Town vs Vela (2026)

Read and write integrations reach Google, Microsoft and more than fifty business tools, including Gmail (read, search, draft, send, label), Google Calendar (create meetings with Meet links, edit events), Docs, Drive, Sheets, Outlook and Microsoft 365 mail and calendar, Slack (bot and send-as-user), and read-write connectors across CRM (Salesforce, HubSpot, Attio, Pipedrive, Copper, Affinity), project tools (Asana, Jira, Linear, ClickUp, Monday.com, Notion, Todoist), finance (QuickBooks Online and Xero create invoices, Brex, Ramp, Stripe), data (Airtable, Supabase, PostHog, Google Analytics, Hex) and meetings (Zoom, Fathom, Fireflies, Granola, Gong).

Microsoft Entra has its own admin setup. Connectors are native plus Pipedream-backed, actions create, update and send, and OAuth tokens are stored, refreshed automatically and revocable per account. WhatsApp and Telegram are inbound-only. Custom MCP servers can be added too.

Sourcetown.com home; town.com/docs, /docs/safety/security; readread 2026-09-16

The assistant acts in connected calendars, sheets, boards and messaging channels. In the staffing deployment, Vela connects to the client's Google Sheet, where interviewers post availability, and to the Monday.com board, where candidates move through the pipeline. It calls candidates by phone, emails and texts them, creates calendar invites and takes Slack instructions.

Vela reaches Google Calendar and Gmail data through the Google API Services and connects Google or Microsoft calendars, with access the user can revoke. It works over email (Gmail and Outlook), SMS, WhatsApp, Slack, Teams and phone, and it reads and updates connected boards.

Vela publishes no integrations directory, and the only credential scoping it describes is revocable calendar access.

Sourcetryvela.ai/case-studies/scaling-interview-ops, /privacy, home; readread 2026-09-16

Routines can call other routines and mix deterministic code steps with AI steps. A routine can call another routine mid run, in which case the caller pauses until the called routine returns its result, and a parent must list the child in its Callable Routines setting before invoke_routine can call it.

AI steps handle writing, summarizing, deciding and analyzing, while deterministic steps handle filtering, formatting, aggregating and iterating over a list, as in a four step example that gathers and organizes with code, writes with AI and sends with code. Users describe a routine in plain language, set it on a trigger or schedule, and share routines across a team. Town does not describe routine versioning.

Sourcetown.com/docs/routines/custom-routines/concepts/calling-agents, /docs; readread 2026-09-16

Scheduling runs as a branching workflow with retries across channels, configured in natural language. In one staffing deployment, a pipeline change sets Vela to work. It pulls interviewer availability from the connected Google Sheet and calls the candidate by phone first, following up by email if they do not answer. It then books a slot, sends double blind calendar invites and sends reminders 24 and 2 hours before.

On a cancellation it automatically attempts to reschedule by phone, email or SMS, continuing on whichever channel the candidate replies. The customer sets rules in natural language, such as first round interviews lasting 30 minutes and in person interviews 60, and a new client or role takes about 15 minutes to set up. The workflow falls back from phone to email, routes by channel and repeats reschedule attempts, and one system runs across clients.

Vela names no versioning or debugging tools.

Sourcetryvela.ai/case-studies/scaling-interview-ops, home; readread 2026-09-16

Each routine can have one or more triggers and runs whenever any fires, whether that is incoming email, which runs it every time a new email arrives, a smart email trigger that judges a plain language condition with sender and subject filters, outgoing email, email to the assistant, a schedule or a manual run, with meeting start (calendar) triggers on Pro and above.

Triggers can be event driven, scheduled or conversational, several can feed one routine, and the smart trigger still runs if its condition cannot be judged. The Townie is reachable by email, Slack, text messaging, WhatsApp and Telegram (inbound-only), the web app, iOS and macOS. Event and calendar triggers need Pro or a paid team plan, and Starter is schedule only, at most once a day. An authenticated webhook endpoint can also start a routine.

