How does Sigma Assistant work?

Sigma Assistant answers questions inside workbooks and shows its logic and formulas. Sigma Agents can plan multi-step tool use in public beta.

Does Sigma offer a free plan?

Sigma Public is free for public datasets and does not connect to warehouses. Production license prices still require a sales quote.

How does Sigma compare with Dot?

Sigma Assistant works inside Sigma workbooks. Dot connects to an existing stack, including Sigma, and supports Slack, Teams, email, and multi-step investigations.

All comparisons

Dot vs Sigma Computing

Dot is built for conversational analytics across Slack, Teams, and email. Choose Sigma when spreadsheet workflows, write-back, or embedded BI are the priority.

What are the differences between Dot and Sigma Computing?

Showing 26 of 43 capabilities across 10 categories

01 / 10

Who can use it to get answers?

Built for business users, not just analysts

Dot: Yes. Built for business users to self-serve, not analysts
Sigma Computing: Partly. Chat open to all; building needs Build tier Source

02 / 10

Where can users receive answers?

Native Slack app

Dot: Yes. Native Slack app, ask and get answers
Sigma Computing: Partly. Private beta supports conversational data questions in Slack Source

Native Microsoft Teams app

Dot: Yes. Native Teams app, same conversational Q&A as Slack
Sigma Computing: No. Teams integration exports reports via SharePoint, no chat Source

Answers and reports by email

Dot: Yes. Ask Dot by email; scheduled reports land too
Sigma Computing: Partly. Scheduled exports to email; no inbound Q&A Source

03 / 10

Which data sources can it access?

Automatically routes questions to the right data

Dot: Yes. Routes each question across connected sources automatically
Sigma Computing: Partly. Automatically selects sources, not specialized agents Source

Joins data across separate sources

Dot: Yes. Analyze multiple sources in one workspace
Sigma Computing: Partly. Only via pre-built relationships, no ad hoc joins Source

04 / 10

Which business context grounds its answers?

Grounded in dbt models and metrics

Dot: Yes. Uses dbt models and metrics as context
Sigma Computing: Partly. Docs sync; Semantic Layer needs dbt Cloud, SQL Source

Grounded in LookML

Dot: Yes. Uses Looker and LookML definitions as context
Sigma Computing: No. No LookML integration; Looker is a listed competitor Source

Your own metric and term definitions

Dot: Yes. Org metrics glossary, business-term glossary, playbooks
Sigma Computing: Partly. Data Models centralize metrics; no dedicated glossary/playbook layer Source

05 / 10

How do you know the data is correct?

Regression tests for important questions

Dot: Yes. Per-org eval question suites, feedback-driven improvement
Sigma Computing: No. No org-specific eval/training framework found in docs Source

Learns from feedback with human approval

Dot: Yes. Feedback proposes improvements for human approval
Sigma Computing: Partly. Collects feedback; admins refine context and agents manually Source

06 / 10

Who owns and maintains the business logic?

Business context lives in a repository you own

Dot: Yes. Two-way sync with your GitHub or GitLab
Sigma Computing: Partly. Model specs support customer-managed Git and CI/CD Source

Context and apps use Git and pull requests

Dot: Yes. Every publish is versioned through Git and PRs
Sigma Computing: Partly. Code-backed models support versioned context and CI/CD Source

Context stays current when schemas change

Dot: Yes. Schema changes trigger assisted context review
Sigma Computing: Partly. Nightly sync detects changes; model updates need review Source

Context remains portable if you leave

Dot: Yes. Readable context and apps stay in your repository
Sigma Computing: Partly. Exports readable model specs; workbook portability remains limited Source

07 / 10

Which outputs can it produce?

Multi-step investigations, not just lookups

Dot: Yes. Multi-step investigations with parallel sub-agents, shows its plan
Sigma Computing: Partly. Public beta agents plan multi-step tool use transparently Source

Runs Python for statistical work

Dot: Yes. Uses Python during investigations
Sigma Computing: Partly. Python only via Snowflake stored procedures, Admin-gated Source

White labeling and embedded analytics

Dot: Partly. Dashboard embedding; limited white-label controls
Sigma Computing: Yes. White-label embedded analytics for customer applications Source

Notebook or IDE for analysts

Dot: No. No notebook workspace; Python runs internally
Sigma Computing: Partly. SQL/Python as workbook elements, not a standalone notebook Source

08 / 10

Which governance and security controls are included?

