“Compare these offers.”
A shop page, a supplier catalogue or a research source. Bring the facts you need into columns.
Every cell is a workload. Connect data, files, code and AI through formulas. Reuse each result—and see exactly where a workflow goes wrong.
Designed to run locally or across approved compute nodes, through the spreadsheet or its APIs. Work individually or together, turning data you choose to share into small, reusable models for everyday tasks and enterprise workflows.
Local by design. Cloud by choice. Errors remain visible.
#ERR!=WEB.EXTRACT(A1, "product specifications", COLUMNS(B1:G1))A web page → structured rows you can compare.
Explore the full product direction. These illustrate planned adapters, not live connections.
With the things you already use: a URL, a social feed, a photo or a voice message from a friend. Give a cell an input, describe the job and use the result in your next step. The same idea scales from a household list to a business workflow.
A shop page, a supplier catalogue or a research source. Bring the facts you need into columns.
Turn a permitted feed or saved export into topics, recurring questions and useful signals.
A receipt, an invoice or a handwritten list. Extract the fields, then calculate with them.
A friend’s voice note or a team recording. Turn the words into a transcript and reviewable actions.
From just 100 synthetic receipts, we built a small predictive model of shopping habits. It measures the gaps between purchases and uses them to suggest what may be due again.
That is a first step toward useful AI at home: a familiar question, answered from your own everyday data.
Try “What should I buy?”A deterministic purchase-cadence model. It estimates shopping needs; it does not measure what is left in the fridge. Training and exporting neural models are planned capabilities.
The input scenarios above describe the full product direction. This public demo uses prepared receipts and a bundled offers feed; personal uploads, live URLs and social connections are not enabled here.
These answers are calculated from the sample household’s 100 receipts. Choose an example to load its formula, then press Run formula in the sheet. All public examples run without paid AI calls.
This workbook is generated from a fixed seed and reference date. Every formula below runs in the CogSheet™ deterministic engine and returns the same result for the same input.
A complex formula can involve many cells, including AI. When a step fails or its output fails a check, that cell shows an error such as #MODEL!. You can identify the input, formula or model result that needs attention.
Interactive illustration · fixed sample outputs, no AI call.
Original input stays available.
Expected output: a numeric total.
=SUM(B2, 5)Uses the result from C2.
B2 supplies a valid number. C2 adds £5, and D2 can use the result.
Find the cause, even in a long workflow. The intended full-workbook behavior is to mark dependent cells as blocked until the failed step is corrected and run again. The illustration above demonstrates this on a small chain.
Checks make failures visible. Invalid formats, timeouts and detected inconsistencies can become cell errors. A plausible but incorrect AI answer still needs appropriate checks or human review.
Export and embed compatible specialist micro-models wherever you need them, in Open Neural Network Exchange (ONNX) format.
At the heart of CogSheet™ is the LOGFORCE LFS Model Family: AI models trained through LOGFORCE's patented signal-learning approach. Their signal-based and non-autoregressive architecture turns task-specific representations of documents, media, web content, device readings and workflow state into fingerprints for recognition and decision-making.
The LOGFORCE LFS Model Family connects each workload to the right execution path: reuse a capability, compose known steps, adapt a function or create a new one. Designed for deterministic low-latency, high-throughput decisions, it directs generation toward new capabilities and keeps proven intelligence ready for immediate reuse.
Data, intended result and a clear input/output contract.
Match the workload with eligible functions, models and execution capabilities.
A structured execution choice, supported by traceable evidence and clear permissions.
Run a compatible, approved function or model.
Combine capabilities through typed inputs and outputs.
Retrieve existing code and prepare a tested new version.
Use an approved AI worker to prepare new code or a model workflow.
Run existing intelligence directly. Test and approve new functions; train and evaluate specialist micro-models when the task requires them.
Compose results into the next workload, with versions and source evidence attached.
Save and export compatible code and model packages for reuse in your chosen environment.
Versioned code, models, contracts and tags return to your authorized capability library. Retrieve and reuse them instead of starting again.
Your workspace: cells, formulas, dependencies and specialist model workflows.
The intelligence layer: the LOGFORCE LFS Model Family, signal fingerprints and capability recognition.
The target sovereign runtime: controlled local execution and approved distributed nodes.
Local by design. Cloud by choice. This cloud Private BETA previews the product being built for ecOS >_ CogPOSIX. The destination is a complete local experience with your workbooks, data, functions and specialist models under your control. You choose when to enable external processing and which approved nodes may participate.
Private BETA progressively brings this full product architecture into the workspace, from workload recognition and reusable functions to sovereign execution. The public sample demonstrates its currently available capabilities.
