WHISPER / INITIATIVE UNDER DEVELOPMENT

TRULY
HUMANAUTOMATION.

Whisper is being developed to turn everyday conversations into completed, verifiable outcomes—through permitted applications, devices and services, with authority you control.

Explore the design Request information
WhisperOptional control plane Simulation
ACTIVE OUTCOME · FRIDAY

Friday has one hard constraint.

Your 4:30 call cannot move. This example connects a message, calendar, location and flight options.

9signals resolved1human decision retained
9:415G  ◉
WhisperiMessage · design example
Protect my 4:30 call and get me to Melbourne tonight.

Your 4:30 call cannot move. This example connects a message, calendar, location and flight options.

UNDERSTANDFriday has one hard constraint.

1/4
iMessage
01 / WHAT WHISPER IS

An agentic operating layer for everyday life.

The proposed operating layer combines personal context, bounded planning, device and service execution, and independent verification. The goal is less life administration, with the important decisions and permissions still in your hands.

01

No app required

The intended experience uses text, calls and voice notes through approved channels, with an optional dashboard for inspection and control.

02

Uses devices like you do

The design combines supported APIs with isolated computer or phone operators, using explicit permissions for screen, audio and local software.

03

Finishes life admin

The proposed specialists coordinate appointments, purchases, negotiations, forms and service providers against observable completion conditions.

04

Its own email

A planned dedicated address separates authorised registrations and merchant threads from the personal inbox, with identity and send controls.

05

Maintains an active state

Permission-aware temporal memory is designed to retain relevant commitments, preserve contradictory evidence and identify material changes.

06

Acts inside your authority

The authority design binds scope, expiry, spend and consequence to each action; independent external-state read-back is required for completion.

Conversation-first designText and voice through approved channels.

Adaptive agent executionSpecialists re-plan across devices, services and changing conditions.

Independent completion proofCompletion requires the external state to match the contract.

02 / NO APP REQUIRED

Text it. Call it. Keep moving.

The experience is designed around one permission-aware task state across text, voice and approved messaging channels, with context and control carried between them.

NO NATIVE APP INTERFACE

Whisper meets you where conversation already happens.

The intended experience supports text, calls and voice notes through approved channels. Reactions acknowledge context; consequential actions need explicit, action-bound approval.

9:415G  ◉
WhisperiMessage◉›
Can you handle my Friday night? Dinner for six after the show, then rides home.
I found three restaurants within a six-minute walk, checked everyone’s preferences and held Luma at 10:00 PM. The booking needs one approval.
WHISPER PLANDinner + rides coordinated
Guests
6 calendars aligned
Reservation
Luma · 10:00 PM
Authority
One tap required
Whisper is ready to act
iMessage
03 / DEEP DEVICE EXECUTION

It uses software the way a person would.

The integration design covers email, calendars, messages and explicitly permitted screen, audio and location context. It prefers supported APIs, with isolated interface operators for authorised legacy workflows and human handoff at authentication or platform boundaries.

Whisper OperatorVirtual computer + phone
Design session
whisper.example/session/health
ILLUSTRATIVE DELEGATION

Find and book an in-network doctor

Thursday afternoon · within 8 km · existing insurer

Understanding
GmailHuman-style interface operation

Context resolved across permitted sources

Whisper separated hard constraints from preferences and located every credential, record and conversation needed for this outcome.

Coverage verified3 providers comparedIntake form preparedCalendar protected
OPERATOR DECISION SUMMARY

What does success mean?

Resolve the real outcome before touching a tool.

Authority
Scoped execution
Exposure
Credentials isolated
Memory
Outcome + proof
Task-scoped authority · reversible where possible
04 / DEDICATED AGENT EMAIL

Give the work an inbox of its own.

The planned agent inbox separates operational communication and supports scoped thread handover. A CC provides context, not authority to accept terms or send sensitive information; mailbox identity, retention and approval rules remain explicit.

10:125G  ◉
M Search in mailmia@whisper.exampleM
PrimaryWhisper Email · 3 priority

Whisper triaged 14 messages3 need action · 8 filed · 3 monitored

WHISPER EMAIL

An agent-owned address. A quieter personal inbox.

The planned address supports permitted account administration and merchant communication. Thread access and external-send authority are separate permissions.

05 / AUTONOMOUS LIFE ADMIN

Real work, carried through to reality.

The intended workflows connect research, conversation and software to external service providers. Submission, provider acceptance and actual completion are different states; unknown or contradictory results must remain open for reconciliation.

WhisperLife operations
Synthetic context
OUTCOME ORCHESTRATION

Life fits together, not into separate apps.

