Frequently asked questions
Real answers to what people ask most — no marketing phrases, no stubs.
92 questions across 10 categories
Skip to FAQ content
Getting started
How do I sign up?
Go to sami-agent.com and click “Get started”. You can register with an email address or continue with Microsoft OAuth. After registration you receive a verification email — click the link and your account is active.
How do I install the desktop app?
Visit /download and grab the installer for your platform (Windows, macOS, or Linux). Run the installer, then sign in with your SAMI account. The app keeps itself updated in the background.
What is a consensus run and how do I start one?
A consensus run is a structured task session where an AI council works through your request in stages — gathering context, planning, drafting, reviewing, and finalising — before producing a result. Open the desktop app, describe your task in the War Room, and click Submit. The council begins immediately.
How do I set up my workspace?
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.
What verbosity modes are available?
Three modes: Silent (final output only), Normal (stage summaries + key decisions), and Verbose (every stage turn visible in the conversation pane). Switch at any time from the toolbar dropdown — the change applies to the next run.
What are approvals and do I need to click through them?
Approvals are checkpoints where the council pauses and asks you to confirm before writing files, running commands, or making significant changes. On the default autonomy level most positive-vote stages advance automatically; only destructive or irreversible actions require an explicit click. You can raise or lower the autonomy level in Settings.
Does SAMI work offline?
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.
Do I need to configure anything before my first run?
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.
About the product
What is S.A.M.I.?
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.
What is S.A.M.I. not?
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.
How does SAMI differ from single-model coding assistants?
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.
What does a consensus run actually look like end-to-end?
A run passes through seven named stages: (1) Connector— an interactive Q&A loop where the council gathers any missing context before work begins. (2) Strategist — a structured plan is produced and checked for completeness. (3) Architect — system design, interfaces, and contracts are defined. (4) Maverick — the council produces the draft implementation. (5) Optimizer — the draft is refined and challenged for correctness. (6) Guardian — a red-team and security audit is performed; a blocking no must carry a written rationale, and the council deliberates until the objection resolves into a genuine yes. (7) Debugger — the final validation pass before the result is written to your workspace.
Who is SAMI built for?
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.
Which languages and frameworks does SAMI support?
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. Python, TypeScript, Go, Rust, Java, C#, SQL, Terraform, and dozens of others have all been used successfully.
Is SAMI a code editor?
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.
Does the AI run on my machine or in the cloud?
AI inference runs on managed cloud infrastructure — not on your machine. Your code and context are sent to the AI council, the council responds, and nothing is stored server-side after the session. Sensitive material never leaves the encrypted request/response channel.
Which operating systems are supported?
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.
What is the web dashboard for if the AI is in the desktop app?
The web dashboard handles everything account-related: plan management, billing, seat provisioning, 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.
Is there a mobile app?
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.
What does the name S.A.M.I. stand for?
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.
War Room & Pipeline
What is the War Room?
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.
What stages does the pipeline run through?
The pipeline has seven named stages: 01 Connector (interactive context Q&A), 02 Strategist (planning), 03 Architect (system design and contracts), 04 Maverick (draft implementation), 05 Optimizer (refinement and challenge), 06 Guardian (red-team and security audit), 07 Debugger (final validation). Each stage leaves a visible artifact and vote record.
What is a veto round and how is it resolved?
A veto round is a review stage where any Guardian can cast a blocking no vote. A no must carry a written reason — at least three sentences and one concrete piece of evidence. An objection is raised as a no with a written reason, and the council resolves it into a genuine yes through discussion.
When a no lands, the stage pauses and the full council re-deliberates with the rationale surfaced to all Guardians. The council discusses counter-arguments and alternatives until the objection resolves into a genuine yes or the no is upheld. If the no is upheld, the run advances with an explicit risk note attached to the final artifact, visible in the War Room.
Every vote is yes or no — a no always carries its reasoning, which is what drives the resolution loop.
When a no lands, the stage pauses and the full council re-deliberates with the rationale surfaced to all Guardians. The council discusses counter-arguments and alternatives until the objection resolves into a genuine yes or the no is upheld. If the no is upheld, the run advances with an explicit risk note attached to the final artifact, visible in the War Room.
Every vote is yes or no — a no always carries its reasoning, which is what drives the resolution loop.
What is the Execution-Verify Gate and how does it differ from a normal vote?
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 actually runs the project's build, tests, lint, and typecheck and feeds the real output back to the council before any verdict is reached.
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 flows into the same never-abort resolution loop as any no: the council deliberates with the real failure in view until it resolves into a genuine yes; only run-budget exhaustion or cancelling advances with the risk noted. The run is never silently stopped.
