Question 1

How do I sign up?

Accepted Answer

Go to sami-agent.com and click "Get started". You can register with an email address or continue with GitHub or Google. After registration you receive a verification email — click the link and your account is active.

Question 2

How do I install the desktop app?

Accepted Answer

The desktop app is not publicly released yet. Visit the Download page and join the waitlist to get notified the moment an installer for your platform (Windows, macOS, or Linux) is available.

Question 3

What is a consensus run and how do I start one?

Accepted Answer

A consensus run is a structured task session: an AI council works through your request in five stages — Understand & Contract, Plan, Build, Harden and Acceptance — and each stage ends in a yes/no vote. Open the desktop app, describe your task in the War Room and press Enter or the Send button. The council starts by asking you what it needs to know.

Question 4

How do I set up my workspace?

Accepted Answer

In the desktop app, open a folder from your file system using the Explorer panel or File → Open Folder. SAMI reads the project structure and makes it available to the council as context. You can open multiple folders as a multi-root workspace.

Question 5

What verbosity modes are available?

Accepted Answer

Three modes: Full (every contribution with its full text and the vote panel — the default), Compact (a one-line summary per model), and Minimal (just the council's activity pulse). Switch from the War Room toolbar or with the sami.view.verbosity setting; the change applies right away.

Question 6

What are approvals and do I need to click through them?

Accepted Answer

Approvals are the points where a run waits for you. L1, "Ask before every tool call" (the default): you approve every tool call, including reading files, and each finished stage. L2, "Ask before destructive calls": reads run without asking; you approve changes to files and commands, and confirm each stage. L3, "Full auto": nothing waits for you — the council's yes moves the run on. The council reviews every stage at every level, and destructive operations are blocked at every level. You choose the level in the desktop app, and it stays until you change it.

Question 7

Does SAMI work offline?

Accepted Answer

The desktop app requires an internet connection to reach the AI inference infrastructure. Local editing, file browsing, and terminal use work offline, but no council run can start without a network connection.

Question 8

Do I need to configure anything before my first run?

Accepted Answer

No. After installing and signing in, you can start a consensus run immediately. The model catalog, credit allocation, and team settings are all pre-configured based on your plan. Advanced users can fine-tune the council size, autonomy level, and verbosity in Settings.

Question 9

What is S.A.M.I.?

Accepted Answer

S.A.M.I. (Strategic · Agentic · Multilayer · Intelligence) is a desktop coding environment that runs an AI council instead of a single model. Multiple AI models propose, critique, vote, and converge on a result before any change lands in your workspace.

Question 10

What is S.A.M.I. not?

Accepted Answer

SAMI is not a chatbot, a prompt playground, or a single-model autocomplete tool. It is not a code generator that pastes a snippet and walks away. Every task goes through a structured pipeline where independent AI perspectives check each other before you see a result.

Question 11

How does SAMI differ from single-model coding assistants?

Accepted Answer

Single-model tools get one shot. If the model makes a flawed assumption or misunderstands scope, you inherit that mistake. SAMI's council architecture means the first draft is challenged by other models in a structured review stage — logical errors, missing edge cases, and scope creep get flagged before you see the result. The tradeoff is more compute per run; the benefit is fewer runs that need a full redo.

Question 12

Who is SAMI built for?

Accepted Answer

Primarily professional software engineers and engineering teams who need reliable AI-assisted development — not just code generation but structured reasoning about their specific codebase. SAMI is also useful for technical leads reviewing complex changes, researchers prototyping software experiments, and companies in regulated industries that need an auditable AI workflow.

Question 13

Which languages and frameworks does SAMI support?

Accepted Answer

SAMI is language-agnostic. The council reasons in natural language about your code, so any language or framework that can be represented as text is supported.

Question 14

Is SAMI a code editor?

Accepted Answer

The desktop app includes a full code editor so you can view, edit, and review files alongside the AI conversation. It is not a stripped-down viewer — you get syntax highlighting, file tree, integrated terminal, and git integration. The editor is the AI work surface; managing your account and billing happens in the web dashboard.

Question 15

Does the AI run on my machine or in the cloud?

Accepted Answer

AI inference runs on managed cloud infrastructure, not on your machine. Chat content isn't stored on SAMI's servers — SAMI relays it to the model providers and streams the answer back. Council runs are the exception: each run's record (stages, votes, results) is saved to your account so you can replay it.

