Sierra

What it does

Writes code

PartlyGhostwriter turns a prompt, an SOP or a transcript into a production agent journey with workflows and guardrails; what it authors is agent configuration, not application source code.Build or modify agents by describing how you want them to behave. Update workflows, systems integrations, guardrails, tone, and style with simple…sierra.ai/product/ghostwriter ↗

Debugs and fixes

PartlyGhostwriter diagnoses its own failed simulations and implements the fix; the failure it repairs is agent behaviour, never a defect in your software.When a simulation fails, Ghostwriter diagnoses the issue and implements the fix, so your agent keeps improving without manual debugging.sierra.ai/product/ghostwriter ↗

Writes tests

PartlyIt generates and runs conversational test suites for the agent you build, which is testing, but not unit tests over a code repository.Build a test suite to detect and prevent potential regressions prior to releasing new versions of your agent.sierra.ai/product/agent-studio ↗

Ships it

PartlyIt ships agent versions rather than code: publishing to ChatGPT can run through CI/CD, but nothing deploys application software.Make your agent available on ChatGPT with the push of a button or via CI/CD.sierra.ai/product/channels ↗

Done-for-you service

PartlyYou license software and get Sierra's own agent-development team alongside it, so delivery is a partnership rather than pure self-serve tooling.Work with an expert agent development team that has supported hundreds of deployments — and will keep you ahead as AI evolves. Only pay for the value…sierra.ai/product ↗

How much it does unattended

Runs autonomously

YesAgents resolve end-to-end customer requests without a human in the loop, including email replies and multi-step actions in systems of record.Autonomously respond to customer emails, reducing response times and freeing up your support team.sierra.ai/product/channels ↗

Multi-agent

PartlyTwo vendor agents hand work to each other — Explorer's findings go straight to Ghostwriter — but customer-built agents coordinating on one task is not documented publicly.Send any recommendation directly to Ghostwriter, and it implements the improvement automatically, without any manual work on your part.sierra.ai/product/explorer ↗

Agent permissions

YesAutonomy is configurable per workflow: you set goals and guardrails and name the steps that require human sign-off before the agent proceeds.Define what the agent can do on its own, and where human sign-off is required.sierra.ai/product/horizon ↗

Which models it runs on

Claude

PartlyAnthropic is a named AI-services subprocessor, so Claude is in the mix, but Sierra routes models itself and never exposes a Claude selector.Anthropic, PBC • AI services • United Statestrust.sierra.ai/subprocessors ↗

GPT

PartlyOpenAI is listed as an AI-services subprocessor, so GPT models are used under the hood, chosen by Sierra's router rather than by the buyer.OpenAI, L.L.C. • AI services • Global (localization available in United States, European Union)trust.sierra.ai/subprocessors ↗

Open models

PartlySierra states it blends open-weight models into its constellation, but the buyer neither picks nor supplies them and no model names are published.Sierra is built on a constellation of LLMs—combining frontier, open-weight, and proprietary models—so your agent can execute seamlessly and reliably.sierra.ai/product/trust-and-reliability ↗

Model choice

NoModel selection belongs to Sierra: it routes each turn to what it judges optimal and swaps providers on outages, with no published customer model choice.Sierra automatically switches between LLM providers to optimize your agent’s performance and maintain service continuity in case one provider…sierra.ai/product/trust-and-reliability ↗

Where you use it

In your editor

PartlyAgent SDK journeys are written in your own editor and software lifecycle, but Sierra ships no editor extension and the agent itself runs in customer channels.Develop agents in your existing programming environment and software development lifecycle.sierra.ai/product/agent-sdk ↗

In your pipeline

PartlyPublishing an agent can be driven from CI/CD for the ChatGPT channel; Sierra publishes no broader pipeline or pull-request integration.Make your agent available on ChatGPT with the push of a button or via CI/CD.sierra.ai/product/channels ↗

In a browser

YesAgent Studio is a hosted web application where non-technical teams build journeys, manage knowledge and run simulations without code.Empower teams to build and manage agents—no code requiredsierra.ai/product/agent-studio ↗