Doctors, DMV appointments, restaurants, flights and road trips are planned against calendars, coverage, location and the people affected.

AGENT PLAN
ACTIVE DETAIL · 01

Coverage checked

Whisper recovered the people, timing, preferences, policies and previous conversations relevant to this outcome.

Evidence stage1/4Open loops3Human inputNone

COMPLETION PROOFAppointment + calendar agree

06 / MEMORY + PROACTIVITY

It remembers the promise, not just the prompt.

The memory design retrieves relevant, fresh and permitted evidence rather than treating every past message as current truth. Proactivity is opt-in, with quiet hours, notification limits, inspectable inferences and separate approval for consequential actions.

CONTEXTUAL MEMORY + PROACTIVITY

The right intervention, before the open loop becomes a problem.

Whisper remembers commitments, watches permitted signals and surfaces only what has become consequential.

3:465G  ◉
Whisper · MessagesDetected from permitted context

WHY THIS MATTERS NOWYou promised Sarah the risk note.

Detected
SARAH · 4 DAYS AGO
Could you send the final risk note before the board brief?
You: “Yes — I’ll send it when the figures are final.”

READY ATTACHMENTBoard-risk-note-v7.pdf

FINAL

Whisper linked the promise, final file and tomorrow’s dependency.

1Recall2Reason3Act

The file is complete, but the conversation has been quiet for four days and tomorrow’s board brief depends on it.

Messages
07 / WHISPERPRIME / DUAL-USE

The same intelligence layer. Mission scale.

WhisperPrime proposes a separate deployment profile for authorised intelligence analysis, government coordination, security and critical infrastructure. It combines source-governed queries, evidence-linked assessments and named human release within deployment-specific sovereignty and assurance controls.

WhisperPrimeSovereign mission intelligence
MISSION DESIGN SIMULATION
FEDERATION6 federated domainshealthyEVIDENCE127 lineage recordshealthyACTIVE STATE42 live observationshealthyAUTHORITY1 command gateretained
Resolve an emerging maritime riskFuse sovereign, partner, sensor and open-source claims without moving protected holdings outside their governed domains.Observing
MSN-04B / MARITIMEFederated mission fabric6 sovereign domains · query at source
WhisperPrimeEntity resolutionPolicy evaluationAgent coordination127 lineage records
OBSERVE42 observations admitted

Clock drift normalised; duplicate reports collapsed without discarding provenance.

ADMIT-7F2 · 6 policies passed
SOURCE + POLICY INSPECTOR

Maritime OSINT

STIX/TAXII + typed claims

Live state
18 corroborated
Admitted objects
31 entities
Handling
OPEN · REL PARTNER
Custody
Owner-controlled
Interface
Delta / S3 query-at-source
Query mode
Read-only claims
CURRENT MISSION RESULTShared assessment prepared with two unresolved identity residualsADMIT-7F2 · 6 policies passed

Purpose-bound query enforcedNo source grants broader access than this mission purpose requires.

Sovereignty includes inference

Query-at-source alone is insufficient. Specify data residency, model and embedding location, key custody, administrator access, support paths and log placement. Derived intelligence retains the source's handling and releasability constraints.

Federation requires semantic agreement

Version entity and event schemas; reconcile identifiers, units, timestamps and lineage. Enforce purpose, role, mission and time attributes at each source gateway; handle policy conflicts and disconnected operation explicitly.

Assurance is deployment-specific

ABAC, mTLS, STIX/TAXII, OGC and OPC UA are design choices, not proof of accreditation. Keep OT access read-only until independently approved, disclose inference residuals and require named human release of consequential mission actions.

Federated interoperabilityModern and legacy platforms connect without collapsing data boundaries.

Mission-governed autonomyPurpose, role, policy and time bound every agent action.

Evidence-linked intelligenceClaims retain source, confidence, transformation and handling rules.

Cross-agency executionStakeholders coordinate through shared outcomes and accountable gates.

08 / GOVERNED AUTONOMY

More capable. Still yours.

Task-scoped access

The proposed gateway leases credentials and tools only to a bounded outcome.

Consequence-aware approval

Purchases, binding commitments and sensitive changes remain gated.

Control at any moment

Pause authority, revoke connections, delete memory or stop execution.

Proof, not promises

Completion is specified to require external-state verification and an inspectable record.

09 / TECHNICAL ARCHITECTURE

Intelligence proposes. The system enforces.

Six connected engineering layers define how Whisper should understand an outcome, retain context, recover interrupted work, constrain authority and verify the result. Each layer has an explicit contract and trust boundary.

Define the state that counts as finished.