Question 16

Which operating systems are supported?

Accepted Answer

The desktop app runs on Windows (x64 and ARM64), macOS (x64 and Apple Silicon), and Linux (x64 and ARM64). The web dashboard works in any modern browser — Chrome, Firefox, Safari, and Edge.

Question 17

What is the web dashboard for if the AI is in the desktop app?

Accepted Answer

The web dashboard handles everything account-related: plan management, billing, usage analytics, and team administration. The separation is deliberate — AI workloads belong in an environment with direct file system access and a proper editor; account and billing belong in a secure, browser-accessible backoffice.

Question 18

Is there a mobile app?

Accepted Answer

Not currently. The desktop app is the AI work surface and needs a real file system and editor context to be useful. The web dashboard is mobile-responsive for checking usage or managing your account on the go.

Question 19

Does SAMI remember earlier work on the same project?

Accepted Answer

On paid plans, yes. A follow-up run on the same project carries forward the decisions and lessons from earlier runs, so the council does not re-open a choice you already settled or repeat a mistake it already corrected.

Question 20

What does the name S.A.M.I. stand for?

Accepted Answer

Strategic · Agentic · Multilayer · Intelligence. Each word describes a design principle: the council forms strategy before acting, each model in the council is an autonomous agent, the pipeline is multilayered with independent review stages, and intelligence emerges from the interaction rather than from a single model.

Question 21

What is the War Room?

Accepted Answer

The War Room is the main interface in the desktop app where you interact with the AI council. You describe your task, attach files or context, set the verbosity and autonomy level, and submit. The council's staged pipeline runs in the conversation pane and writes results directly to your workspace.

Question 22

What stages does the pipeline run through?

Accepted Answer

The pipeline has five stages, always in this order: 01 Understand & Contract — clarifies the request with you, then fixes the contract the build must follow. 02 Plan — plans the complete structure: folders, files and modules. 03 Build — the Writer writes the code while the other models review it. 04 Harden — every model challenges the build, and the Writer applies the validated fixes. 05 Acceptance — a final audit and one last run of the project's checks. Each stage ends in a yes/no vote and leaves a visible artifact and vote record.

Question 23

What is a veto round and how is it resolved?

Accepted Answer

A veto round starts when any Guardian votes no at the end of a stage. A no must carry a written reason — at least three sentences and one concrete piece of evidence. When a no lands, the stage pauses and the full council re-deliberates with the rationale surfaced to all Guardians, bringing counter-arguments and alternatives until the objection resolves into a genuine yes. If the objection is not resolved within a bounded number of rounds — or the run budget runs out, or you cancel — the stage moves on with it recorded as unresolved, visible in the War Room. Every vote is yes or no — a no always carries its reasoning, which is what drives the resolution loop.

Question 24

Can a review stage send work back to the design, not just the code?

Accepted Answer

Yes. Build, Harden and Acceptance can send the run back to Understand & Contract or Plan with a written change request, a limited number of times per run; code-level problems are fixed inside the stage.

Question 25

Does the council actually run my project, or just review the code?

Accepted Answer

Both. After Build, Harden and Acceptance, SAMI runs the project's own checks — typecheck, lint, tests and build, when the project defines them — and puts the real output in front of the council. A failure goes back to the council: the Writer may make a limited number of fixes and the council always votes again. If the objection is not resolved within a bounded number of rounds — or the run budget runs out, or you cancel — the stage moves on with it recorded as unresolved, visible in the War Room.

Question 26

What is the Execution-Verify Gate and how does it differ from a normal vote?

Accepted Answer

Most AI tools vote on plausibility — they read the code and decide if it looks right. SAMI's Execution-Verify Gate makes the council vote on proven behaviour: it runs typecheck, lint, tests and build when the project defines them, and a stage only moves on once that real run is green or the council has voted on the failure. A passing run is proven, not assumed. A failing run is placed in front of the council with the real failure visible — the council either accepts it (a known, expected, or flaky failure, with the decision recorded) or treats it as a blocker. A blocker goes into the same resolution loop as any no: the Writer may make a limited number of fixes and the council always votes again. If the objection is not resolved within a bounded number of rounds — or the run budget runs out, or you cancel — the stage moves on with it recorded as unresolved, visible in the War Room.