Each workload declares its inputs, operation, expected output and versions. Approved results can be replayed directly. New inputs, code or model versions create a new execution identity. Non-autoregressive models produce decisions through signal recognition; validation and evaluation establish their fitness for the task.
Keep the familiar rows, columns and calculations. Add formulas that process documents, audio, images, web pages, signals and models, using capabilities compatible with ecOS >_ CogPOSIX.
These are planned contract examples. Their syntax and adapters are still to be implemented; the public sheet above runs the pantry formulas today.
“Show bills with a missing due date.” The assistant proposes a formula for your cell. You review it, run it and use its result in the next calculation.
=TABLE.FILTER(BILLS, DUE_DATE = "")=SUM(C2:C12)The LOGFORCE LFS Model Family uses signal-based, non-autoregressive recognition to choose what to reuse, combine, adapt or create. A concise, typed execution plan connects the workload to the capabilities ready to serve it.
=CAPABILITY.PLAN(A2, TaskContract)Read an authorized web snapshot, extract only the requested facts and spill schema-validated rows into named columns with source evidence.
=WEB.EXTRACT(A2, "all product specifications", COLUMNS(B1:G1))=WEB.CITE(B2:G20)Preserve page coordinates while turning PDFs, scans, contracts and invoices into searchable text, layouts and reviewable structured records.
=DOCUMENT.OCR(A2, "en", "layout")=DOCUMENT.EXTRACT(A2, SCHEMA("invoice"), pages: "all")Denoise a recording, transcribe it with timestamps, identify the most frequent meaningful terms, translate it or synthesize an approved voice output.
=AUDIO.DENOISE(A2, profile: "speech")=AUDIO.TRANSCRIBE(B2, "en", timestamps: TRUE)=TEXT.TOP_TERMS(C2, 20, stopwords: "en")=SPEECH.SYNTHESIZE(TRANSLATE(C2, "en", "es"), voice: E1)Detect, segment or measure objects in images and sampled video frames while retaining the exact frame, region and model evidence behind each result.
=VIDEO.SAMPLE(A2, every: "2s")=VISION.DETECT(B2:B120, classes: {"defect","scratch"})=VISION.SEGMENT(C2, target: "damaged area")Build permission-aware indexes across text, images and audio, retrieve relevant evidence locally and generate summaries that remain linked to their sources.
=EMBED.INDEX(A2:A500, modality: "auto", placement: "local-required")=SEMANTIC.SEARCH("termination clauses", B2, 10)=LANGUAGE.SUMMARIZE(C2:C11, format: "decision memo")Forecast calibrated time series, detect unusual sensor patterns and classify security events without turning a model score into an automatic privileged action.
=SERIES.FORECAST(A2:A365, horizon: 30, interval: 0.95)=SERIES.ANOMALIES(B2:B10000, baseline: "weekly")=SECURITY.CLASSIFY(C2, profile: "event-v1")Generate reviewable code capsules, reuse pinned environments, prepare labelled datasets and export validated small models for governed local execution.
=CODE.CAPSULE("python", A2, lockfile: B2)=MODEL.TRAIN(A2:F500, label: F, template: "classifier")=MODEL.EXPORT(G2, "onnx")A factory for intelligent formulas: combine approved capabilities, create specialist functions and models, and keep them ready for the next task. Built on signal theory and LOGFORCE's patented technology, with non-autoregressive decision intelligence at its core.
Sensing APIs connect inputs and outputs to applications, devices and infrastructure, bringing the same intelligence into the tools and environments you use.
=MY.READ_VENDOR_FORMAT(A2)=MY.SPECIALIST_MODEL(B2)Today: a working sample, visible formulas and a small predictive model. Next: your own files, reusable code and models, and execution on your own computer.
Per-user workspaces, signed uploads, artifact storage, asynchronous jobs, cancellation and execution receipts.
Local capability discovery, signed manifests, offline replay and explicit local or hosted placement per cell.
Reviewable generated code, pinned dependencies and reusable isolated environments with no default network access.
Dataset and label export, validated training templates and model-specific ONNX export where technically supported.
Approved-node placement, node identity, revocation, permissions and transfer accounting across a future trusted mesh.
Through CogSheet™, LOGFORCE incentivizes AI production, not just consumption. Share useful functions, models and packages, set a price in φ KBSU and earn credits when others pay to use your work.
Use your earned credits to pay for LOGFORCE and CogSheet™ subscriptions, services and AI capabilities. Pricing will be shown in both money and φ KBSU.
Your credits can cover your use of the platform. How much you can use without paying money depends on what you earn and spend. Credit payments and purchases are planned; pricing will be announced at launch.
φ KBSU are internal virtual credits.
A personal project, a team’s workflow or an enterprise process. Request private access and help shape CogSheet™.
cogsheet@logforce.com