OUTCOME DELIVERY PLATFORM
Describe the outcome. Flushnet builds, automates and delivers it.
Use a simple task for one direct action, or Build & Deliver when you want Flushnet to plan and execute a larger outcome.
Workspace status
Ready
Sign in to see your active work
START SOMETHING
What would you like to do?
Choose the outcome; advanced execution details stay out of the way until you need them.
LIVE BUILDER SHOWCASE
See what Flushnet can build before you start
Explore production-style websites, business apps, dashboards, presentations, games and AI agents created with Flushnet App Builder, Presentation Builder and Agent Builder. Every public demo includes the exact prompt or specification, so you can copy it, reproduce the result and adapt it for your own project.
RUNNING WORK
In progress
Sign in to view running work.
NEEDS ATTENTION
Blockers and failures
Sign in to view items needing attention.
RECENTLY COMPLETED
Latest finished work
Sign in to view completed work.
DELIVERABLES
Ready to use
Sign in to view deliverables.
SIMPLE TASK
Run one direct task
Choose what you want done, provide the input, and Flushnet handles the execution details.
Checking which services can run automatically now…
Estimated cost10 Compute credits
MANAGED DELIVERY
Complex job request
Describe the complete outcome you need. Flushnet will assess feasibility, estimate cost and delivery time, and accept the job only when it can be scheduled.
ACTIVITY
Job history
| ID | Type | Status | Cost | Created | Progress | Result / Actions |
|---|
PROJECTS
Persistent workspaces
A project keeps the objective, execution plan, jobs, progress and final results together over time.
AI APP / MOBILE BUILDER
Build a web or mobile app from scratch
Describe the product in plain language. Flushnet generates source files, validates builds, previews supported web targets and deploys or exports the result. AI agents are built separately in Agent Builder.
READY TO BUILD
Your AI development workspace
Generate an app to open its files, edit code, request changes, preview it and deploy it.
Select a file
Versions & deployments
Managed database
Environment secrets
Custom domain
GitHub Actions builds optional
GitHub is optional. Connect it when you want repository sync and CI builds.
Use access token instead
Use a fine-grained token only if you prefer token-based GitHub access.
Connected GitHub projects can sync source, run CI builds and return build outputs to your workspace.
Build and deployment logs
No logs yet.
AI PRESENTATION BUILDER
Build PowerPoint presentations from a prompt
Create the outline, slide copy and browser preview with Flushnet AI, then download standard PowerPoint and OpenDocument files.
PRESENTATION WORKSPACE
Browser preview + real Office exports
Generate a deck to preview it here and download the available presentation formats.
Exports · Download the presentation formats currently available for this deck.
AUDIO TRANSCRIPTION
Turn audio and video into editable transcripts
Upload or record audio and video to create accurate, editable transcripts. Automatic processing chooses the best available method. Choose Private / on-device when you want the source media to remain on your device.
Drop an audio or video file hereor click to browse
Or record audio directly in your browser.
Automatic · Flushnet chooses the best available transcription method. Paid AI processing is never started without your explicit confirmation.
Estimated costSelect an audio or video fileFinal Compute Credits are shown before processing. Paid AI processing is never enabled silently.
Your transcripts
Your saved transcripts and exports.
FLUSHNET RAG · MANAGED KNOWLEDGE & RETRIEVAL
Build, operate and reuse grounded AI knowledge
Flushnet RAG combines a managed knowledge service, reusable retrieval infrastructure and automated RAG workflows. Connect or upload sources once, keep them owner-isolated, and reuse retrieved context across Flushnet AI, Agent Builder, App Builder and your own APIs.
MANAGED RAG SERVICE
From source content to grounded retrieval
Use Flushnet as the managed RAG layer instead of assembling ingestion, indexing and retrieval components yourself.
- File and text ingestion with extraction and cleanup
- Chunking and managed embedding/index preparation
- Semantic + keyword hybrid retrieval
- Document search, context retrieval and lifecycle management
Knowledge processing uses Compute Credits according to your account and plan.
This is your canonical private RAG service. Flushnet AI, Agent Builder, App Builder and Gateway/MCP use the same owner-scoped knowledge database.
RAG INFRASTRUCTURE
A reusable knowledge layer for your AI products
Each account receives an owner-isolated knowledge layer that can be consumed by multiple Flushnet products and authenticated API clients.
- Owner-isolated documents, chunks and retrieval indexes
- Authenticated Access Code, API-key and compatible bearer access
- Vector and keyword retrieval with a stable logical knowledge binding
- API/tool interfaces for search, context and ingestion
- Customer-owned source storage with temporary ingestion copies
RAG WORKFLOWS
Automate the complete knowledge lifecycle
RAG is available as a repeatable workflow, not only as a vector search endpoint.
- Source → extract → clean → chunk → embed → index → retrieve
- Connected-source synchronization and unchanged-file skipping
- Transactional re-ingestion so a failed refresh does not replace the working index
- Controlled re-indexing when retrieval settings become incompatible
- Reusable retrieval context for AI, agents, apps and API workflows
USE RAG ACROSS FLUSHNET
One knowledge base, multiple consumers
Flushnet AI
Ground AI responses in your authorized knowledge.Open
Ground AI responses in your authorized knowledge.Open
Agent Builder
Bind account knowledge to an agent without storing the access credential in the agent definition.Open
Bind account knowledge to an agent without storing the access credential in the agent definition.Open
App Builder
Use RAG search and context from generated applications.