Question 27

Who decides the final answer in a run?

Accepted Answer

The council votes at each stage. The protocol is binary: yes or no. A no is always explained and worked through before a stage advances. If the objection is not resolved within a bounded number of rounds — or the run budget runs out, or you cancel — the stage moves on with it recorded as unresolved, visible in the War Room. The final output is the artifact that clears every stage.

Question 28

How do I read the War Room conversation?

Accepted Answer

Each message in the conversation pane is labelled with the stage it came from and the council voice that produced it. Stage labels appear as collapsible headers; expand one to see the full reasoning. In Minimal mode you only see the council's activity pulse; in Full mode every contribution is visible, with its full text and the vote panel. Use the stage progress bar at the top to track which stage the current run is in.

Question 29

Can I interrupt or cancel a run mid-way?

Accepted Answer

Yes. Stop the run from the War Room. Files the Writer already changed stay in your workspace; undo them with Undo run in Tool Audit.

Question 30

How long does a typical run take?

Accepted Answer

It depends on task complexity and the number of council members active on your plan. Focused bug-fix or explanation runs finish quickly; a multi-file refactor or architecture proposal with full review rounds takes longer. Token consumption per run is visible on your usage analytics page.

Question 31

Can I attach files or images to a run?

Accepted Answer

Yes. Type an @-mention in the War Room composer: @file attaches that file's content (without a path, the file open in the editor), and @folder attaches a listing of a folder. For images, use the Attach image button in the composer, or drag an image onto it or paste one — PNG, JPEG, WebP and GIF work. The council treats attachments as additional context alongside your workspace structure.

Question 32

Which AI models can I choose from?

Accepted Answer

The model catalog is curated and updated as providers release new versions. It includes flagship models from major providers across reasoning, coding, and instruction-following specialisations. Specific model IDs are not listed publicly because the catalog rotates — what you see in the app is always current. You pick models in the desktop app's model picker.

Question 33

Why use a council of models instead of just one?

Accepted Answer

A single model gets one shot at your task. It cannot internally challenge its own reasoning or catch its own misunderstandings. A council with independent voices and structured review stages is architecturally immune to a class of single-model failure: overconfident wrong answers, tunnel-vision on one approach, and silent scope creep. The cost is more tokens per run; the benefit is results that have already been cross-examined.

Question 34

How do I choose which models go in the council?

Accepted Answer

Open the model picker in the desktop app. Every model you select becomes a council Guardian — an equal voting participant across every stage. Two of those Guardians take on per-stage coordination duties (one coordinates the stage, one writes the stage artifact), but all cast votes with equal weight. For most tasks, leaving the selection empty is the best starting point: SAMI picks a balanced default set of models for your plan.

Question 35

What roles do models play in the council?

Accepted Answer

Every model you add to the council is a Guardian — it participates in every stage with equal voting weight. There are no separate 'review models' or 'draft models'. Per stage, two Guardians carry a duty on top of that: one acts as Lead (coordinates the stage flow and aggregates votes) and one acts as Writer (produces the stage artifact and is the only model that writes code or runs commands). These are duties, not ranks — both still vote with the same weight as everyone else. A single blocking no vote from any Guardian holds the stage while the council re-deliberates, regardless of which duty that Guardian carries — and that no never ends the run. If the objection is not resolved within a bounded number of rounds — or the run budget runs out, or you cancel — the stage moves on with it recorded as unresolved, visible in the War Room. Inside every stage the models work through a shared ledger of claims, challenges and proposals, each backed by evidence. An objection stays open until the model that raised it is satisfied or the Lead records it, objection preserved — then the council votes.

Question 36

How many models can be in the council on each plan?

Accepted Answer

Council size depends on your plan — the pricing page's detailed comparison lists the limit for each plan. Higher plans unlock larger councils, which means more independent review per run.

Question 37

What happens on the Free plan when it comes to model access?

Accepted Answer

Free plan users get access to a selected subset of the catalog — capable models optimised for cost. You will not have access to the highest-capability or highest-cost models. Upgrading expands the catalog; Team and higher plans also allow a larger council.

Question 38

Can I use my own provider credentials?

Accepted Answer

Using your own provider credentials is available exclusively on the Enterprise plan, for organisations that need to route inference through pre-approved provider contracts or compliance-specific endpoints. On Free, Pro, Team, and Ultra, all inference runs through the managed catalog — no external credentials are needed or accepted.

