The EVO knowledge base.

EVO Alpha is an AI workspace for Mac that connects a goal with the work needed to finish it: conversations, selected files, evidence, decisions and results.

A saved Work gives you a place to inspect progress, review a proposed action and continue with relevant context, instead of rebuilding the brief from scattered messages.

For a website change, keep the requirement, reviewed file and preview checks beside the remaining questions.

You choose the sources, processing mode and supported actions; a remembered goal does not authorize execution.

The Mac development build demonstrates these foundations. Public downloads remain closed, and individual capabilities have their own availability limits.

Yes. EVO combines a limited recent conversation with saved Work context and approved memories, so durable preferences can remain useful beyond one exchange.

Only selected, relevant material within the current context limit is included. Saved memory and the complete conversation archive serve different purposes.

An approved preference to compare primary sources can inform a new research brief without replaying the conversation where you first expressed it.

Review saved items and ask EVO to correct or stop using them. Restored memories need confirmation again.

This is limited recall, not automatic understanding or retrieval of every old chat. A missing item may need to be selected or supplied again.

Selected local requests can run with a compatible installed model. This does not make search, account services or every feature offline.

Swift has real Apple Silicon tests, with unresolved accuracy and incomplete-answer failures. Sage remains Preview.

Final hardware requirements and public model downloads are pending. Proposed plans are on the pricing page; checkout is closed.

No. Adding a reference file to the Mac workspace does not automatically upload it or make it a shared memory.

Storage, selection for a task and cloud processing are separate choices. A conversation receives supported content you have selected within that task’s scope.

You can keep a project brief locally, then choose an appropriate extract for a specific comparison.

Review selected material before sending and choose the processing mode. Manage reference files separately from memories and conversation records.

Supported formats and extraction limits vary. Removing a local file does not recall a copy already sent elsewhere or erase separate backups.

macOS is the first product focus. The download page also provides Windows, iOS and Android destinations so you can follow the platform relevant to you.

The current product demonstrations come from the Mac development build. Mobile continuity is a planned extension of the same work-focused experience.

The intended journey is to capture a request on a phone and return to richer work on Mac.

Choose a platform manually if the website’s device suggestion is wrong.

macOS, Windows, iOS and Android are all in development. No public installer is available on any platform. A platform listing is not evidence of a completed app, matching features or a release date.

Search can identify candidate sources, but a search snippet is not a verified page. Open and check the source before relying on an answer.

The new inline Evidence Layer remains internal. Search, page capture and final synthesis have not yet passed one complete current-source journey.

The Mac development build can read selected material, use supported tools and prepare changes in built-in apps for you to review.

Available actions have a defined target and scope. Supported browser inspections and application changes follow their own controls.

EVO can turn selected task information into a proposed change; you inspect it and check the saved result after approval.

Choose permissions, review consequential actions and use Stop to prevent further supported work.

This is not unrestricted control of every Mac app or website. This public website does not operate your computer, and public App access is not open.

Compare the proposed Free, Core, Pro · 5x and Studio · 20x plans by working capacity and usage, rather than assuming a higher plan makes every answer better.

The multipliers describe relative cloud allowance against Core. Local usage and the number of simultaneously active Works are separate plan dimensions.

Someone who runs frequent research may need a different allowance from someone mainly using local text tools.

Review the current plan comparison and future purchase terms before choosing; existing EVO memberships are not silently converted.

Pricing is proposed and checkout is closed. Final allowances, billing periods, taxes and renewal terms must be confirmed before purchase becomes available.

Proposed prepaid points cover eligible cloud use beyond the relevant plan allowance. They are service credits, not cash or a transferable currency.

A confirmed account balance and usage record must support any displayed deduction; returning from a payment page alone cannot establish a balance.

The intended use is extra eligible work during a busy period without treating points as a bank account.

Review eligible services and the deduction order before buying; check actual usage in your account when the service is available.

Purchases are closed. Expiry, refunds, taxes and final deduction terms are not yet a live commercial offer.

Public downloads and updater feeds are closed. You can submit a Mac preview application; it does not guarantee access.

Signing in does not unlock a download. Installation instructions, supported hardware and verified public update packages will be published with a qualified release.

EVO gives you separate controls for selected files, memory, cloud sharing and supported actions, alongside an encrypted offline backup option in the Mac development build.

These controls let you decide what a task may use and keep an inspectable history of relevant choices.

You can retain a local reference document while sharing only the supported material selected for a particular task.

Review data choices before sending, revoke reusable permissions and manage copies and backups deliberately.