Sourcetown.com/docs/routines/custom-routines/triggers, /docs/billing/plans; readread 2026-09-16

Pipeline changes and calendar conflicts start Vela's work on their own, and people can also reach it through the channels they already use. In the staffing deployment, when a candidate moves to the interview stage on Monday.com, Vela detects the change automatically with no manual trigger.

When a candidate cancels, it attempts to reschedule without human intervention. Vela also monitors availability in real time, reschedules automatically if conflicts arise and follows up when someone does not respond. Users start work by CCing vela@yourdomain.com on email, SMS or WhatsApp, texting Vela or messaging it on Slack.

Vela does not say how it handles duplicate triggers.

Sourcetryvela.ai/case-studies/scaling-interview-ops, home; readread 2026-09-16

The Townie, Town's assistant, is grounded in the user's connected email, calendar, chats, contacts and tools, queried at run time rather than indexed.

Every integration added, such as Slack, Notion, Drive, Linear or GitHub, becomes another source of context, and the integrations offer search and read tools (Gmail search, Drive search and read, Box files and metadata, Notion pages and databases, Granola and Fireflies transcripts).

Access to connected sources follows each account's permissions and the routine's account scope, and new knowledge comes from connecting a source, not from retraining. No index or search layer over connected content persists between runs. The Wiki and memories summarize the user rather than index their content.

Sourcetown.com/docs/features/context-and-memory, /docs integration directory; readread 2026-09-16

Scheduling decisions draw on the thread, calendars and sheets Vela is connected to, assembled at run time. Vela reads context from the thread it is copied on and reads the user's calendar. In the staffing deployment it reads interviewer availability directly from a connected Google Sheet, the source of truth, and matches candidates to open slots by time zone, duration and location. It sees only the conversations and calendars a user brings it into.

Vela names no maintained index, knowledge base or citations for its answers.

Sourcetryvela.ai/case-studies/scaling-interview-ops, home, /privacy; readread 2026-09-16

The Townie remembers who the user is, their preferences, and notes on contacts and people. Memories are either global, applying to everything across all routines, or specific to one routine, and a run automatically receives all global memories plus those for that routine. Memory carries over between Slack, email, the app and the Mac app, and users view and delete memories in Settings > Profile or by asking, for example to forget a preference about Friday afternoons, and can add, change or remove anything.

A Wiki synthesizing profile, preferences, goals and projects is refreshed every night, retiring what is stale, and is editable line by line, with Recent Updates showing what changed. Memories last until the user removes them, with nightly retirement of stale entries, and can be deleted without deleting any email, event or document. Town does not say what should stay out of long term memory.

Sourcetown.com/docs/features/context-and-memory, /docs/features/wiki; readread 2026-09-16

A scheduling conversation carries across channels. In the staffing deployment, if a candidate replies to a confirmation email or calls back the number that contacted them, Vela continues the conversation across channels. Customers write standing natural language instructions for each workflow, and scheduling preferences are among the information Vela collects.

Vela names no memory layer and no way to review, edit or delete what it remembers.

Sourcetryvela.ai/case-studies/scaling-interview-ops, /privacy; readread 2026-09-16

Approval modes are configurable at the routine, tool and session level. Every routine has a default mode, which is autonomous, approval required or read only, and in approval required mode, actions that make changes create approval requests with approve or reject options and run only after the user approves them. Per-tool permission levels override the routine mode (Auto, Ask each time, Always allow), so labeling can run autonomously while email sending always waits.

Chat sessions run "Ask before any changes" by default, "Always allow safe actions" or "Allow all actions", with Allow once and Always allow per approval. Town also flags routines that combine private data, untrusted input and external sending (a lethal-trifecta warning) when they are saved, and keeps external-send tools on approval under safe mode. Low-risk and high-risk actions can run under different autonomy modes, and the warning explains why a checkpoint fired. Approvals arrive in the app and through notifications, with no routing into ticketing systems.

Sourcetown.com/docs/safety/modes-approvals, /docs/safety/security; readread 2026-09-16

After multiple failed attempts, Vela escalates to a person on the team. It holds a permission step by default, and the customer can lift that step for a named type of action through natural language instructions. One customer told it, on rejection, to call the candidate back immediately to reschedule without asking permission. Autonomy is set per action this way. Vela's terms warn that AI generated suggestions can be wrong and leave the user responsible for reviewing outputs and final decisions, such as sending a message or confirming a time.