Use RAG search and context from generated applications.
API & tools
Use authenticated ingestion, search and context retrieval from your own systems.Open Studio
Use authenticated ingestion, search and context retrieval from your own systems.Open Studio
Stable knowledge binding
flushnet://rag/default
flushnet://rag/default
CONNECTED SOURCES
Keep knowledge synchronized with customer-owned storage
Ready: WebDAV / Nextcloud-compatible sources. Staged through Flushnet Connect: Google Drive, Dropbox, OneDrive, SharePoint, S3-compatible storage and Box.
Persistent originals remain in the user's connected provider. Remote and manual files are used as temporary ingestion copies and cleaned up after processing.
Open Flushnet ConnectPLANS & BILLING
Allocated private RAG capacity
Sign in to load your current Free / Pro / Power limits.
Free
50 documents · 50 MB indexed knowledgeincluded
50 documents · 50 MB indexed knowledgeincluded
Pro
1,000 documents · 2 GB indexed knowledge · connected-source syncincluded
1,000 documents · 2 GB indexed knowledge · connected-source syncincluded
Power
10,000 documents · 20 GB indexed knowledge · higher sync limitsincluded
10,000 documents · 20 GB indexed knowledge · higher sync limitsincluded
Indexed RAG capacity stores chunks, embeddings, metadata and retrieval indexes. Original files can remain in Workspace or customer-owned connected storage. RAG processing and embedding/provider inference are accounted separately where applicable.
API · MCP · CONNECTED PLUGIN
Use the same knowledge outside the Flushnet UI
Flushnet Gateway exposes the owner-scoped rag module for MCP and connected AI clients. It reads the same private knowledge database used here and in Flushnet AI.
rag.status— capacity and index statusrag.list_documents— indexed documentsrag.search— read-only knowledge retrievalrag.retrieve_context— grounded context for agents and apps
Use Advanced RAG Studio for ingestion, embedding policy, source synchronization and memory administration.
ETL / ELT SERVICES
Open advanced ETL studioBuild reliable data pipelines
Extract, clean, transform, enrich and load data into warehouses, databases, APIs or files.
ETL / ELT pipeline
Checking automation path…
Your ETL/ELT requests
GPU COMPUTE
Run accelerated GPU workloads
Request GPU / AI compute for inference, media, Python/CUDA, training and batch workloads. Choose the workload, compute class, duration and preferred region; capacity and price are confirmed before paid execution.
Run a workload for me
Describe the task and required compute. Flushnet reviews the workload and handles the accelerated execution for you.
- AI inference and batch processing
- Audio / transcription workloads
- Embeddings and data workloads
- No separate infrastructure account required
Request external GPU capacity
For heavier Python/CUDA, model-training or longer-running workloads, request a compute class and duration. Capacity and price are confirmed before paid provisioning.
- Simple compute classes
- Single or multi-accelerator requests
- Preferred region
- No paid capacity starts without confirmation
New GPU Compute request
Managed GPU compute · request/quote workflow
Request submission0 Compute creditsExternal GPU usage is billed separately after capacity, price and execution scope are confirmed. No paid capacity is started by this button.
Your GPU Compute requests
Track quote/activation status here. Normal execution jobs also appear in Job history.
MODEL TRAINING
Train or fine-tune a model
Describe the model outcome, dataset and compute needs. Flushnet reviews feasibility, delivery and cost before execution.
Training request
Checking training availability…
Your training requests
APPS & AUTOMATIONS
What Flushnet has built for you
FILES
Workspace files
Uploaded inputs and generated workspace artifacts. Final user-facing outputs are kept separately in Deliverables.
| Name | Type | Size | Added | Action |
|---|
INFRASTRUCTURE
Runtime resources
High-level resources assigned to your projects.
DELIVERABLES
Finished results
Final outputs ready to use, download or open, linked back to the project that produced them when available.
BILLING
Credits & usage
Compute execution and managed AI processing are accounted separately.
Workflow and build execution
Used for Flushnet Compute tasks, app-building, presentation-building, audio-transcription workflow processing, ETL, training services and managed execution where shown.
Managed paid model inference
Used only when managed paid AI processing is selected. This is separate from Compute Credits.
0 AI Credits
When a supported operation uses free AI processing, no AI Credits are charged. Compute workflow charges can still apply to the surrounding task or build.
No silent paid AI usage
When paid AI processing is required, the charge is shown and confirmation is required before it runs.
Buy Compute Credits
These packs add to your Flushnet Compute execution balance.
€10
1,000 Compute Credits
€49
5,500 Compute Credits
€99
12,000 Compute Credits
ACCOUNT
Settings
The same Flushnet account and preferences are used across Flushnet AI, AI Runner and supported Compute services.
Loading account settings…
DEVELOPER
API keys
Use API keys for the standard Flushnet APIs enabled for your account.
| Name | Prefix | Created | Last used |
|---|