Backup encryption is not encryption of the entire running workspace. No blanket privacy, end-to-end encryption or compliance certification is claimed.

The website reuses the existing EVO account service when Google sign-in is available, keeping account access connected to the EVO identity you already use.

Sign-in preserves the supported account destination. Product browsing and the optional Alpha access request do not require an account.

You can explore a workflow first, then sign in to view account information when that service is available.

Review the consent shown before continuing; EVO does not ask you to put your Google password in a conversation.

Website sign-in is separate from native App activation. It does not grant downloads, a paid plan or a balance that has not been confirmed.

Genesis Evo Technology LLC is identified as the operator in the existing EVO company and legal information. The contact page provides the relevant support and inquiry routes.

Use product questions to describe a workflow; use the business route to explain deployment, data and operational requirements.

A team evaluating document analysis can share its general requirements before proposing any access to sensitive records.

Choose what to disclose and use the listed contact route rather than putting passwords or private account details into a public request.

An inquiry is not a service agreement, guaranteed response time, enterprise certification or promise that a requested integration is already available.

Yes. The Mac development build connects a selected website file to a conversation, a reviewable replacement and a preview workflow.

Choose one saved file, explain the change, inspect the proposed complete file and run the available checks before explicitly applying it.

You could revise a page’s call to action, then build and preview the result at desktop and mobile widths.

You select the file, separately consent to cloud sharing and explicitly approve applying a reviewed change. Inspect the result; applying a file does not publish it.

This path currently handles one HTML, CSS or JavaScript file up to 6 KB. Public hosting is not open; multi-file autonomy and real-model coding quality need further qualification.

Notes, Todo and other built-in application actions are under internal development. A valid proposal is not proof that a change was applied.

The latest local Notes journey retained a proposal but did not reach a complete approved save. These actions are not yet publicly available.

EVO Mail brings an inbox, drafts and message organization into a dedicated app, with separate choices for AI reading, reply help and sending.

The development foundation covers internal delivery and review of the actual recipients, content and attachments before a send.

The intended workflow is to select a message for help, review a proposed reply and independently decide whether to send it.

Mailbox reading, cloud sharing and sending are separate permissions: permission to read is not permission to send. Signing in with Google does not grant access to Gmail.

Real mail service, Internet delivery and Gmail linking are not publicly available. Operational recovery, account verification and external-mail security still need qualification.

The Mac development build can load a rendered page and preserve desktop and mobile-size screenshots alongside page structure and recorded findings.

This captures the result of the page loading, rather than treating its original HTML as proof of its final appearance.

An inspection can show a narrow-screen overflow or a small control with the page, viewport and captured evidence attached.

Choose the page and inspection scope. Cloud review of selected screenshots requires a separate data-sharing choice.

The published example demonstrates browser capture and rule findings. It does not qualify model visual judgment, every interaction, logged-in pages or full accessibility compliance.

No. Voice interaction starts through explicit controls and requires microphone permission; typing remains available.

The development flow separates a voice session from permission to perform an action. Stopping voice and stopping supported work have distinct effects.

A spoken request can express what you want, but a proposed message still needs its applicable send review.

You choose when to start or stop the microphone session and can continue using text.

Voice is still in development. Service availability, public allowances and real member usage require separate validation before release.

Optional approximate location is being developed to make relevant assistance more useful, while keeping location permission separate from conversation sharing.

Device-provided context can inform a selected task; a network address alone is not treated as proof of where you are.

A nearby-help request could benefit from a city you confirm instead of a location guessed from your connection.

Choose whether to provide location, use it in a conversation or request weather, and withdraw consent when you prefer.

Real location and weather behavior still need device validation. This is not continuous tracking, reliable VPN detection or an available background travel-notification service.

A Work connects the conversation to a goal, constraints, evidence, proposed actions and recorded outcomes, making it possible to inspect what actually happened.

Chat text can explain a plan; a saved result or approval record can establish a different fact about its execution. EVO keeps those roles separate.

A reply saying “updated” is different from a reviewed file change with a saved result and a preview still to check.

Reopen the Work, inspect its current state and choose the next step you want to run.

Persistence does not automatically recover missing evidence, run in the background or make every completion claim correct.

EVO can keep the saved goal, constraints, recent discussion, available evidence, action history and remaining verification around a Work.

Reviewed continuation can reuse selected previous tool results and current saved action outcomes, while excluding changed or unavailable sources.

After a website edit, return to the applied change and see that a mobile preview still needs checking, instead of assuming the entire task is finished.