Vela does not say whether approvals can be routed to other channels.

Sourcetryvela.ai/case-studies/scaling-interview-ops, /terms; readread 2026-09-16

Town is SOC 2 Type 2 compliant, with its security controls independently audited, and it links to a Security Portal and a Subprocessors list. Routines operate within strict account boundaries with configurable scope (the trigger account only by default, all accounts, or specific accounts), tools can only reach accounts connected through OAuth with revocable access, and optional domain allowlists and recipient limits apply to email.

Prompt validation blocks instruction-override and exfiltration patterns, and lethal-trifecta detection flags routines that combine private data, untrusted input and external sending. Data is not used to train AI models unless the user opts in, and is encrypted in transit and at rest. People sign in with Google or Microsoft accounts, including Microsoft Entra ID, and Teams plans add domain capture.

An Entra admin can grant consent for the whole tenant and then either let every user in the tenant sign in or restrict access to chosen users and security groups, and Google Workspace has its own admin guide. Town does not mention SAML single sign on or SCIM provisioning for team admins. SOC 2 Type 1 and Type 2 reports, the latest penetration test and a CASA Tier 2 assessment are available under NDA through trust.town.com.

Traffic uses TLS 1.2 or 1.3, data at rest uses AES 256 GCM with extra encryption on connected account tokens, Enterprise agreements can enforce no training for every user, and no Town team member has production database access.

SourceTown, town.com/docs/admin-setup/microsoft-entra, /docs/safety/security and town.com/trustread 2026-10-05

Administrative, technical and organizational safeguards protect customer data, including encryption in transit and at rest. Vela's AI providers are contractually prohibited from training their models on customer content. Google user data follows the Google API Services Limited Use requirements, and people read it only in listed cases. Calendar access can be revoked at any time, and integration data travels over encrypted channels, with encryption at rest required of providers.

Vela names no certification or attestation report and no customer facing access model, such as roles, SSO or SAML.

Sourcetryvela.ai/privacy, /terms, /trust (404); readread 2026-09-16

Each action is logged with what was done, when, why (the routine's reasoning), what triggered it and the result, success or failure, for auditability, debugging and accountability. Users open a routine, view the session history, and review actions taken and their reasoning. A separate security event log records blocked prompt injections, suspicious prompts, blocked tool outputs and unauthorized recipients, and custom tool results show up in the run history. There is no export to monitoring or SIEM tools, and no retention period by plan is given.

Sourcetown.com/docs/safety/security, /docs/integrations/mcp-servers; readread 2026-09-16

Operations teams get one dashboard over the scheduling work and a measure of time saved. In the staffing deployment, the operations team went from monitoring 17 systems multiple times a day to checking one dashboard. Once deployed, Vela measures the actual time it saves, and reminders and confirmations go to all parties.

Vela names no step by step view of what it did, no activity history per meeting and no audit log of what it sent and changed.

Sourcetryvela.ai/case-studies/scaling-interview-ops, home; readread 2026-09-16

Town hosts the service in the US on Convex and AWS. There is no region choice, self hosting or customer environment option, and the Teams and Enterprise plans cover billing and credits, not deployment.

Sourcetown.com home; town.com/docs/billing/plans; readread 2026-09-16

This is a cloud service, run by a company headquartered in the United States that may process personal information in the United States and other countries, with Standard Contractual Clauses where required. No hosting region is published, and Vela names no residency choice or customer hosted option.

Sourcetryvela.ai/privacy, /terms; readread 2026-09-16

Ready made routines sit in a browsable catalog, each a complete job a user enables.

The catalog filters by Inbox, Calendar, Meeting Prep, Stay Informed and Relationships, with a Browse all Routines view, and its entries include Auto-inbox (watches new email, labels, drafts replies, helps schedule), Decline Cold Outreach, Schedule Optimizer, Meeting Briefing, Contact Research Dossier, Morning Briefing, Competitive Intel Briefing, Newsletter Digest, GitHub Reports, Relationship Reconnect, Deal Spotter and New User Research.

