Tana
Summary
Every post-meeting ritual — the action item thread, the Jira ticket nobody filed, the follow-up email that went out three days late — exists because the meeting itself produced no structured output. Tana is an agentic meeting platform that runs inside Zoom, Teams, and Google Meet without a visible bot, turning the conversation into filed issues, updated docs, and refreshed knowledge graphs before the call ends.
The core workflow is: join a call, talk through the work, and let configured agents handle the artifacts. The vendor describes this as 'botless' — participants do not see a recording bot in the call, which removes the social friction that kills adoption on tools like Fireflies or Otter. Agents are configured by describing the workflow in plain language; Tana builds the skills from that description. Integrations cover GitHub, Jira, Linear, Slack, HubSpot, and Google Calendar, with Google Workspace and Microsoft 365 listed as coming. The compounding-knowledge claim — that every meeting feeds a shared context graph so agents never start blank — is the architectural bet that separates Tana from transcript-only tools, and also the one that requires organizational discipline to validate.
Bottom line: Bet on Tana if your product team is drowning in post-meeting artifact work and willing to invest in configuring agents properly; reconsider if your org runs on Microsoft 365, since that integration is not yet available.
Pricing Plans
Subscription- Free Tier
- 5 meetings a month, 50 AI queries, 1 calendar connection
Free
Perfect meeting memory without taking notes. Host 5 meetings a month with AI transcripts and summaries. Connect 1 calendar. View and edit all your content. 50 AI queries.
- 5 meetings/month
- AI transcripts and summaries
- 1 calendar connection
- 50 AI queries
Pro
End the meeting with the work already done. 20× more AI than free. Unlimited hosted meetings. Botless meeting agent. Integrations and full MCP.
- 20× more AI
- Unlimited meetings
- Botless agent
- Integrations and full MCP
Max
When meetings are the job. 5× more AI than Pro. Dedicated support & onboarding. Unlimited agents, skills, and types.
- 5× more AI than Pro
- Dedicated support
- Unlimited agents/skills/types
Business
Intelligence that compounds with every meeting. SAML SSO, advanced security, designated CSM, audit logs, custom DPA.
- SAML SSO
- Advanced security & controls
- Audit logs
- Custom data policies
View full pricing on tana.inc →
Pricing may have changed since last verified. Check the official site for current plans.
Community Performance Report Card
No community ratings yet. Be the first to rate this tool!
Community Benchmarks Community
Sign in to submit a benchmarkNo community benchmarks yet. Be the first to share a real-world data point.
Pros
Sign in to edit- Botless call presence — agents operate inside the meeting without a visible recording bot joining the call — so participants do not self-censor and adoption friction drops compared to tools that announce themselves to every attendee.
- Plain-language agent configuration, so an operations lead can describe a workflow in prose and get a working agent without writing code or hiring someone who can.
- Bidirectional integrations with Jira, Linear, GitHub, Slack, and HubSpot, which means issues and tasks land in the tracker where engineers actually work rather than sitting in a meeting notes doc nobody revisits.
- Compounding knowledge graph across meetings, so agents preparing for next week's all-hands pull last week's committed decisions rather than asking someone to re-summarize what was covered.
- LLM-agnostic architecture, so switching inference providers when cost or capability shifts does not require rebuilding the agent configuration.
Cons
Sign in to edit- Google Workspace and Microsoft 365 integrations are not available; the vendor lists both as coming with an ETA of Q3 2026. Teams whose calendar, docs, and email live in either ecosystem hit a hard wall on the integrations that would make artifact routing automatic — they bridge the gap manually or wait.
- Agent quality is a direct function of workflow description quality. Teams that invest time in configuring skills precisely get specific, routable outputs; teams that do not get a well-organized transcript at best. There is no default agent behavior sophisticated enough to substitute for deliberate setup, which means the first two weeks look more expensive than a transcript-only tool.
- The knowledge graph compounds only if meetings happen consistently inside the platform. A team that routes some standups through Tana and others through a separate recorder ends up with a fragmented context store — agents surface incomplete histories and the compounding-intelligence premise breaks down. Teams that hit this fragmentation typically either mandate full migration or abandon the graph-based features and use Tana as a transcript tool, at which point the cost-to-value comparison against simpler alternatives shifts unfavorably.
Community Reviews
Sign in to write a reviewNo reviews yet. Be the first to share your experience.
About
- API Available
- No
- Self-Hosted
- No
- Last Updated
- 2026-06-12T14:29:29.023Z
Best For
Who it's for
- Teams seeking to reduce post-meeting work
- Users needing botless agents in Zoom, Teams, or Google Meet
- Organizations wanting compounding intelligence from recurring meetings
What it does well
- AI-assisted meeting transcription and summarization
- Real-time document creation and issue filing during calls
- Knowledge graph updates from meeting content
Integrations
Discussion Community
Sign in to commentNo discussion yet. Sign in to start the conversation.
Spotted incorrect or missing data? Join our community of contributors.
Sign Up to ContributeCommunity Notes & Tips Community
Sign in to contributeBe the first to contribute. General notes, observations, gotchas, and tips from people who use this tool day-to-day.
Frequently Asked Questions
- Is Tana free?
- Tana is a paid tool. A 30-day free trial is available.
- Is Tana open source?
- No — Tana is a closed-source tool. Source code is not publicly available.
Hours Saved & ROI Stories Community
Sign in to contributeBe the first to contribute. Concrete time/cost savings, with context. e.g. "Cut my code review backlog from 4h to 45m per week."
Curated lists that include this category
Post-meeting cleanup — filing issues, updating briefs, logging decisions, sending follow-ups — consumes hours that Tana is built to reclaim. The platform embeds AI agents directly into video calls on Zoom, Teams, and Google Meet without surfacing a bot to other participants. During the call, agents with pre-configured skills capture decisions, draft documents, and push structured output to connected tools. The user describes the workflow they want; Tana generates the agents and skills to execute it.
The differentiating architecture is what the vendor calls ‘connected knowledge’: every meeting feeds a shared graph of docs, tasks, decisions, contacts, and projects. When an agent prepares a meeting or drafts a follow-up, it pulls from that accumulated context rather than starting from a blank document. The vendor gives concrete examples — pulling last week’s milestones across product, sales, and ops for an all-hands, or synthesizing patterns across a quarter of customer calls — that suggest the system’s value compounds over time rather than delivering a flat per-meeting utility.
Tana fits teams that already have structured workflows in Jira, Linear, GitHub, or HubSpot and want those systems updated without a manual handoff step. The configurable-agent model means the tool’s usefulness is proportional to the investment in setup; a team that describes workflows precisely gets specific outputs, and a team that skips configuration gets a transcript. Google Workspace and Microsoft 365 integrations are listed as coming with an ETA of Q3 2026, which means organizations whose work lives in those ecosystems face a gap in the integration surface today.
On compliance and data handling, the vendor states SOC2 compliance, GDPR compliance, HIPAA compliance (marked in progress), no training on customer data, SSO support, and an MCP API-first architecture with portable data export. The platform is described as LLM-agnostic, with Claude, Gemini, and Codex listed as connected models, so teams are not locked to a single inference provider.