Security audit log

Dot: Yes. Security audit log with a SIEM API
Sigma Computing: Partly. Exports to cloud storage; no SIEM API Source

Self-hosting available

Dot: Partly. Self-hosted option at the Enterprise tier
Sigma Computing: No. No self-hosting option documented; AWS/Azure/GCP-hosted SaaS only Source

Uses the platform's native governance

Dot: No. Separate service; only metadata/samples sync to Dot
Sigma Computing: Partly. Snowflake Native App hosts Sigma data path services Source

09 / 10

What is the product built to become?

Purpose-built as a full AI analytics platform

Dot: Yes. Purpose-built for AI analytics across the full workflow
Sigma Computing: Partly. A spreadsheet-native BI platform expanding into AI agents

10 / 10

How do pricing and cost controls work?

Public, predictable pricing

Dot: Yes. Published plan prices
Sigma Computing: No. No public price list; sales-quoted license and credits Source

Hard usage limits, spend visibility, and ROI

Dot: Yes. Set usage limits; track spend and ROI
Sigma Computing: Partly. Seat or contract limits; ROI tracked separately Source

Free tier or trial

Dot: Yes. Free plan, no credit card, unlimited users
Sigma Computing: Partly. Sigma Public is free but lacks warehouse connections Source

Across all 43 capabilities

Dot36 supported2 partial5 not available

Sigma Computing15 supported20 partial8 not available

Category	Decision point	Dot	Sigma Computing
01 / 10Who can use it to get answers?	Built for business users, not just analysts	Yes. Built for business users to self-serve, not analysts	Partly. Chat open to all; building needs Build tier Source
02 / 10Where can users receive answers?	Native Slack app	Yes. Native Slack app, ask and get answers	Partly. Private beta supports conversational data questions in Slack Source
	Native Microsoft Teams app	Yes. Native Teams app, same conversational Q&A as Slack	No. Teams integration exports reports via SharePoint, no chat Source
	Answers and reports by email	Yes. Ask Dot by email; scheduled reports land too	Partly. Scheduled exports to email; no inbound Q&A Source
03 / 10Which data sources can it access?	Automatically routes questions to the right data	Yes. Routes each question across connected sources automatically	Partly. Automatically selects sources, not specialized agents Source
03 / 10Which data sources can it access?	Joins data across separate sources	Yes. Analyze multiple sources in one workspace	Partly. Only via pre-built relationships, no ad hoc joins Source
04 / 10Which business context grounds its answers?	Grounded in dbt models and metrics	Yes. Uses dbt models and metrics as context	Partly. Docs sync; Semantic Layer needs dbt Cloud, SQL Source
	Grounded in LookML	Yes. Uses Looker and LookML definitions as context	No. No LookML integration; Looker is a listed competitor Source
	Your own metric and term definitions	Yes. Org metrics glossary, business-term glossary, playbooks	Partly. Data Models centralize metrics; no dedicated glossary/playbook layer Source
05 / 10How do you know the data is correct?	Regression tests for important questions	Yes. Per-org eval question suites, feedback-driven improvement	No. No org-specific eval/training framework found in docs Source
05 / 10How do you know the data is correct?	Learns from feedback with human approval	Yes. Feedback proposes improvements for human approval	Partly. Collects feedback; admins refine context and agents manually Source
06 / 10Who owns and maintains the business logic?	Business context lives in a repository you own	Yes. Two-way sync with your GitHub or GitLab	Partly. Model specs support customer-managed Git and CI/CD Source
	Context and apps use Git and pull requests	Yes. Every publish is versioned through Git and PRs	Partly. Code-backed models support versioned context and CI/CD Source
	Context stays current when schemas change	Yes. Schema changes trigger assisted context review	Partly. Nightly sync detects changes; model updates need review Source
	Context remains portable if you leave	Yes. Readable context and apps stay in your repository	Partly. Exports readable model specs; workbook portability remains limited Source
07 / 10Which outputs can it produce?	Multi-step investigations, not just lookups	Yes. Multi-step investigations with parallel sub-agents, shows its plan	Partly. Public beta agents plan multi-step tool use transparently Source
	Runs Python for statistical work	Yes. Uses Python during investigations	Partly. Python only via Snowflake stored procedures, Admin-gated Source
	White labeling and embedded analytics	Partly. Dashboard embedding; limited white-label controls	Yes. White-label embedded analytics for customer applications Source
	Notebook or IDE for analysts	No. No notebook workspace; Python runs internally	Partly. SQL/Python as workbook elements, not a standalone notebook Source
08 / 10Which governance and security controls are included?	Security audit log	Yes. Security audit log with a SIEM API	Partly. Exports to cloud storage; no SIEM API Source
	Self-hosting available	Partly. Self-hosted option at the Enterprise tier	No. No self-hosting option documented; AWS/Azure/GCP-hosted SaaS only Source
	Uses the platform's native governance	No. Separate service; only metadata/samples sync to Dot	Partly. Snowflake Native App hosts Sigma data path services Source
09 / 10What is the product built to become?	Purpose-built as a full AI analytics platform	Yes. Purpose-built for AI analytics across the full workflow	Partly. A spreadsheet-native BI platform expanding into AI agents
10 / 10How do pricing and cost controls work?	Public, predictable pricing	Yes. Published plan prices	No. No public price list; sales-quoted license and credits Source
	Hard usage limits, spend visibility, and ROI	Yes. Set usage limits; track spend and ROI	Partly. Seat or contract limits; ROI tracked separately Source
	Free tier or trial	Yes. Free plan, no credit card, unlimited users	Partly. Sigma Public is free but lacks warehouse connections Source
Across all 43 capabilities		Dot36 supported2 partial5 not available	Sigma Computing15 supported20 partial8 not available

