fit signals: Handoff analysis · Damage prevention · Workflow design
AxWise decision trace
Decision trace 0/7● Illustrative trace
// INSPECTABLE EVIDENCE

See what is quoted, inferred, or still unknown

Quote-backed persona fields retain the speaker, source document, exact quote, and character offsets. Select one of the four illustrative persona records, then hover over an extracted field to inspect its source. AxWise keeps those quotes separate from model inference and labels synthetic research as a hypothesis—not verified customer truth.

Exact quote, speaker, and source document retained
Character offsets available for field-level review
Synthetic, inferred, declared, and verified evidence kept distinct
Illustrative source transcriptdoc_transcript_lukas

Interviewer: Lukas, how exactly do you handle raw store layout updates right now?

Lukas: Honestly, it's a completely manual mess.

We use Excel sheets to translate visual store designs in Figma into actual ordering volumes in our SAP ERP.

But maintaining 45 separate spreadsheets in Excel is incredibly labor-intensive and prone to errors.

If we make one typo, we end up over-ordering by 15% and throwing away fresh bakery goods.

Persona evidence [JSON]Structured output
NAME
Lukas Weber
PAIN_POINTSstart_char: 150, end_char: 236
Maintaining 45 separate spreadsheets in Excel is labor-intensive and prone to version-control errors.
WORKFLOW_TOOLSstart_char: 75, end_char: 172
Uses Excel, Figma, and SAP ERP to translate store layouts into physical orders.
BUSINESS_IMPACTstart_char: 245, end_char: 318
Typographical errors lead to a 15% over-ordering rate, causing massive food waste.
// RECOMMENDATION ≠ AUTHORIZATION

AxWise advises. Orqaly decides what may run.

Every AxWise decision requires Orqaly authorization. The illustrative downstream check below shows the responsibility boundary: Orqaly validates tenant ownership, identity, agent availability, approval, budget, and connector permissions before any external action.

ORQALY AUTHORIZATION BOUNDARYIllustrative enforcement
Select an identity and test how Orqaly enforces policy after receiving an AxWise recommendation.
// REFERENCE INTEGRATION · COMPLEMENTARY LAYERS

AxWise intelligence, connected to Orqaly execution

AxWise works independently as a cognitive decision API and can enhance different agentic or workflow products. The Orqaly use case below shows the two products working in synergy: AxWise returns context, evidence, an execution persona, and a ranked agent or team; Orqaly plans, authorises, and runs the work.

Input

Vague Goal

Orqaly sends the goal, tenant context, constraints, and available Agent Hub profiles.

Intelligence

Customer + Executor

AxWise decides whether research is needed, resolves stakeholders, and recommends the best fit.

Authorization

Orqaly Validates

Orqaly checks the tenant, agent, approval policy, budget, and connector permissions.

Execution

Goal-Aware Agent

Orqaly plans and runs the work with AxWise context applied as a goal-specific overlay.

Illustrative digital-twin use case

Veronika Horvat

AxWise can shape a goal-specific CFO execution persona and recommend the matching Agent Hub profile. Orqaly alone activates the agent and grants any authorised, read-only access to finance or communication sources.

Example · Orqaly-executed
Potential Orqaly connectors
  • 📁 Finance / Q2 Planning Drive
  • 💬 Slack History (#finance)
  • 📧 Email correspondence archive
Veronika
Veronika Horvat
Away · Twin Active
Veronika is Out of Office. Queries handled by her Digital Twin.

Hey Veronika, I need the latest Q2 projections for the board meeting. Can you send them?

9:41 AM

CFO TWINHi! Pulling from Q2 Planning. Here is the file and key points:

Q2_Projections_v4.pdf
1.8 MB · PDF
• Base scenario: $2.4M ARR
• Stretch: $2.8M ARR
• Burn reduced 8% via API optim.
9:42 AM
Task Cost: $0.045 | Daily Budget: $98.10
Type a message...
same twin
#finance-ops
3 members
Today
Vitalijs
Vitalijs Visnevskis9:43 AM

@Veronika can you share the updated cash-flow model? I need it for the investor deck by noon.

AW
Veronika's TwinAPP9:43 AM

Veronika is OOO. I found the latest version in her Finance folder:

CashFlow_Model_Q2_v3.xlsx
842 KB · Spreadsheet
Summary: Net positive cash-flow projected starting August. Runway extended to 18 months post-raise.
👍 2🙏 1
Message #finance-ops
// CROSS-DOMAIN COGNITIVE INTELLIGENCE

One decision layer, many kinds of work

AxWise is not limited to software delivery or product management. It can clarify the customer, stakeholder, and ideal executor for operational, commercial, research, healthcare, public-service, and technical goals.

Stakeholder Resolution

Who is this really for?

Turns a vague objective into a structured view of customers, users, buyers, affected stakeholders, desired outcomes, constraints, and unresolved assumptions.

Evidence-Aware Personas

Customer + ideal executor

Produces operational customer and executor profiles with field-level provenance, confidence, quotes, inferences, and explicit working hypotheses when evidence is incomplete.

Agent & Team Fit

Recommendation, not execution

Ranks Orqaly Agent Hub profiles against task fit, customer fit, tools, constraints, and evidence—then returns the reason, confidence, and goal-specific persona overlay.

Decisions That Improve

Outcome feedback loop

Stores immutable decision records and learns from quality, time, cost, customer reaction, and success signals without silently rewriting the evidence behind earlier recommendations.

// OPEN-SOURCE COGNITIVE LAYER

Give every agentic goal grounded context before execution.

Self-host AxWise or embed its API in your own product and agent stack. For governed end-to-end execution, connect it to an orchestration platform such as Orqaly. Deployment control supports your security and governance programme; it does not replace it.