Inspect the checkpoint and choose what belongs in the next run; you can change the goal or supply updated material.

The stored state covers supported, recorded activity. It is not a live model of every app, file or event in your life.

EVO uses limited recent conversation, the selected Work and approved memory selected for the task, rather than sending the entire archive on every request.

Supported search looks within material already available to the current task. A reviewed continuation can add relevant prior results with their sources.

To revisit a requirement from an older project, reopen that Work or provide the relevant excerpt instead of expecting every old message to be present.

Select the project, correct a missing reference and review what context is being used.

Universal semantic search across all conversations is not a qualified capability. Relevance can be missed, and a long saved history does not mean unlimited model context.

EVO separates producing an answer from meeting the Work’s agreed success conditions, so remaining checks can stay visible after a response ends.

Where supported, completion review connects the requested outcome to actual evidence and asks you to inspect unresolved limits before accepting it.

A supplier shortlist may be written while one important source still needs confirmation; a website file may be saved while its mobile behavior remains unchecked.

Define the result you need, review the evidence and decide whether the remaining limitations are acceptable.

Not every task has an automatic outcome check. Real-world effects and subjective quality can still require your judgment or additional testing.

A successful tool result should count as evidence of that operation, not proof that the whole task is complete.

EVO’s supported workflows distinguish a proposed change, an applied change and an outcome that has been checked against the original request.

Saving a new button label proves the file changed; it does not prove visitors understand it or that the button works on mobile.

Inspect the saved result, identify the unmet condition and request the next focused check or correction.

The system can preserve this distinction, but model judgment may still miss a requirement. Important outcomes need direct verification.

EVO keeps source timing and saved state distinct from present-day truth, and reviewed continuation excludes certain changed or time-sensitive results until they are checked again.

A previous web observation is not automatically a fresh observation. A changed selected file or application result can invalidate its earlier context.

Returning to a price comparison should trigger new source checking rather than treating last week’s price as today’s.

Provide updated material, review source dates and explicitly continue the checks you need.

A capture date does not establish when the publisher updated a page. EVO does not continuously refresh all saved information in the background.

Reopening saved work does not itself run an action. A new run uses the permissions and selected material valid for that continuation.

Some eligible permissions may be reusable; changed sources, cloud sharing and consequential actions have their own renewed review requirements.

You can inspect a previous result without rerunning it, then choose the next check and review any new action it proposes.

Review the continuation, edit the next request and send when ready. You can revoke reusable permissions.

An old approval is not unlimited future authority. Stop does not reverse completed effects, and uncertain outcomes may need reconciliation before retrying.

Short-term context helps with the current exchange. Approved longer-term memory preserves selected facts or preferences worth using beyond that exchange.

Recent conversation, saved Work state, reference files and memory are separate sources with different selection and retention rules.

Today’s temporary deadline belongs to the task; your confirmed preference for concise summaries may be useful in later work.

Review what is saved as memory and ask for corrections, suppression or deletion instead of assuming every conversation becomes a permanent preference.

Recall has limits. A provisional guess is not a confirmed fact, and a saved item is not guaranteed to appear in every response.

Open Memory, inspect the item and prepare a correction or forgetting request in conversation. Review the proposed change before it becomes active.

Preparing the request keeps it as an unsent draft and preserves existing unsent text. It does not save a memory or send automatically. Suppression stops future recall; deletion removes the owned memory content while preserving relevant audit metadata.

If your preferred project language changes, replace that preference instead of asking every specialist to ignore an obsolete one.

You choose the item and the intended change. Files, source conversations and backups can be managed separately.

Forgetting a memory does not erase the original conversation, external copies or older backups. It is not a promise of forensic erasure.

Specialist views are internal experiments, not a first-release promise. They cannot turn an inferred preference into approved memory or grant a new permission.

The current focus is the single conversation, its chosen context and reviewed memories.

EVO starts with your current request, relevant earlier facts and explicit corrections, then relates them to the outcome you are asking for.

It should distinguish the goal from one suggested method, use known constraints and identify missing information that could materially change the result.

“Make this page clearer” may call for a better product explanation before visual decoration; EVO should keep that interpretation provisional until supported.

Correct the goal, provide a constraint or choose an answer when a decisive question is offered.

This is task interpretation, not mind-reading. Real-model intent accuracy still needs further evaluation, and inferred motives must not replace your explicit request.

Only after interpreting the task, when a missing answer could materially change correctness or usefulness. Clear requests should not trigger a questionnaire.