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 flows into the same never-abort resolution loop as any no: the council deliberates with the real failure in view until it resolves into a genuine yes; only run-budget exhaustion or cancelling advances with the risk noted. The run is never silently stopped.
Who decides the final answer in a run?
The council votes at each stage. The protocol is binary: yes or no. A no is always explained and always resolved before a stage advances. The final output is the artifact that clears every stage with every no resolved into a genuine yes.
How do I read the War Room conversation?
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 Silent mode you only see the final output; in Verbose mode every intermediate thought is visible. Use the stage progress bar at the top to track which phase the current run is in.
Can I interrupt or cancel a run mid-way?
Yes. Click Stop in the toolbar at any time. The run is cancelled cleanly — partial workspace changes are not written unless a stage already completed and applied its output. If you want to resume from a specific point, start a new run and describe what was already done; the council will pick up from your description.
How long does a typical run take?
It depends on task complexity and the number of council members active on your plan. A focused bug-fix or explanation run usually completes in under two minutes. A multi-file refactor or architecture proposal with full review rounds can take five to fifteen minutes. Token consumption per run is visible on your usage analytics page.
Can I attach files or images to a run?
Yes. You can attach files from your workspace by clicking the paperclip icon in the War Room toolbar. Images (for UI or diagram tasks), text files, and code snippets are all supported. The council treats attachments as additional context alongside your workspace structure.
Models & council
Which AI models can I choose from?
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.
Why use a council of models instead of just one?
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.
How do I choose which models go in the council?
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, using SAMI's recommended council preset is the best starting point — it balances reasoning quality and cost.
What roles do models play in the council?
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, the council assigns two coordination duties on top of the Guardian role: one model acts as Lead (coordinates the stage flow and aggregates votes) and one acts as Writer (produces the stage artifact). These are temporary per-stage responsibilities, not fixed roles — the same model that writes in one stage may coordinate in the next. A single blocking no vote from any Guardian vetoes the stage regardless of which coordination duty that Guardian holds — and that no never ends the run: it loops back to deliberation and is resolved into a genuine yes.
Guardian. Every selected model. Equal vote, every stage, the whole run. There are no separate review or draft models — every Guardian votes with equal weight at every stage.
- Lead
Lead. A per-stage duty: coordinates the discussion and announces the outcome — votes with equal weight. It moves to a different Guardian every stage — a coordination duty, never a higher rank or a super-vote.
- Writer
Writer. A per-stage duty: the only model that writes code or runs commands, at the build stages. It is the only model that writes code, and only at the two build stages — then the duty rotates on.
- No
Binary vote. Each Guardian votes Yes or No — there is no third option. A No never ends the run: it loops back to deliberation, the council brings counter-arguments, and it resolves into a genuine Yes.
How many models can be in the council on each plan?
Council size depends on your plan — check the pricing page for current limits. Higher plans unlock larger councils, which means more independent review passes per run. Enterprise can configure council size on request.
What happens on the Free plan when it comes to model access?
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 to Pro or higher expands the catalog and council size available to you.
Can I use my own provider API keys (BYOK)?
BYOK (Bring Your Own Keys) 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 keys are needed or accepted.
Does output quality differ between plans?
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. A Pro two-voice run will generally produce better results than a Free single-model run on the same task, and an Ultra four-voice run better still.
Can I use local models or Ollama?
No. SAMI does not support local model execution or Ollama on any plan other than Enterprise BYOK. All inference runs through managed cloud infrastructure. This ensures consistent performance, no GPU required on your machine, and uniform security guarantees across all users.
What is the scribe model and how is it different?
The scribe model produces the final written summary of a completed run — the human-readable explanation of what changed and why. It is distinct from the council models that do the reasoning and drafting. On most plans SAMI selects an appropriate scribe model automatically; Pro and above can override it in the model picker.
What happens if a model I rely on is retired by its provider?
SAMI monitors provider model lifecycle announcements and automatically routes retired models to their approved successors. You will see a brief notification in the desktop app the first time a substitution is made, and your runs will continue uninterrupted. You don't need to do anything.
Pricing & billing
What plans are available and what do they cost?
Five plans: Free ($0/month), Pro ($50/month), Team ($150/seat/month), Ultra ($400/month), and Enterprise (custom pricing). The live plan details — including exact token quotas and feature gates — are on the pricing page and fetched directly from the backend.
What is a token quota and what counts toward it?
Every AI council run consumes tokens — the units of text that models process. Tokens are counted for both the context you send (your code, instructions, workspace) and the responses the council generates. The quota is the monthly ceiling for your plan. Usage over the quota is either blocked (on Free) or metered at an overage rate (on paid plans).
What happens when I hit my quota?
On Free: new runs are blocked until the monthly reset. On Pro, Team, and Ultra: you can continue running at an overage rate (metered per token), or you can set a hard spend cap in your billing settings so new runs block instead of incurring charges.
