Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
22 changes: 14 additions & 8 deletions AGENTS.md
Original file line number Diff line number Diff line change
Expand Up @@ -13,12 +13,12 @@
The navigation keeps Home first and sorts the top-level sections alphabetically. Agents follows the user journey. Other sections keep their existing order:

- **Agents (Beta)** - `/developers/*`. Start with a familiar task, then improvement and scheduling. Keep Examples and More about Agents (`/developers/guides/*`) collapsed by default. Introduce features when they help the reader's current task. Keep prompts natural and explain terms before using them.
- **App setup** - `/integrations/{github, gmail, google-calendar, slack, zoom}`. Per-app permissions and prompts, not feature pages. All of them connect through the Apps tab of the Add MCP dialog.
- **Deployment models** - `/deployment-models`. Current availability and operating boundaries for Fluso Cloud, dedicated AWS VPC, planned Azure VNet, and scoped on-premises deployments.
- **App setup** - `/integrations/{github, gmail, google-calendar, slack, zoom}`. Per-app permissions and prompts, not feature pages. Use the current Apps catalog under Plugins → MCP → Add MCP. Google services connect separately; native Fluso connectors have the Fluso mark.
- **Deployment models** - `/deployment-models`. Released Fluso Cloud and custom Enterprise deployments requiring confirmed scope.
- **Features** - `/features/*`. Approvals and permissions, Apps and MCP servers, Chat, Confidential mode, Imports, Memory, Projects, Skills, and Tasks.
- **Fluso API** - `/api/*`. Start with access and a first request. Document shared workflows once under Use the API. Lead with a useful task, runnable requests, and the expected result. Reuse the deployment's example helpers. Put protocol details and recovery rules beside the step that needs them. Each deployment's `/docs` and `/v1/openapi.json` own exact request and response schemas. Keep endpoint tables collapsed after the workflow. Preserve old API URLs with redirects.
- **Fluso API** - `/api/*`. Start with access and a first request. Document the released Cloud API; do not publish daemon setup or pairing instructions. Document shared workflows once under Use the API. Lead with a useful task, runnable requests, and the expected result. Reuse the deployment's example helpers. Put protocol details and recovery rules beside the step that needs them. Each deployment's `/docs` and `/v1/openapi.json` own exact request and response schemas. Keep endpoint tables collapsed after the workflow. Preserve old API URLs with redirects.
- **Get started** - `/going-deeper`, `/introduction`, `/quickstart`. These pages explain the path from first setup to daily use.
- **Reference** - `/resources/{faq, legal, pricing}`. Legal links to the terms of service at `https://fluso.ai/terms` and privacy policy at `https://fluso.ai/privacy`; do not duplicate the policies in the docs.
- **Reference** - `/resources/{availability, faq, legal, pricing}`. Legal links to the terms of service at `https://fluso.ai/terms` and privacy policy at `https://fluso.ai/privacy`; do not duplicate the policies in the docs.
- **Release notes** - `/release-notes`. Customer-facing changes, newest first.
- **Workflows** - `/workflows/*`. Six concrete stories: bug-to-PR, content launch, knowledge recall, meetings, morning brief, and research-to-deck.

Expand All @@ -34,16 +34,16 @@ This is the mental model the docs use. Every page should reinforce it, not contr
- **Apps & MCP** are the plugs into external apps. Every connection is an MCP connection: managed apps from the catalog, or custom servers by URL.
- **Skills** are the capabilities Fluso reaches for when a request matches one (built-in or custom via `SKILL.md`).
- **Tasks** is the unified to-do system, populated mostly automatically.
- **Memory** is the knowledge graph that builds in the background.
- **Memory** includes saved preferences, project context, and working-memory summaries. Do not promise complete automatic indexing of every connected app.

Email, calendar, code, content, research are skills, not separate features. The skills page (`/features/skills`) is the catalog. Per-app integration pages (`/integrations/*`) cover setup and permissions.

## Terminology

- **Fluso** — the product.
- **Apps** / **MCP connections** — the connections to third-party apps. There is no separate connector system; connections live under **Plugins → MCP**. Use **Connectors** when referring to the Agent editor's capability picker.
- **Apps** / **MCP connections** — the connections to third-party apps. Native Fluso and provider-managed connections live under **Plugins → MCP**. Use **Connectors** when referring to the Agent editor's capability picker.
- **Agent** — saved setup and a continuing main conversation. **Manager** refines that one Agent; **sessions** are delegated conversations; **routines** are scheduled messages. Main conversations take saved setup changes on their next turn; existing delegated sessions retain their setup.
- **Knowledge graph** — Fluso's persistent memory. Lowercase.
- **Memory** — saved context with the boundaries described on the Memory page.
- **Skills** — specialised capabilities that activate automatically. Built-in or custom (`SKILL.md`).
- **Projects** — workspaces that scope context, files, and tasks.