The development flow checks for supplied facts and useful low-impact defaults before allowing an optional clarification card.

An unknown workshop audience may change the whole agenda; an unspecified minor formatting preference usually should not stop an initial draft.

Choose an option, enter your own answer or leave the question for later. A question card cannot authorize an action.

The flow is implemented, but live-model question quality remains under evaluation. It may still ask unnecessarily or miss a useful question.

Reliable background execution across a closed conversation is still an internal experiment. Do not rely on it for unattended work in a public release.

Saved results and full background execution are different capabilities.

See release status before planning a long-running task.

Your explicit correction should take priority over the conflicting interpretation while preserving requirements you have not changed.

EVO can revise the brief and produce a more appropriate next result. A tentative interpretation should remain separate from a confirmed user fact.

If “simplify” meant fewer steps rather than shorter text, say so; the next result should address the workflow instead of repeatedly trimming words.

State the intended outcome or answer the relevant clarification. You can also review a captured correction separately.

A correction does not guarantee the model will reason perfectly next time, and it cannot undo an already completed external action.

No. Sources make an answer inspectable; accuracy also depends on what the source says, its date, independence and whether the conclusion follows.

EVO’s research structure links claims to evidence and keeps contested or unsupported parts visible instead of treating a link as automatic verification.

Three articles repeating one press release are not three independent confirmations of a product claim.

Open the evidence and ask for stronger or contradictory sources when the decision warrants it.

A genuine source can still be mistaken, incomplete or misinterpreted. EVO is an aid to checking, not a replacement for all expert judgment.

A disagreement should remain part of the answer, with the competing evidence and the decision it affects made clear.

The research workflow can retain supporting and counterevidence rather than flattening every source into one confident narrative.

A vendor’s current specification and an older independent test may describe different versions; comparing dates and scope can explain part of the difference.

Ask to inspect the competing passages or narrow the question to a particular date, region or product version.

EVO cannot always resolve the conflict. It may need another source, a direct test or a clearly marked unresolved conclusion.

EVO can work with supported extracted document text and structured tables. Image content and page layout need a separate visual-capable path.

Selected text can be searched or compared, and supported tables inspected and aggregated. Supported PDFs provide page text and limited rendered previews; supported images can yield recognized text.

A pricing CSV can be compared by column, while a scanned PDF needs readable extraction or visual review before its contents can support a conclusion.

Select the material and inspect extraction limits before relying on an answer or sharing it with cloud processing.

Text extraction is not proof of layout understanding. Complex PDFs, scans and images do not have universal qualified support, and model visual review remains separately limited.

Text reveals what a page says. A rendered screenshot and element positions reveal how that content appears at a particular screen size.

EVO’s browser inspection keeps those evidence types separate, so a text-only reading cannot be presented as a completed visual review.

A headline can read well in extracted text yet overlap a button on a narrow screen; that requires rendered-page evidence.

Choose desktop or mobile inspection and open the recorded captures beside the findings.

A screenshot covers its recorded state and time. It does not prove every responsive width, interaction, visual interpretation or accessibility behavior is correct.

Supported tools include calculations, selected table analysis, text search and comparison, selected document reading, time conversion and scoped app proposals.

The tool workflow operates on material authorized for the task and returns recorded results that can support the answer.

EVO can total a selected numeric column or compare two selected text versions, then explain the result using that output.

Choose source material and supported access. Review an app proposal separately before applying a change.

The tool collection has defined limits. Public-page text reading is not visual inspection, and selecting tools does not grant arbitrary file, website or account access.

Supported changes with meaningful consequences need the applicable action review; reading selected material does not grant permission to modify or send it.

Some low-risk supported actions allow revocable reusable permission. Deletion and other consequential changes require a fresh review of their target and effect.

Preparing a task or message can produce a proposal, while applying the change or sending the message is a separate decision.

Inspect what will change, narrow the scope, approve when ready or revoke existing permissions.

Not every proposed external action is implemented. A clarification answer, saved preference or old approval never creates an unsupported capability.

Saved results can survive a restart in tested internal flows. This does not mean every interrupted task can finish automatically.

A recorded calculator test kept 6 × 7 = 42 when the final explanation timed out. This is a narrow recovery check, not evidence of general task success.

Unknown external actions must be checked before retrying. Complete App recovery remains under qualification.

They are separate processing choices. Cloud use sends selected request content to the service and needs a connection; local use needs an installed compatible model.

Their capabilities and answer quality differ. Joint continuity after disconnection is still being qualified.