Input

User objective, parties, constraints and permitted sources

Output

Versioned outcome + acceptance predicates + authority envelope

Represent the outcome as structured entities, hard constraints, preferences, deadlines, budget and observable acceptance conditions. Bind approvals to the actor, provider, amount, recipient, purpose, action revision and expiry.

Maintain explicit states: proposed, authorised, executing, awaiting external response, uncertain, verified, blocked, cancelled and requiring review. An attempted tool call, fluent reply or generated receipt cannot close an outcome.

Track dependencies as a task graph. Serialize writes to the same external resource; allow independent research in parallel. A specialist receives a narrower mandate and may not increase its parent's scope, spend or delegation depth.

Clarification precedes any ambiguous consequential action

The proposed asset is the execution and evidence layer.Defensibility must come from lawful domain data, tested adapters, calibrated outcome evaluation and adoption. Chat interfaces, agent swarms and familiar protocol names alone do not establish a moat.

10 / COMPLETION + FAILURE

Trust includes the ability to stop.

Explore a verified result, malicious instructions, expired or revoked authority, a changed quote, a lost acknowledgement and conflicting evidence. The control laboratory makes the proposed execution rules visible.

Outcome control laboratoryControl simulation
OUT-104 · REPAIR BOOKING

Ready to prepare

OUT-104 · synthetic repair booking · no external connection

Committed writes
0
Approved amount
None
Completion
Withheld
Inspect the execution ledger (1 events)
  1. 01

    OUT-104 · synthetic repair booking · no external connection

11 / VALIDATION + RELEASE

Capability needs evidence.

Whisper's engineering and investment case depends on reproducible outcomes, measured failure modes, lawful data access and useful economics. The validation plan tests the complete outcome lifecycle, from permission and execution to recovery and external confirmation.

Outcome quality

Verify the external result

Test the agreed identity, amount, destination and timing against provider records. Track false completion, unresolved work and human escalation.

Control integrity

Challenge the authority boundary

Exercise malicious instructions, expired approvals, revoked access and uncertain writes. Measure whether the system blocks, reconciles or requests review.

Practical value

Measure the work saved

Count cost per verified outcome, elapsed time, human minutes and interruptions, including failed attempts, recovery and support.

Evaluate the complete system, including its failures.

Measure a pinned model + harness + adapter + policy combination on held-out tasks, with independent external-state graders. Publish the task mix, sample size, repeated runs, confidence intervals, intervention rules, version manifest and failure taxonomy. General coding or browser benchmarks are supplementary; they cannot establish reliability in life administration or mission workflows.

EvaluationMeasureRequired challenge
Outcome correctnessExternal acceptance predicates; false completion rate; pass@1 and repeated-trial pass^kMatched tasks against human work and a single-agent baseline; include failures and escalations
Authority integrityUnauthorised writes, scope expansion, expired approvals and revocation latencyDirect and indirect injection; malicious peer agents; cross-tenant and cross-person leakage
Recovery + reliabilityDuplicate effects; checkpoint recovery; blocked and uncertain outcomesCrash before/after writes; lost acknowledgements; stale quotes; provider and layout drift
Memory + privacyRetrieval accuracy, stale-fact use, correction and deletion coverageContradictory records; revoked sources; embeddings, logs, caches and backup expiry
Economics + usabilityCost per verified outcome; p50/p95 latency; human minutes and interruption rateInclude failed attempts, model/tool cost, operator support and compensation; separate merchant spend
Prime assuranceCross-domain leakage, releasability decisions, evidence residuals and named releaseIndependent tenant fixtures; denied queries; inference leakage; analyst and operator review
01

Sandbox validation

Synthetic identities and controlled providers. Exercise recovery, isolation, approvals and outcome verification before connecting real accounts.

Proposed release gate
02

Bounded pilot

Start with scheduling and merchant follow-up for consenting adult users. A signed test plan sets workload-specific thresholds, cohort size and stop conditions before the trial; sensitive writes retain human approval.

Proposed release gate
03

Operational release

Require approved channels, independently reviewed security and privacy, measured outcome economics, incident ownership and tested recovery. Separate payment and health-administration authorisation from general access.

Proposed release gate
04

WhisperPrime validation

Use separate tenancy, model hosting, key custody and assurance. Customer accreditation and cross-domain controls must precede classified or critical infrastructure use; consumer success does not transfer assurance.

Proposed release gate
Data, accountability and commercial diligence

The deployment contract must identify the data controller and processors, purpose and lawful authority, regional storage and inference paths, subprocessors, retention, incident response and audit access. Health administration is not diagnosis; legal and financial decisions remain with appropriately authorised people. Call recording and agent identity disclosure need jurisdiction-specific review.