Expand Down Expand Up @@ -84,11 +84,17 @@ Use the [ASD-STE100 writing skill](https://github.com/danyuchn/asd-ste100-skill/

## Content boundaries

- Compare current production release evidence and feature configuration with source before describing a feature as available. A dev merge is not a public release.
- Fluso Local is not enabled in production; the Telegram bot is retired. Keep their setup guides out of navigation, search, and generated Markdown. Redirect old routes to Availability. Preserve historical release notes.
- All standard plans have weekly allowances: Plus is 10 times Free, Pro is 10 times Plus. Do not publish pending accounting changes or internal budget values.
- Native connectors do not imply every catalog entry is native. Encrypted inference does not imply enclave-hosted workspace storage, tools, or connected apps.
- Do not publish an unconfirmed release date, bug-fix version, or measured performance claim.

- Fluso Admin is internal. Do not publish its operator guide, navigation, links, or panel instructions in this public documentation site.
- Never invent feature behaviour. If a capability isn't documented in source materials, leave it out.
- When describing external sends, explain how to request and review a draft and choose **Ask me first**. Do not claim every write requires approval: saved tool rules, connection settings, and the chat's mode determine that behavior.
- Verify Agent behavior against both current frontend and backend code. Do not restore removed Studio graphs, evaluations, version rollback, YAML transfer, webhook triggers, or thread-management toggles from historical release notes.
- For product actions, point users to the macOS download at `https://fluso.ai/` and to support at `support@premai.io`. Don't link to `app.fluso.ai`. Fluso is a desktop app.
- For product actions, point users to the desktop downloads at `https://fluso.ai/` and to support at `support@premai.io`. Don't link to `app.fluso.ai`. Fluso has macOS, Windows, and iOS apps. Desktop guides do not establish mobile feature parity.

## Publishing release notes

Expand Down
8 changes: 7 additions & 1 deletion content/docs/api/cloud/apps.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -4,10 +4,16 @@ icon: plug
description: Connect a supported Cloud app when your integration needs its data or tools.
---

Cloud can guide users through connecting supported apps, such as Google Workspace. A connection belongs to the authenticated account. Completing sign-in does not remove its tool-approval rules.
Cloud can guide users through connecting supported apps, such as Gmail. A connection belongs to the authenticated account. Completing sign-in does not remove its tool-approval rules.

For a custom server, use [custom MCP connections](/api/workflows/connections).

## Native and provider-managed apps

Read the current catalog rather than hard-coding app IDs. Its `connect_kind` distinguishes native Fluso, Google, Microsoft, and provider-managed flows. Only configured services are available. Google services have separate entries.

An app may require an API key or account-specific setup instead of OAuth. If the catalog flow returns `API_KEY_REQUIRED` or `SUBDOMAIN_REQUIRED`, complete that setup in Fluso, then recheck the connection. Do not treat a provider redirect or an old saved connection as proof that migration is complete.

## Connect the requested app

For example, a morning-brief Agent may need a calendar connection. Its run can enter `waiting_action` with an `mcp_connect` action in thread state.
Expand Down
2 changes: 1 addition & 1 deletion content/docs/api/cloud/client-sign-in.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -73,7 +73,7 @@ Use `auth.access_token` as `Authorization: Bearer TOKEN` for API requests. Save

Store `auth` in the client's credential store. It includes `access_token`, `refresh_token`, `expires_in`, `session_id`, and `user`.

The browser step calls `POST /v1/auth/client/complete` with the returned state under the user's Clerk app session. Current browser callbacks support configured Fluso handoffs. A developer token cannot perform that browser step.
The browser step calls `POST /v1/auth/client/complete` with the returned state under the user's Clerk app session. Only configured Fluso callback clients are supported. A developer token cannot perform that browser step.

Sign-in state expires after ten minutes. The returned code expires after five minutes and works once. If the exchange response is lost, start sign-in again.

