Sim

Native integrations with 1,000+ services documented across communication (Gmail, Slack, Teams, Telegram, WhatsApp), productivity (Notion, Google Workspace, Airtable), development (GitHub, Jira, Linear), CRM and revenue (Salesforce, HubSpot, Attio, Gong), data and search (PostgreSQL, BigQuery, Pinecone, Perplexity, Exa) and security and IT surfaces (CrowdStrike, Okta, AWS IAM), exposed to agents as tools inside workflows; anything not built in connects through MCP support, Sim documentation introduction and integrations catalog 2026-08-02

Sourcedocs.sim.ai/introductionread 2026-08-02

Visual workflow builder with first class control blocks including Router, Condition, Loop, Parallel and a Workflow block for composing sub workflows; agents reason inside Agent blocks and act through tools, and Mothership, the natural language control plane, scaffolds and edits workflows, tables and knowledge bases across the workspace, with API and SDK build paths running alongside the canvas, Sim documentation 2026-08-02

Sourcedocs.sim.ai/introductionread 2026-08-02

Knowledge bases are a first class workspace resource with their own documentation section covering connectors, tag based filtering, chunking strategies and retrieval debugging; agents retrieve relevant passages from customer documents to ground answers, Sim knowledge base documentation 2026-08-02

Sourcedocs.sim.ai/tools/knowledgeread 2026-08-02

Human in the Loop and Guardrails ship as first class core workflow blocks alongside Condition and Wait, and enterprise access control enforces which blocks and model providers each permission group can use at both the UI and execution time, Sim core blocks and enterprise documentation 2026-08-02

Sourcedocs.sim.ai/introductionread 2026-08-02

Strong documented controls: SAML 2.0 and OIDC SSO across Okta, Entra ID, Google Workspace and ADFS, workspace roles and permission groups enforced at execution time, secrets management, organisation wide audit logs, configurable data retention, and data drains continuously exporting logs to a customer owned S3 bucket.

SourceCertification is the gap: SOC 2 and HIPAA are ASSERTED on Sim's own marketing microsite with type unspecified and no trust centre or downloadable report found on sim.ai or the documentation, which grades as asserted rather than verifiable, Sim enterprise documentation and ai4.sim.ai; docs.sim.ai/platform/enterpriseread 2026-08-02

Logs record every run block by block as a first class workspace resource, with dedicated Logging and Alerts documentation, per run cost visibility, enterprise audit logs tracking configuration and security relevant actions, and data drains streaming workflow logs, audit logs and Mothership data to a customer owned S3 bucket or HTTPS webhook on a schedule, Sim logs and enterprise documentation 2026-08-02

Sourcedocs.sim.ai/introductionread 2026-08-02

The Agent block documentation states memory requires a conversation ID to persist across runs and documents four memory modes as agent configuration: None with independent requests, Conversation holding full history keyed by a conversation ID, Sliding Window by messages keeping the N most recent, and Sliding Window by tokens keeping messages up to a token limit.

The Mem0 integration is documented as enabling agents to maintain persistent memory across workflow executions, recalling past conversations, remembering user preferences and building upon previous interactions, with add, semantic search and retrieve operations, and Zep ships as a second external memory option. Tables hold durable structured rows that workflows read and write, and Variables carry in-run state.

Sourcedocs.sim.ai agent block, Mem0 tool and workflow documentationread 2026-08-31

Cloud hosted at sim.ai or self hosted with documented Docker Compose and Kubernetes paths, including a fully offline setup with local models through Ollama, and self hosted deployments unlock the entire enterprise feature set through environment configuration; customer controlled hosting is the strongest deployment shape in the index convention, Sim self hosting and enterprise documentation 2026-08-02

Sourcedocs.sim.ai/introductionread 2026-08-02

Agent skills provide reusable packaged capabilities and Mothership scaffolds complete systems from a natural language description, but no template gallery, prebuilt agent library or marketplace is documented anywhere in the documentation navigation after a two pass check, Sim documentation 2026-08-02

Sourcedocs.sim.ai/introductionread 2026-08-02

Six core triggers documented as their own section: Start, Schedule, Webhook, RSS Feed, Table and Sim Workspace Events, and deployments expose any workflow to the outside world as an API, a chat interface or an MCP server, Sim workflows and deployment documentation 2026-08-02

Sourcedocs.sim.ai/introductionread 2026-08-02

Fifteen plus providers documented including OpenAI, Anthropic, Google Gemini, Groq, Cerebras, DeepSeek, Mistral, xAI and OpenRouter, bring your own key at base provider pricing with no markup, and local models through Ollama or VLLM at no API cost; enterprise permission groups can restrict which providers are allowed, Sim documentation 2026-08-02

Sourcedocs.sim.ai/blocks/agentread 2026-08-02

Open source under Apache 2.0 with the full source on GitHub, a public API and SDKs, a Function block for custom JavaScript, custom tools, and MCP in both directions: agents consume MCP tools and any workflow deploys as an MCP server, with enterprise custom blocks on top, Sim documentation and GitHub repository 2026-08-02

Sourcedocs.sim.ai/introductionread 2026-08-02

The Evaluator block is documented as a core block that uses AI to score and assess content quality against customer-defined metrics, each with a name, description and numeric range, with accuracy, clarity and relevance on one-to-five scales as worked examples.

The block generates a JSON Schema response format from those metrics and enforces strict mode so the model returns only numeric scores, and is documented for quality control and A/B testing, with comparing multiple AI-generated responses as a named use case and assessing Agent block outputs to create feedback loops as documented guidance. A published pattern chains Agent to Evaluator to Condition against a threshold.

Guardrails, knowledge base retrieval debugging, block-by-block run traces and per-run cost visibility support the debugging limb. No retained test set, stored expected outputs or cross-version regression history is documented.

Sourcedocs.sim.ai evaluator block and core blocks documentationread 2026-08-31

The vendor's integrations catalogue ships Browser Use and Stagehand as workflow tools alongside Apify and Bright Data, letting workflows drive real browsers against interfaces that expose no programmatic API, with Stagehand performing natural-language navigation and action on live pages rather than retrieval alone.

Held at Partial because these are third-party browser engines wired in as catalogue integrations rather than an engine the platform owns and operates, which is the published Partial condition for this axis stated in its own terms. Corrected from Full: the ownership point is not a portable principle borrowed from other axes but a distinction this axis writes into its own bar, so the general rule that a component's provenance does not affect a grade does not apply here. Full would need a hosted or local browser or desktop session the platform runs itself.

Sourcedocs.sim.ai tools catalogueread 2026-08-31