Question 39

Does output quality differ between plans?

Accepted Answer

Yes, in two ways. First, higher plans unlock higher-capability models. Second, larger council sizes mean more independent review passes, which statistically catches more errors — so a run on a higher plan generally produces stronger results than the same task on the smaller Free mini-council.

Question 40

Can I use local models or Ollama?

Accepted Answer

No — local model execution and Ollama are not supported on any plan, including Enterprise. Enterprise customers can use their own provider credentials for regulated environments, but inference still runs through SAMI's managed cloud infrastructure, not on your own hardware. This ensures consistent performance, no GPU required on your machine, and uniform security guarantees across all users.

Question 41

What happens if a model I rely on is retired by its provider?

Accepted Answer

SAMI monitors provider model lifecycle announcements and automatically routes retired models to their approved successors. Your runs continue uninterrupted, and you don't need to do anything.

Question 42

What plans are available and what do they cost?

Accepted Answer

Five plans: Free, Pro, Team (per-seat), Ultra, and Enterprise (custom pricing). Current prices and feature details are on the pricing page.

Question 43

How are council runs charged?

Accepted Answer

Your account has a credit balance in dollars. Every model in the council is charged for the tokens it reads and writes, at that model's rate, stage by stage — so the cost builds up as the run goes. Paid plans add their monthly credits to your balance, and credits roll over instead of expiring. The Free plan is a one-time trial allotment, not a monthly quota. You can also set an optional monthly spend cap under Billing.

Question 44

What happens when my credits run out?

Accepted Answer

Nothing is charged behind your back. With an empty balance, a new run does not start until you add credits. A run that works in several passes checks the balance again before each pass and stops before a pass it can no longer pay for. Ultra and Enterprise runs are never stopped by the balance. You can top up or upgrade at any time from Billing. If you set a monthly spend cap there, new runs don't start once the cap is reached.

Question 45

What payment methods do you accept?

Accepted Answer

Subscriptions are paid by credit or debit card through Stripe.

Question 46

Can I cancel anytime?

Accepted Answer

Yes. Cancel from the billing page in your dashboard. Your plan stays active until the end of the current billing period; no prorated refund is issued for the remaining days. After cancellation you revert to the Free plan.

Question 47

Do you offer refunds?

Accepted Answer

Yes, within 14 days of the first payment for new subscriptions, and case-by-case for billing anomalies (double charges, technical failures). The Refund Policy has the details. To open a request, email support@sami-agent.com or use the contact form, with your invoice number and the reason.

Question 48

How does Team plan billing work?

Accepted Answer

Team is a per-seat plan; the current price is on the pricing page. You subscribe from your billing page, and you add members from the team management panel by inviting them by email, up to the team's member limit.

Question 49

Is there a free trial for paid plans?

Accepted Answer

The Free plan itself is the trial — a limited allotment, not a recurring monthly quota. It runs a genuine mini-council of the three most affordable models in the catalog through the same full workflow as every paid plan, so you experience the real consensus effect before you commit. Any remaining credits roll over rather than resetting. You can upgrade to a paid plan at any time from your billing page. Refer to the pricing page for the current Free plan limits.

Question 50

Do you charge VAT or sales tax?

Accepted Answer

Tax handling depends on your billing country. EU business customers with a valid VAT ID can enter it in billing settings to receive invoices with reverse-charge VAT. Consumer accounts in applicable jurisdictions will see local VAT added at checkout. Stripe handles the tax calculation.

Question 51

Where can I view and download invoices?

Accepted Answer

Invoices are available from the billing page in your dashboard: choose Manage subscription to open the Stripe billing portal, where each invoice is available as a PDF. If you need a custom invoice format for your accounting system, contact support with your invoice number.

Question 52

Do you train AI models on my code?

Accepted Answer

No. SAMI does not use your prompts, code, or outputs to train any model. Where the underlying provider offers a no-training endpoint, that endpoint is used. This is confirmed in our AI Use Policy.

Question 53

Is my chat history stored on your servers?

Accepted Answer

No. Chat content isn't stored on SAMI's servers — SAMI relays it to the model providers and streams the answer back. The chat history you see in the desktop app is stored on your machine. Council runs are the exception: each run's record (stages, votes, results) is saved to your account so you can replay it. The web dashboard also keeps the account, billing, team and usage data needed to run the service.

