Runtime vs Town
Town gives each person a Townie, an AI assistant with its own email that learns how you work. Runtime runs governed agents on payment data for whole teams, in your cloud. Compare data and pricing.
TL;DR
Town is a strong personal AI assistant that learns how you work from your email, calendar, and docs, with no setup. Runtime is the better fit when agents work payment and customer data across several teams and need to run in your cloud, with approvals before money moves and a full record of every run.
| Feature | ||
|---|---|---|
| What it is | ||
| Setup | ||
| Primary job | ||
| Its own identity | ||
| Where it runs | ||
| Bring your own models | ||
| Isolated computer per agent | ||
| Approvals on money movement | ||
| Public self-serve pricing |
Town is a strong personal AI assistant that learns how you work from your email, calendar, and docs, with no setup. Payment operations need team agents that work regulated data in your cloud, with approvals before money moves, not a personal assistant. Runtime is the AI agent harness for payment and fintech teams.
Town and Runtime at a glance
Town is a personal AI assistant. Everyone in Town gets a Townie, an assistant with its own town.com email address, that learns how you work from the tools you already use: email, calendar, Slack, docs, and more than 50 integrations including Gmail, Notion, HubSpot, Salesforce, and Stripe. Townies keep a profile of how you work, take items off your to-do list, run routines such as morning briefings, inbox management, and meeting prep, and suggest repetitive work they could take over. Town Teams lets Townies work together across a team with shared integrations and routines. Town was founded by Jean-Denis Grézé, formerly CTO of Plaid, and Tony Vincent, and raised a $55M Series A led by a16z in June 2026. It is for busy professionals who want a capable assistant without writing prompts.
Runtime is the AI agent harness for payment and fintech teams. Payment ops, risk, compliance, finance, underwriting, onboarding, and support build agents from their SOPs. Each agent works on its own isolated computer in your cloud, reaches your ledger, processor, and bank portals through APIs, databases, MCP servers, and a browser, and stops for a person before anything moves money. It is for operations leaders who want many governed agents running the work of their teams.
Good products, different jobs.
How they differ
Your work vs your team's queue
Town's strength is that it learns you: your clients, deadlines, relationships, and the way you write, then drafts in your voice. The unit is the person and their inbox, calendar, and to-do list.
Payment operations run on queues, not inboxes. A single stuck payment touches four teams: support gets the ticket, payment ops traces it, finance sees a recon break, and risk or compliance may review it. Today each team investigates it separately in different tools. On Runtime it is one investigation with one record, and every run adds to the organization's memory of resolved tickets, fraud caught, and reconciliation edge cases.
Where it runs and who holds the data
Town publishes a solid security baseline: SOC 2 Type II, encryption in transit and at rest, no training on your data unless you opt in, and US hosting on Convex and AWS. It is a hosted service.
Runtime runs agent computers in your AWS, GCP, or Azure account, or you self-host the whole platform with Helm, and you can bring your own sandbox provider. Credentials are masked, and card numbers and SSNs are stripped from prompts and logs. For teams with PCI scope or a sponsor bank reviewing their controls, that difference usually decides the question.
Models and harnesses
Town does not publish which models it uses or a way to bring your own. Runtime lets you use any model, including open-weight models served in your cloud for PCI and PII work, with harness routing (Claude Code, Codex, OpenCode), model routing, and fallbacks when a provider goes down.
Depth on money movement
Town never sends emails or calendar invites without your approval, which is the right control for an assistant. Runtime's controls are built around money: agents start read-only, and approvals sit in front of releasing a payout, applying a reserve, booking a ledger entry, or replying to a sponsor bank. Every run is recorded end to end, including the trigger, every query and tool call, approvals, cost, and result, ready to export for an auditor or examiner.
Self-serve vs a forward-deployed engineer
Town is designed to need no setup at all. Runtime pairs you with a forward-deployed AI engineer whose team built payment and fintech infrastructure at Hulu's payments team at Disney, Finix, Modern Treasury, and BlackRock. The FDE maps your processes, builds the first agents with your team, sets up guardrails, and trains your admins, so your people keep running it after the FDE leaves.
Where Runtime enters the picture
Town is built to run one person's day. Payment operations run on shared queues. When a sponsor bank sends an RFI about a flagged merchant, the answer pulls from onboarding files, transaction history, risk notes, and prior cases, and someone in compliance signs off before it goes back. That is team work on regulated data, and it needs a record the bank can review.