No. Choosing local processing does not authorize a hidden cloud fallback when the local route is unavailable or insufficient.

The current workflow keeps the selected processing route and its data permission separate. A different route needs a new explicit choice.

If a local model cannot review images, the honest result is a capability limit or supported text-only work, not an unannounced screenshot upload.

Stay local, narrow the task or choose an available cloud route after reviewing the sharing scope.

Local selection does not make unrelated network tools offline, and it cannot guarantee that a local model can complete every requested task.

An installed compatible local model can answer selected local text. Search, cloud models and new downloads need a connection.

Local responses can be incomplete or inaccurate; reconnecting does not guarantee automatic cloud handoff.

The App and public model downloads are not yet released.

The local improvement feature can turn relevant direct corrections into reviewable suggestions for future response style and final checks.

It records a cautious summary of the reported mismatch. An adjustment becomes active only after you confirm the relevant records and approve the proposed change.

Repeated requests to lead with the result can become a reviewed preference for placing the useful answer before background.

Inspect, correct or delete the records; approve or revoke supported adjustments and disable capture.

This changes selected response guidance, not model weights, product code or tool permissions. Long-term improvement in real-user outcomes has not yet been demonstrated.

Supported workflows check the result against its required structure, available evidence and requested outcome, keeping unverified parts separate from observed results.

Research, selected-file changes and tool results use different checks. Additional reasoning can explain a problem, but cannot substitute for a missing test or source.

A proposed website file can pass source checks while the final report still says its rendered layout has not been reviewed.

Open the checks, ask for a focused follow-up and decide whether further verification is necessary.

Self-checking reduces opportunities for unsupported claims but is not proof that every answer is correct. Model review and user acceptance have different roles.

Time-aware assistance is designed to adjust the work rhythm using local time and your preferences, without treating late-night or frequent use as a health diagnosis.

The local development feature distinguishes declared preferences from tentative routine patterns and can reduce schedule comments or use a temporary focus mode.

During a late deadline, a shorter next-step summary can be useful without telling you that your schedule is unhealthy.

Turn comments or routine learning off, set work preferences, reset history or request a temporary sprint.

Routine guesses can be wrong. This is not medical monitoring, emotional companionship or an unsolicited push-reminder service; real-user helpfulness remains to be evaluated.

The planned experience keeps the same goal and reviewable progress across devices: capture the request on iPhone, continue suitable work on Mac, then review the result on the phone.

The design preserves where a task started and treats access, device capability and action approval as separate decisions.

You might note a website issue while away, then review the relevant file and proposed change when back at your Mac.

Cross-device sharing would require an explicit choice; desktop actions would still need the appropriate review.

This is a planned workflow, not a released iPhone feature. Live pairing, synchronization and physical-device handoff have not been qualified.

The development design distinguishes a device’s time zone and capabilities from the account’s longer-term preferences, rather than assuming every device is in the same situation.

A device change or travel-related time difference should be treated as context to confirm, not proof of a new routine or permission.

A request started in one time zone may be continued elsewhere without rewriting when the original request happened.

Correct location or schedule assumptions and choose whether temporal preferences may be shared when synchronization becomes available.

Cross-device operation remains planned. Device hints cannot reliably identify the person using a shared computer or establish that travel occurred.

The implemented workspace controls do not make selected business files shared memory for other accounts. Cloud processing and training terms need to be evaluated separately.

Task selection limits what EVO uses; a local correction record is not a model-training job or permission to circulate the original document.

A team can first evaluate a workflow with non-sensitive sample material and determine which data may be shared under its policy.

Review the chosen processing route, applicable terms and organizational requirements before providing confidential information.

No blanket promise about every service’s training or retention practices is made here. A signed enterprise data agreement and deployment controls are not yet an available offering.

Start with the workflow and data boundary: what the team needs to accomplish, which records may be used and who must approve consequential actions.

The existing Work, evidence and review concepts provide material to evaluate. Organization-wide identity, retention, deployment and support require their own assessment.

For a research workflow, agree which sources are permitted, what counts as a complete result and who accepts it before introducing confidential material.

Use the business inquiry route to define requirements without uploading sensitive records into a general product request.

Enterprise SSO, certified compliance, organization-wide retention and service-level commitments are not verified or commercially available capabilities on this site.

Final public rules are not yet published. The internal designs use weekly image allowances and monthly weighted call estimates; they are not currently purchasable services.

Call preparation does not consume call usage, and no live calling service is connected. Read the published plan terms when these features launch.