Expand Down
2 changes: 1 addition & 1 deletion content/docs/api/first-request.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,7 @@ Set the URL for your workspace:
export FLUSO_API_URL='https://api.fluso.ai/v1'
```

For Fluso Dev, use `https://api.dev.khichdi.cc/v1`. The token must belong to that workspace.
The token must belong to your production Cloud account.

Read your token without showing it or saving it in shell history:

Expand Down
6 changes: 4 additions & 2 deletions content/docs/api/index.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -12,9 +12,11 @@ Start with one conversation. Add schedules, connections, or live updates when yo
Get access, submit a short task, and read the saved answer.
</Card>

## Base URL and access
## Use your Cloud workspace

Send requests to `https://api.fluso.ai/v1` with a [developer token](/api/cloud/tokens). Fluso Dev uses `https://api.dev.khichdi.cc/v1`. Use credentials from the same environment as the URL.
The production base URL is `https://api.fluso.ai/v1`. Authenticate with a [developer token](/api/cloud/tokens) from the same account you use in Fluso. Requests use that account's workspace and allowance.

These guides cover the released Cloud API. See [product availability](/resources/availability) for unsupported deployment options.

## Find the exact fields

Expand Down
4 changes: 2 additions & 2 deletions content/docs/api/workflows/connections.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,7 @@ description: Connect a service once, then help users decide when Fluso needs per

Your integration can use the services already connected to the same Fluso workspace. A connection gives access to tools. The user's permission settings decide which actions can proceed.

For an initial setup, connect the service in **Plugins → MCP** in Fluso. Fluso offers managed apps such as Google Workspace, and you can add custom MCP servers.
For an initial setup, connect the service in **Plugins → MCP** in Fluso. The catalog offers native Fluso and provider-managed apps. Google services such as Gmail and Calendar connect separately.

The examples below use `api`, `thread_id`, and `run_id` from [your first request](/api/first-request).

Expand Down Expand Up @@ -69,7 +69,7 @@ Open the returned `authorization_url` for OAuth. `already_connected` needs no si

Read `GET /v1/mcp-oauth/connections` to inspect saved connections. `needs_reauth` means the user must reconnect. Saved inventory alone does not prove the service is reachable.

A developer write token can decide one-time tool approvals. Permanent rules require a signed-in app session.
A developer write token can decide one-time tool approvals. Permanent rules require a signed-in Cloud app session.
</Accordion>

<Accordion title="Custom connection and tool-discovery endpoints">
Expand Down
2 changes: 2 additions & 0 deletions content/docs/api/workflows/schedules.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -57,6 +57,8 @@ Pausing or deleting a schedule does not cancel work already accepted. [Cancel th
</Accordion>

<Accordion title="Understand late, failed, and one-time runs">
Delayed recurring work does not replay every missed occurrence. Check the saved next-run time and conversation state.

Delivery failures can pause a schedule. A failed accepted run does not automatically pause recurring work.

A one-time schedule stops submitting after acceptance, even if its run later fails. Inspect the saved run before deciding whether to request that work again.
Expand Down
2 changes: 2 additions & 0 deletions content/docs/api/workflows/streaming.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -49,6 +49,8 @@ After a disconnection, repeat that sequence. Continue checking saved state perio
Buffer incomplete frames across network chunks. Ignore unknown event types and keepalive comments. Use a client that supports an Authorization header. Keep tokens out of URLs.

If you use `stream: true` during input submission, save the first `input.accepted` receipt. It contains the IDs for recovery if the stream fails.

If your client connects through a proxy you operate, disable response buffering for this stream.
</Accordion>

<Accordion title="Render tool progress accurately">
Expand Down
62 changes: 15 additions & 47 deletions content/docs/deployment-models.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -2,63 +2,31 @@
title: Deployment models
sidebarTitle: Overview
icon: server-cog
description: Compare Fluso Cloud and Enterprise deployments.
description: Start with Fluso Cloud, or discuss a custom Enterprise deployment with the team.
---

Your deployment model decides who operates Fluso and where its runtime, durable data, and diagnostics can live. It does not by itself control where connected Apps or external model providers process data.

| Model | Availability | Operations |
| --- | --- | --- |
| Fluso Cloud | Available | Managed by Fluso |
| Dedicated AWS VPC | Supported for scoped Enterprise deployments | Responsibilities agreed during deployment design |
| Azure VNet | Coming soon | Not available today |
| On-premises | Scoped Enterprise engagement | Responsibilities agreed before implementation |

## Fluso Cloud

Fluso Cloud is the standard managed service. It runs on AWS with European hosting by default. Fluso operates the application services, Agent runtimes, storage, and platform updates; you manage your workspace, users, connected Apps, and approval policies.

Choose it when you want to start without operating infrastructure. See [Legal](/resources/legal) for Fluso's privacy policy.

## Dedicated AWS VPC

A dedicated AWS VPC deployment is available for Enterprise customers whose network or residency requirements do not fit the managed service. It is a scoped deployment, not a self-service switch.