What payment methods do you accept?
Credit and debit cards, SEPA direct debit, Apple Pay, Google Pay, and selected regional methods through Stripe. EU customers on Team and Enterprise can also pay by invoice.
Can I cancel anytime?
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.
Do you offer refunds?
Yes within 14 days of the first payment for new subscriptions, and case-by-case for billing anomalies (double-charges, technical failures). Open a request via the contact form with your invoice number and the reason.
How does Team plan billing work?
Team is billed per seat per month. The workspace owner is the billing contact. Seats are added through the team management panel; each new seat is charged pro-rata for the remaining days in the current billing cycle.
Is there a free trial for paid plans?
The Free plan is a permanent free tier, not a trial. It runs on the same council infrastructure with one model lane and a smaller token quota. 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.
Do you charge VAT or sales tax?
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.
Where can I view and download invoices?
Invoices are available on the billing page in your dashboard under the Invoices tab. Each invoice links to the Stripe-hosted PDF. If you need a custom invoice format for your accounting system, contact support with your invoice number.
Privacy & data
Do you train AI models on my code?
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.
Is my chat history stored on your servers?
No. Conversation content streams through the backend and is not written to a remote conversation database. Chat history visible in the desktop app is stored locally on your machine. The web dashboard stores account, billing, team, and usage metadata needed to operate the service.
Where does my code go when I run a task?
The code and context you explicitly include in a task is sent to the AI council over an encrypted channel. It is processed ephemerally for inference and the response is streamed back. SAMI does not keep a permanent server-side copy of your code or conversation content.
Who are your sub-processors?
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.
What are my rights under GDPR?
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). To exercise any of these rights email privacy@sami-agent.com. We respond within 30 days. Full details are in the Privacy Policy.
Can I delete my account and all my data?
Yes. Go to Settings → Account in your dashboard 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.
What does "local-first" mean for my data?
Local-first means the data that matters most to daily work - conversation history, workspace state, and local IDE settings - is written to your machine by default, not synced to a remote chat database. SAMI's server only sees what you explicitly send in a task request plus the account and usage records required to run the service.
Is there an audit log of who accessed what?
Admin accounts have access to an audit log of administrative actions in the admin panel. Individual user sessions are not logged at the message level because chat content is not stored server-side. Billing and account-change events are recorded and accessible in your billing history.
Where is data physically stored?
Account data (email, plan, billing references) is stored in a managed cloud database in the EU. No chat content is stored server-side. Sub-processors may process data in their own regions as disclosed in the subprocessors list.
Can I export my account data?
You can request a data export under GDPR Art. 20 by emailing privacy@sami-agent.com. We will provide the server-side data we hold about you (account record, billing history) in a machine-readable format within 30 days. Local files are already on your machine.
How do I report a security vulnerability?
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.
Do you use cookies and tracking?
Teams & collaboration
How do team plans work?
One workspace, multiple seats, shared billing. The workspace owner manages members, roles, spend caps, and saved prompts. Each seat gets the same model access and council size as the plan level. Team analytics in the dashboard show usage per member.
Is SSO available?
Domain-locked Microsoft OAuth SSO is available for Team plan sign-up. Enterprise customers can request custom SSO configuration. SAML and SCIM provisioning are in scope for Enterprise — contact contact@sami-agent.com to discuss requirements.
What does the team analytics dashboard show?
Team analytics shows total token consumption, spend against budget cap, runs per member, and model usage breakdown — all scoped to your workspace and filtered by date range. Administrators can export the data as CSV from the analytics page.
What permissions do different team roles have?
There are three roles: Owner (full access, billing contact, can transfer ownership), Admin (manage members and settings, cannot change billing), and Member (run tasks, view own usage). Owners and Admins can set per-member spend caps.
Can my organisation get a Data Processing Agreement?
Yes. Email contact@sami-agent.com with your legal entity name and we will share the standard DPA. Custom riders are handled on Enterprise.
How do I remove a team member?
Go to Team → Members in your dashboard, find the member, and click Remove. Their seat is released at the end of the current billing cycle and the seat count is adjusted on the next invoice. Removed members immediately lose access to the workspace.
Compliance & Enterprise
What is your current compliance posture?
We are working toward SOC 2 Type II certification. We are not certified yet — it would be dishonest to claim otherwise. We do have documented security controls, encrypted data in transit and at rest, access control, and an incident response process. Enterprise customers can request our security overview document by emailing contact@sami-agent.com.
Is a Data Processing Agreement available?
Yes. A standard DPA is available for Team and Enterprise customers. Contact contact@sami-agent.com with your legal entity name. Enterprise customers can negotiate custom riders.