A Stock Routines index has per-routine pages, and routine sharing and discovery let teams install and reuse shared routines. Each routine runs whole without the others, and routines are edited in plain language ("change my morning briefing to include..."). The routines cover personal productivity rather than specific industries, and no customer references are tied to them.

Sourcetown.com home; town.com/docs; readread 2026-09-16

One scheduling assistant, configured per client, is the whole offer, sold as one assistant for all your meetings from end to end. In the staffing deployment, the customer sets up each client's workflow in natural language instructions in about 15 minutes. Vela publishes no catalog, template library or set of agents to adopt separately, and the site has only three case studies.

Sourcetryvela.ai home, /case-studies/scaling-interview-ops, /sitemap.xml; readread 2026-09-16

Town routes between models on its side, names no models and offers no choice. Priority model routing is a feature of the Power, Power Plus and Team Plus plans and is among what pauses on cancellation. No model or provider is named and customers cannot choose one, and the models in the Cursor integration are Cursor's. Town's no training commitment covers its providers without naming them.

Sourcetown.com/pricing; readread 2026-09-16

The service runs on unnamed third party AI models. Vela uses third party AI model providers to power features of the service, under terms that bar them from training on customer data, and lists them among its service providers. It names no model or provider, describes no routing between models and mentions no model choice for the customer or an admin.

Sourcetryvela.ai/privacy; readread 2026-09-16

Outside systems can reach Town in two ways, but Town has no REST API, SDK or MCP server of its own.

Through a webhook trigger, an external system starts a routine by sending an authenticated HTTP request to a routine specific URL, with a per routine bearer secret and rotation, JSON or text payloads, an idempotency header, rate limits and defined 202, 400, 404, 413, 415 and 429 responses, from Zapier or the customer's own app or backend.

Through custom integrations, users add MCP servers by URL, Town runs OAuth or dynamic client registration, and the tools are enabled per routine, so Town consumes MCP as a client. A trigger endpoint returns only an acceptance. The api.town.com host shows only the Convex backend banner, with no developer documentation.

Sourcetown.com/docs/routines/stock-routines/webhooks, /docs/integrations/mcp-servers; api.town.com; readread 2026-09-16

Whether Vela offers an API is not public. The site has only three case studies and links no developer, docs or API page.

Sourcetryvela.ai home FAQ; triedread 2026-09-16

A new or changed routine can be tried against real input, with its attempted actions reviewable, before it is allowed to act. Read only mode runs a routine that can read and analyze but blocks every change, and Town suggests it for testing new configurations, as it does the manual trigger for testing new routines. Each run's session history shows the actions the routine took and its reasoning, and read only runs still send their results to the user.

Reviewing a read only run before switching the routine to approval required or autonomous shows how the agent behaves before release. When a smart email trigger cannot judge its condition, the routine runs anyway. There are no fixtures or datasets, scored test cases or quality scores over time, and testing uses a mode rather than a dedicated harness.

Sourcetown.com/docs/safety/modes-approvals, /docs/routines/custom-routines/triggers; readread 2026-09-16

What Vela measures is the customer's outcome after it goes live. It tracks the actual time saved once deployed, a measure of the customer's scheduling load. The Scheduling Benchmark is a published study of scheduling emails, not a tool customers run. Setup happens in natural language with no test step, and Vela names no simulation, test run or scored evaluation of its own behavior.

Sourcetryvela.ai home, /case-studies/scaling-interview-ops; readread 2026-09-16

Town has no browser, desktop or computer control. Actions run through named integrations with read-write tools, a run_code sandbox with optional internet access, and email, Slack and messaging channels. Town Desktop is a macOS app for native desktop workflows and notifications, a way to reach the assistant rather than an agent that operates the screen.

Sourcetown.com/docs, /docs/safety/security; town.com home; readread 2026-09-16

The assistant works through email, SMS, WhatsApp, Slack, Teams and phone calls, connected calendars, and connected Google Sheets and Monday.com boards. Vela names no browser, desktop or screen operation.

Sourcetryvela.ai home, /privacy, /case-studies/scaling-interview-ops; readread 2026-09-16