Not established: On the command line

Whose machine it runs on

Self-hosted

NoSierra runs the platform in its own cloud on AWS, offering regional localization rather than deployment onto customer infrastructure.Amazon Web Services, Inc. • Data storage, cloud hosting, and AI services • Global (localization available in United States, European Union, Southeast…trust.sierra.ai/subprocessors ↗

Open source

NoThe platform and its documentation are contractually confidential, which rules out any source-available or open-source distribution.All Sierra Products are confidential, and you will not use or disclose them other than to evaluate the Sierra Products.docs.sierra.ai ↗

What it costs to run

How it meters

YesBilling is per achieved outcome rather than per seat or per token, which Sierra states as its deliberate business model.At Sierra, we've pioneered an entirely new business model - outcome-based pricing - where you pay only when the software achieves specific, valuable…sierra.ai/product ↗

Free tier

NoNo free tier, trial or self-serve signup: sign-in requires a company deployment that already exists, and every call to action is a contact form.Enter your company's Sierra URLsierra.ai/login ↗

API access

YesA headless API is one of the published deployment surfaces; the reference is behind the docs sign-in, so endpoints, auth and limits are not public.Because ADP is powered by Agent OS, you can build once and deploy everywhere you are — chat, phone, SMS, email, contact center conversations, or via…sierra.ai/blog/agent-data-platform ↗

MCP server

PartlyAgents are exposed over MCP for the ChatGPT Apps channel; a general MCP server other agents may query is not documented publicly.Sierra agents are natively compatible with ChatGPT Apps via Model Context Protocol (MCP).sierra.ai/product/channels ↗

Bring your own key

NoSierra supplies and routes the inference itself through its own model subprocessors; no bring-your-own-key, own-model or own-cloud option is published.Sierra will power your AI agent with the best available LLMs in the industry, so you (and your customers) are always benefiting from the latest…sierra.ai/product/trust-and-reliability ↗

Buying it for a team

A company can buy it

YesThis is sold only to organisations, with large regulated enterprises named as the customer base and no individual sign-up path.40% of the Fortune 50 partner with Sierra.sierra.ai/product ↗

Seat model

NoPricing is not seat-based: Sierra charges for delivered results, so no per-seat rate, floor or ceiling is published.It's Sierra's outcomes-based model at scale: you pay for results, not tokens.sierra.ai/product/horizon ↗

Admin controls

YesAdministrators constrain the agent through goals, guardrails, topic filters and human sign-off points defined before anything reaches customers.Sierra has built-in filters and monitors for topics and keywords that are off-limits based on your company policies.sierra.ai/product/trust-and-reliability ↗

Audit log

PartlyAgent decisions, tool calls and suppressions are auditable in Insights and Horizon; logging of administrative actions by staff is not documented publicly.Understand the reasoning behind every agent action or answer—view knowledge sources, systems accessed, and more.sierra.ai/product/insights ↗

Not established: Pooled budget, Single sign-on

What happens to your code

Opt out of training

YesSierra states customer data is never used to train models at all, so there is no opt-out to negotiate per tier.Your data is never used to train models, and we use industry-standard best practices to ensure its security.sierra.ai/product/agent-sdk ↗

Data residency

PartlyRegional hosting localization is offered in the US, EU, Southeast Asia, Japan and Australia, but some AI subprocessors are US-only or global.Global (localization available in United States, European Union, Southeast Asia, Japan, Australia)trust.sierra.ai/subprocessors ↗

Getting out

PartlyA control commits to deleting customer data on departure, yet no customer-facing bulk export path or credit-expiry rule is published.Customer data deleted upon leavingtrust.sierra.ai/controls ↗

Certifications

YesAn unusually wide certification set is claimed and mirrored in the Trust Center, covering SOC 2, ISO 27001, ISO 42001, GDPR, HIPAA, PCI and FedRAMP High.Sierra is committed to maintaining the highest compliance standards for our customers, including SOC 2, HIPAA, GDPR, PCI, FedRAMP High, CCPA, CSA…sierra.ai/product/trust-and-reliability ↗