Can SAMI be used in regulated industries (healthcare, finance, legal)?
It depends on your specific regulatory obligations. SAMI's local-first chat architecture means code and chat content are not stored server-side, which helps with some data locality requirements. However, we are not HIPAA Business Associates or PCI-certified. Enterprise customers should discuss their specific requirements — contact us to assess fit.
Can Enterprise customers use their own AI provider contracts?
Yes. Enterprise BYOK lets you supply credentials for pre-approved provider accounts so inference is billed under your existing contract. This is useful when your procurement or compliance process requires vendor-approved model access. Contact contact@sami-agent.com to get started.
Is there an SLA for Enterprise?
Enterprise contracts include an uptime SLA and a committed support response time. The specific figures depend on your contract tier. Contact us to discuss requirements — the standard Enterprise SLA is available on request.
Do you have penetration test results available?
We conduct periodic security assessments. Results are available to Enterprise customers under NDA. Contact contact@sami-agent.com to arrange access.
Troubleshooting
I can't log in — what should I do?
First, check the service status page at /status. If the service is up, try resetting your password via the Forgot Password link on the login page. If you signed up with Microsoft OAuth, use that button rather than email/password. If the issue persists, email support@sami-agent.com with your account email address.
A run started but the response is just hanging — what should I do?
Check /status to see if there is an ongoing incident. If the service is healthy, try stopping the run and restarting it. If the hang persists, restart the desktop app. If it happens on multiple attempts, note the error message (if any) and email support@sami-agent.com.
I see a "worker error" message — what does it mean?
A worker error means the background process that was running your task terminated unexpectedly. This is typically a transient infrastructure issue. Retrying the run is the first step. If you see it repeatedly on the same task, the request itself may be hitting a limit (context too large, or a specific model outage). Reduce the context size or switch models and try again. If it persists, check /status.
SAMI is running slowly — is that on my end?
Slow runs have two common causes: large context (the more files and history you include, the more tokens the council has to process) and peak load. Check /status for any performance degradation notices. If your context is very large, try narrowing the workspace selection or using a targeted file list.
The desktop app is not updating automatically — how do I force an update?
The app checks for updates on launch. If auto-update is stuck, download the latest installer from /download and run it on top of the existing installation — it will upgrade in place without losing your settings or local history.
Which browsers does the web dashboard support?
Chrome, Firefox, Safari, and Edge on their current and previous major versions. Internet Explorer is not supported. The dashboard is not intended as a mobile-first surface, though it is usable on modern mobile browsers for account management tasks.
I lost my 2FA device and am locked out — how do I recover?
Use one of the backup codes you were given when you set up 2FA. If you no longer have them, email support@sami-agent.com from the address on your account with a description of the situation. We verify identity before resetting 2FA.
I hit my quota much faster than expected — why?
Large-context runs consume tokens quickly. The context includes not just your message but also your workspace file tree, any attached files, and the full council conversation. Check your usage analytics for a per-run breakdown. If you see unusually high consumption on a specific run, it likely had a very large context or many revision cycles.
Where can I check if there is an outage?
The service status page at /status shows current uptime and any active or resolved incidents. You can also subscribe to status notifications from that page.
I didn't receive my verification email — what should I do?
Check your spam folder first. If it's not there after five minutes, go to the login page and use the ‘Resend verification email’ link. If you still don't receive it, email support@sami-agent.com with your registration email address.
Support
How do I get help?
For product questions or bug reports: email support@sami-agent.com or use the contact form. Service status lives at /status.
How fast do you reply?
Within two business days for general questions and billing enquiries. Security and abuse reports receive an acknowledgement within five business days; severe incidents are triaged immediately. Enterprise customers have a committed response time in their SLA.
How do I report a bug?
Use the Feedback button in the desktop app (bottom-right corner) to send a bug report with automatic diagnostic information. Or email support@sami-agent.com with a description of what happened, what you expected, and the steps to reproduce it. Screenshots and log excerpts help.
How do I request a feature?
Email support@sami-agent.com with the subject ‘Feature request: <short description>’ and explain the use case. We read every request and incorporate them into planning, though we cannot commit to specific timelines.
How do I get beta access to new features?
Beta features are rolled out progressively. Pro and higher plan users are typically in the first cohort. There is no separate waitlist at this time — upgrading your plan is the best way to access new capabilities early. See the pricing page for plan details.
How do I escalate a critical billing or account issue?
Mark your email subject with “URGENT” and send to support@sami-agent.com. For Enterprise customers, use the dedicated escalation contact in your contract. We monitor for urgent flags outside regular hours.
Question not answered?
We add new common questions to this page regularly. For deeper guides, visit the Help Center. Or reach us directly at support@sami-agent.com — we respond within two business days.