Before launch, your team and Fluso agree on AWS account ownership, region, network connectivity, ingress and egress, DNS, secrets, data stores, backups, upgrades, and support access.
Fluso Cloud is the standard managed service. Fluso operates the application, Agent runtimes, storage, and platform updates. You manage your files, connected apps, and approval settings.

## Azure VNet (coming soon)
The desktop and mobile apps connect to this service. Installing them does not run the workspace or inference locally. See [current availability](/resources/availability).

Azure VNet support is planned but is not available today. There is no published availability date. Do not make an Azure deployment dependency until Fluso confirms the required region and services are supported.
Workspace data is hosted in Europe by default. Model inference and connected apps have separate processing boundaries. Pro includes optional [encrypted inference](/features/confidential); this protects model requests without moving the whole workspace into an enclave.

## On-premises
## Custom Enterprise deployments

On-premises deployments are scoped with Enterprise customers against the target infrastructure. Fluso does not currently offer a one-click installer or a generic support promise for every Kubernetes, virtual-machine, or bare-metal environment.
Contact the team to assess a dedicated VPC or on-premises requirement. These are scoped engagements, not self-service options included automatically with a Cloud subscription.

Agree on these boundaries before treating the design as approved:
Before relying on a proposed deployment, agree on:

| Boundary | What to decide |
| Area | What to confirm |
| --- | --- |
| Data residency | Where the database, project files, knowledge data, and backups are stored |
| Runtime and inference residency | Where Agent runtimes execute and which model endpoints may receive requests |
| Diagnostic-data residency | What diagnostic data is captured, where it is stored, how long it is retained, and who can access it |
| Network access | Which inbound paths and outbound destinations are permitted |
| Connected Apps | Which external systems may be read or changed, and what returned data Fluso may persist |

<Warning>
Running Fluso on-premises does not automatically keep model inference or connected-App data on-premises. External providers keep their own processing boundaries. Confirm every provider and route as part of the deployment design. See [Legal](/resources/legal) for Fluso's privacy policy.
</Warning>

## Operational telemetry

AWS deployments send service logs to CloudWatch and define CloudWatch alarms. Fluso's knowledge service emits structured logs and can export traces and metrics through OpenTelemetry (OTLP). The current AWS collector routes traces to X-Ray and metrics to CloudWatch; Prometheus scraping is optional.

Traces can include prompt and response text. For a dedicated or on-premises deployment, agree which signals are captured, where they are stored, how long they are retained, and which customer-owned collectors are supported.

## Choose a model
| Infrastructure | Supported environment, region, and who operates it |
| Data | Storage, backups, retention, deletion, and support access |
| Models and tools | Inference endpoints, connected systems, and outbound network access |
| Identity and audit | Required identity integration and audit records, including implementation scope |
| Operations | Updates, monitoring, recovery, and support responsibilities |

- Start with Fluso Cloud when managed operations and European hosting meet the requirement.
- Scope an AWS VPC deployment when you need a dedicated AWS network boundary.
- Treat Azure VNet as future availability, not a current option.
- Scope on-premises only after Fluso validates the infrastructure, residency, provider, telemetry, and support requirements.
A private deployment does not automatically make external inference or app connections local. An offline or air-gapped requirement needs a specific design and confirmed feature scope.

For a custom deployment, [contact Fluso](mailto:sales@premai.io).
For a custom deployment, [contact Fluso](mailto:sales@premai.io). For the standard service's policies, see [Legal](/resources/legal).
2 changes: 1 addition & 1 deletion content/docs/developers/examples/document-filing.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,7 @@ description: Make proposals and attachments easier to find after you send them.

Customer documents often stay buried in sent email. An Agent can copy them into the right Google Drive folders and keep track of what it already filed.

This job needs a [Google Workspace connection](/integrations/gmail) with **Allowed** access, because it writes files to Drive.
Connect [Gmail](/integrations/gmail) and **Google Drive** separately. Select both in the Agent setup. Drive needs **Allowed** access because the task writes files there; Gmail can stay **Read only**.

## Start with one week

Expand Down
2 changes: 1 addition & 1 deletion content/docs/developers/examples/email.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ After a busy day, the hard part is often deciding which messages still need you.

An inbox Agent can read the recent conversation, identify an unanswered request, and help you write a reply.

Connect [Google Workspace](/integrations/gmail) and select it in the Agent's [app access](/developers/guides/settings#grant-app-access).
Connect [Gmail](/integrations/gmail) and select it in the Agent's [app access](/developers/guides/settings#grant-app-access).

## Give it a clear job

Expand Down
Loading
Loading