Conclusion

Choose for the analytics stack you want to end up with

The decision is not only which tool answers questions today. It is which product can become your analytics platform over time.

Choose Sigma when spreadsheet-style BI and embedding come first

Input tables write budgets and scenarios back to the warehouse.
Pixel-perfect reports support recipient-level bursting and RLS.
DoorDash reports 30% more queries at a flat cost.

Pricing

View, Act, Analyze, and Build prices require a sales quote.
Usage credits apply to rows, integration calls, and exports.
Sigma Public is free without warehouse connections; plan prices require sales.

Source

Choose Dot for best-of-breed AI analytics that can replace BI

Connect Dot to the data sources and semantic models you already have, then start with one agent. Context, apps, and business logic stay version-controlled in a repository you own, so they never become a Dot-only asset. Add dashboards, reporting, and governed workflows as adoption grows, then retire BI software you no longer need.

Watch out

Dot is growing quickly. Its smaller team may not offer the same level of hands-on support as a larger vendor in every region.

Pricing

Free plan, no credit card
Pro at $200/month, or $180/month billed annually. Unlimited users.
Team at $800/month, or $720/month billed annually. Adds single sign-on and row-level security.
Enterprise is custom: self-hosting, SLAs, and volume terms

Full pricing

Why the pricing model matters

Frontier AI has variable inference cost. A vendor that relies only on seat pricing must eventually meter AI, absorb the cost, or limit capability. Dot makes usage visible, lets teams set limits, and tracks the return on that spend.

Receipts

Benchmarked against human analysts, and measured in production

DABStep is Adyen’s public data-analysis benchmark. Dot scored above trained human analysts. It is independently published and available to inspect. In production, customers report these outcomes.

18× ROI

Choco, from time saved on analytics

12,000+ hours

saved every year at Duolingo, across 5,000+ tables

99% faster

time-to-insight at Emerge

€800K found

in a single investigation at KRY

Every Dot answer shows its work. Click any number to inspect the query.