Proactivity must be opt-in, purpose-bound and easy to mute. Define quiet hours, notification budgets, risk thresholds and confirmation for material consequences. Ranking should make sponsorship and commissions visible; inferred needs must not become undisclosed advertising or unsolicited purchases.

An investment case requires lawful rights to training and evaluation data, a reproducible prototype, engineering ownership, delivery milestones, platform dependencies, support costs and customer evidence. Approved integrations and measured net value must support revenue assumptions.

12 / RESEARCH + COMPETITIVE CONTEXT

The layer that carries intent through to proof.

Whisper connects personal context, explicit authority and verified completion in one outcome lifecycle. It is designed to work with foundation models, specialist agents and existing software, carrying the task's constraints, ownership and evidence between them.

WHISPER'S DISTINCTIVE DESIGN

A shared outcome lifecycle for a fragmented AI ecosystem.

A repair can involve messages, a warranty document, a merchant, a payment and a calendar. Each system sees part of the work. Whisper's contribution is to carry the whole commitment: what was requested, what was authorised, what happened and what evidence closes it.

The architectural distinction is the combination of permission-aware context, bounded delegation, durable commitments and independent verification. This creates an operating layer that can use new models and specialist agents while preserving the user's control.

01

One contract, across systems

The objective, hard constraints, acceptance conditions and accountable owner travel together as work moves between a conversation, a specialist and an external provider.

02

Context with permission attached

Memory retains source, time, uncertainty and handling rules. The action gateway checks current authority immediately before a consequential write.

03

Recovery tied to real commitments

An interrupted workflow reconciles what the provider actually did before retrying. A changed price or recipient triggers renewed approval.

04

Completion grounded in evidence

An external read-back tests the agreed result. The same record supports user review, failure analysis and domain-specific improvement.

Where Whisper fits

Read each row as a complementary role: the existing capability, then the outcome-level responsibility Whisper is designed to connect to it.

AI ecosystem roles and Whisper's complementary architecture
Existing AI layer + sourcesWhat it contributesWhisper's complementary role
Personal agentsConversational access to tools, personal context and everyday tasks across channels and devices.A single outcome contract carries budget, permissions, dependencies and completion evidence through a multi-service task. The conversation remains the entry point; the contract coordinates the work.
Models + tool useReasoning and tool-assisted search, code execution and custom functions.Select a model for each bounded task while keeping authority, source provenance and acceptance checks outside the model. A model change preserves the outcome's constraints.
Durable agent infrastructurePersistent sessions, execution harnesses, isolated sandboxes and credential boundaries.Carry that durability into real commitments: checkpoint the approved action, reconcile uncertain provider state and resume without repeating a purchase or booking.
Specialist agentsSpecialist software work and text-native access to always-on agents.Coordinate specialists around one user outcome. Give each a narrower mandate, serialize competing writes and retain ownership when work crosses domains.
Enterprise agent platformsEnterprise agent governance, connector and data policies, identity controls and audit visibility.Connect approved enterprise workflows to explicit outcome contracts and external-state verification. WhisperPrime applies the same lifecycle within separate mission, source-handling and release boundaries.
Agent + payment protocolsInterfaces for agent task exchange, tool access and explicit payment authorisation.Bind each handoff to the actor, purpose, amount, resource and expiry. Test the adapter and read back the resulting state so protocol messages become accountable steps in a larger outcome.
Domain improvement loopsPractitioner feedback, production traces and correction-derived evaluations for specialised work.Use outcome ledgers to turn domain failures into regression tasks. Experts review corrections, and model or adapter updates pass the same acceptance and authority tests before release.
WORKED DESIGN EXAMPLE

One repair. Several systems. One accountable outcome.

  1. Define

    Use permitted fault and warranty evidence to specify the repair, spend ceiling, preferred times and required confirmation.

  2. Authorise + coordinate

    Approve the exact provider, price and time. Carry that mandate through the booking, merchant response and calendar update.

  3. Reconcile + verify

    Read back the provider's booking ID and agreed details. Resolve lost acknowledgements before retrying; request renewed approval if the quote changes.

The value is a completed obligation with an inspectable record and fewer manual handoffs. The control laboratory above demonstrates the approval, recovery and verification logic.

Research behind the architecture

Source review: 6 October 2026. The architecture sections above specify the contracts and trust boundaries for these roles.

WHISPER / LUPOTEK INITIATIVE

Delegate the outcome.
Stay in control.

A conversation begins the work. Clear authority, coordinated execution and verifiable completion carry it through.

Engage with Whisper Initiative notices and disclaimers