Runtime is the AI agent harness for payment and fintech teams. It gives that work a home in your own cloud.
- No single vendor to depend on. Agent computers run in your AWS, GCP, or Azure account or fully self-hosted, on the sandbox provider you choose with fallbacks, using Claude, GPT, Gemini, or open-weight models, with harness routing across Claude Code, Codex, and OpenCode.
- Guardrails you set. Read-only by default, approval before an RFI response is sent or money moves, RBAC, masked credentials, card numbers and SSNs stripped from prompts and logs, and every run recorded.
- Built for teams. Support, payment ops, finance, risk, and compliance share agents, templates, and one memory, so the next RFI on the same merchant starts from what the last one found.
- An engineer, not an account executive. A forward-deployed AI engineer whose team built payment infrastructure at Hulu's payments team at Disney, Finix, Modern Treasury, and BlackRock maps your processes and builds the first agents with your team.
Create a banking ops agent that handles RFIs, hold-harmless requests, and returns of funds from our partner bank, verifies against our ledger, and drafts replies for my approval.
bank-ops-agent
Tools picked from your prompt
Where Town is stronger
- Zero setup. It learns from work you have already done, with no prompts to write.
- Personal context. A persistent profile of your voice, relationships, and routines.
- Its own email address. Each Townie has a town.com address and can coordinate with other people's Townies.
- Everyday assistant routines. Briefings, inbox management, meeting prep, and relationship tracking out of the box.
- Public, low entry pricing. A free plan and paid plans from $15 per month.
Pricing
Town publishes its pricing. Free ($0, 30 chat messages per month), Starter ($15 per month), Pro ($49 per month billed annually), Power ($99 per month billed annually), and Power Plus ($199 per month billed annually), each with a monthly credit allowance. Team and Team Plus plans pool credits across unlimited seats, and Enterprise is custom.
Runtime is available by request, with custom pricing and self-hosting. Approved teams pilot it free on one real workflow first. Teams usually weigh it against the work of analysts they were about to hire. Rain saved $750k in vendor and salary spend with Runtime, which it uses across technical payment support, fraud and risk transaction monitoring, compliance, cybersecurity, payment operations, engineering investigations, PR reviews, QA testing, and reporting.
Which should you choose
Choose Town if
- You want a personal assistant for email, calendar, meetings, and follow-ups
- You want it to learn your style without setup
- The data involved is everyday business communication, not card data or ledgers
- Self-serve pricing per person fits your budget
Choose Runtime if
- Agents need to work card data, PII, ledgers, or payouts
- Agent computers and models have to run in your cloud
- You need approvals before money moves and a run record your sponsor bank will accept
- Several teams touch the same transaction and should share one investigation
- You want an engineer who has built payment infrastructure to get the first agents live
The two can sit side by side: Town for each person's day, Runtime for the operations that touch money.
Frequently asked questions
What is Town?
Town is a personal AI assistant. Each user gets a Townie with its own town.com email address that learns how you work from your email, calendar, Slack, docs, and other tools, keeps a profile of how you work, and handles to-dos, routines like morning briefings and meeting prep, and follow-ups.
Who founded Town?
Town was founded by Jean-Denis Grézé, formerly CTO of Plaid, and Tony Vincent, formerly of Google AI. It raised a $55M Series A led by Andreessen Horowitz in June 2026, when it opened its assistant to everyone.
Is Town secure enough for fintech data?
Town says it is SOC 2 Type II compliant, encrypts data in transit and at rest, does not train on your data without opt-in, and is US-hosted on Convex and AWS. For agents that touch card data, PII, ledgers, and payouts, many fintech teams also need the agents to run in their own cloud, on models they choose, with approvals before money moves. That is what Runtime is built for.
How much does Town cost?
Town has a free plan and paid individual plans from $15 per month (Starter) to $199 per month (Power Plus, billed annually), plus Team, Team Plus, and custom Enterprise plans. Runtime is available by request, with custom pricing, self-hosting, and a free pilot for approved teams.
Where does Runtime fit next to Town?
Town is a personal assistant for one person's email, calendar, and follow-ups. Runtime is the AI agent harness for payment and fintech teams: shared agents that work RFIs, payouts, and recon breaks on regulated data in your cloud, with approvals before money moves. Town can cover each person's day while Runtime runs the operations.