Question 54

Where does my code go when I run a task?

Accepted Answer

The code and context a task includes are sent over an encrypted connection to the model providers that run your council. Chat content isn't stored on SAMI's servers — SAMI relays it to the model providers and streams the answer back. Council runs are the exception: each run's record (stages, votes, results) is saved to your account so you can replay it. Your workspace itself stays on your machine.

Question 55

Who are your sub-processors?

Accepted Answer

The complete list of third-party services that may process user data is maintained at /legal/subprocessors. Optional sub-processors (AI providers) only receive data when you actively select that provider's model.

Question 56

What are my rights under GDPR?

Accepted Answer

If you are in the EU or UK you have rights to access (Art. 15), rectification (Art. 16), erasure (Art. 17), restriction (Art. 18), portability (Art. 20), and objection (Art. 21). Access and portability are self-service: download your data from Settings → Data export. To exercise any of these rights by request, email privacy@sami-agent.com. We respond within 30 days.

Question 57

Can I delete my account and all my data?

Accepted Answer

Yes. Go to Settings → Profile in your dashboard, scroll to the Danger Zone and click Delete Account. This removes your account record, associated tokens, and billing references. Some Stripe records are retained for the minimum period required by applicable tax law. Since chat history is stored locally, deleting your account does not remove local files — you must do that yourself.

Question 58

What does "local-first" mean for my data?

Accepted Answer

Local-first means the data that matters most to daily work — conversation history, workspace state and local app settings — lives on your machine, not in a remote chat database. Chat content isn't stored on SAMI's servers — SAMI relays it to the model providers and streams the answer back. Council runs are the exception: each run's record (stages, votes, results) is saved to your account so you can replay it.

Question 59

Is there an audit log of who accessed what?

Accepted Answer

Admin accounts have an audit log of administrative actions in the admin panel. There is no message-level log of your chats: Chat content isn't stored on SAMI's servers — SAMI relays it to the model providers and streams the answer back. Council runs are the exception: each run's record (stages, votes, results) is saved to your account so you can replay it. Billing and account changes are recorded in your billing history.

Question 60

Where is data physically stored?

Accepted Answer

Account data (email, plan, billing references) is stored in a managed cloud database in the EU. Chat content isn't stored on SAMI's servers — SAMI relays it to the model providers and streams the answer back. Council runs are the exception: each run's record (stages, votes, results) is saved to your account so you can replay it. Sub-processors may process data in their own regions as disclosed in the subprocessors list.

Question 61

Can I export my account data?

Accepted Answer

Yes, and you do not need to ask. Open Settings → Data export in your dashboard and download a ZIP archive of the server-side data we hold about you: your profile, usage records, team memberships, saved prompts, desktop sessions, run records and newsletter status. Chat content is not in it because SAMI does not store it, and secrets such as your password hash are left out. If you would rather ask us, email privacy@sami-agent.com and we respond within 30 days. Local files are already on your machine.

Question 62

How do I report a security vulnerability?

Accepted Answer

Email security@sami-agent.com or follow /.well-known/security.txt for our disclosure policy. Please do not post vulnerabilities publicly before we have had a chance to investigate and patch.

Question 63

Do you use cookies and tracking?

Accepted Answer

We use strictly necessary cookies for session management and authentication. We do not use cross-site advertising trackers, retargeting pixels or third-party analytics. You can manage cookie preferences via the cookie banner.

Question 64

How do team plans work?

Accepted Answer

One workspace with multiple members. The team owner and admins manage members and invitations, and shared saved prompts are visible to every member. Each member gets the same model access and council size as the plan level. Team analytics in the dashboard show usage per member.

Frequently asked questions

Getting started

How do I install the desktop app?

What is a consensus run and how do I start one?

How do I set up my workspace?

What verbosity modes are available?

What are approvals and do I need to click through them?

Does SAMI work offline?

Do I need to configure anything before my first run?

Question not answered?

Frequently asked questions

Getting started

How do I install the desktop app?

What is a consensus run and how do I start one?

How do I set up my workspace?

What verbosity modes are available?

What are approvals and do I need to click through them?

Does SAMI work offline?

Do I need to configure anything before my first run?

Question not answered?