Runtime vs Lorikeet

Lorikeet and Runtime at a glance

Lorikeet is an AI customer concierge for complex support. Its Concierge agent talks to customers over chat, email, voice, SMS, and WhatsApp, and goes past answering questions: it processes refunds, updates accounts, and runs multi-step workflows through your APIs, with "pockets of determinism" for regulated steps and escalation when a person needs to decide. A second agent, Coach, quality-scores every conversation, human or AI. Lorikeet focuses on regulated industries: financial services, healthcare, and insurance. It is for support leaders at fintechs and other regulated companies who want customers answered well and fast.

Runtime is the AI agent harness for payment and fintech teams. Anyone on support, payment ops, risk, compliance, finance, underwriting, or onboarding builds agents from their SOPs. The agents work on isolated computers in your cloud, reach your ledger, processor, databases, and bank portals, and stop for approval before anything moves money. It is for the COO or head of ops who wants agents across the operation, not only at the front door.

How they differ

One team or every team behind the ticket

Lorikeet is built around the support conversation. Its actions run through the APIs you connect, and when a case needs judgment it escalates to your team.

Runtime covers the work that escalation creates. 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 separately in different tools. On Runtime it is one investigation with one record, and support gets a grounded answer back instead of a guess.

Customer-facing quality vs back-office depth

Lorikeet puts its effort where customers see it: tone, multichannel coverage including sub-second voice in the US, UK, and Australia, simulations, Auto QA, and Coach reviewing every ticket.

Runtime is not a customer chat widget. Agents are called from Slack, Teams, email, SMS, voice, or the dashboard, mostly by your own people. Where Runtime goes deeper is the exception work: reading bank files, checking an ACH return code, comparing the ledger to the processor, using a browser on a portal with no API, and drafting the decision with evidence.

Where it runs and who holds the data

Lorikeet is a hosted platform on Google Cloud, US primary, with data residency available in Australia and the EU. It holds SOC 2 Type II, ISO 27001:2022, HIPAA, and GDPR, redacts PII automatically, and has zero-data-retention agreements with its model vendors.

Runtime runs agent computers in your own AWS, GCP, or Azure account, or you self-host the whole platform with Helm. You bring your own models, including open-weight models served in your cloud for PCI and PII work, with routing and fallbacks when a provider goes down. Card numbers and SSNs are stripped from prompts and logs, and the record your sponsor bank asks for stays with you.

Land in support, expand across the operation

Lorikeet grows within support: more channels, more workflows, more tickets resolved.

Runtime starts like a vertical tool, one team and one sharp use case such as "where is my payout" escalations, then becomes the platform the next team builds on. Each run adds to shared organizational memory, so the recon edge case finance solved last month helps support answer the next ticket. Agents can also turn a solved process into a deterministic script that lives in your repos.

Where Lorikeet is stronger

• Customer conversation quality. A purpose-built concierge across chat, email, voice, SMS, and WhatsApp, with simulations and QA before go-live.
• Out-of-the-box support agent. You configure it rather than build it, and it plugs into Zendesk, Intercom, Salesforce, and HubSpot.
• Published compliance posture. SOC 2 Type II, ISO 27001:2022, HIPAA, and GDPR, with reports in a public trust center.
• Coach. Scores every conversation, human or AI, which support leaders use to manage quality.
• Transparent pricing and a free trial. Plans and per-ticket rates are on the website.

Pricing

Lorikeet publishes its pricing. Start is $2,100 per month and Scale is $5,100 per month, both billed annually, plus per-ticket charges for triage, resolution (higher for voice), and QA. Signature is custom for 20,000+ tickets a month. A 30-day free trial is available.

Runtime has three public tiers: Free ($0, one session), Teams from $99 per seat per month, and Enterprise (custom, including self-hosting). The value to weigh is the work of analysts you were about to hire across ops, risk, and finance. Rain replaced $250k in vendor spend with Runtime.

Which should you choose

Choose Lorikeet if

• Your main goal is resolving customer conversations across chat, email, voice, and SMS
• Support is the only team in scope for AI right now
• You want a configured concierge with QA on every ticket, not a platform to build on
• A hosted platform with SOC 2, ISO 27001, and HIPAA meets your security bar

Choose Runtime if

• Escalations need real investigation across the ledger, processor, and bank files
• Payment ops, finance, risk, or compliance also need agents, on one platform
• Card data and PII must stay in your cloud, with models you choose
• You need approvals before money moves and a run record your sponsor bank will accept

Many fintechs will run both: Lorikeet talks to the customer, and Runtime does the investigation behind the ticket.

Frequently asked questions

Is Lorikeet built for fintech?

Lorikeet lists financial services (fintech, banking, lending) alongside healthcare and insurance as its core industries, and its investors and customers include fintech companies. Its Concierge agent handles customer conversations and actions like refunds and account updates, with compliance guardrails and escalation to your team.

What is the difference between Lorikeet and Runtime?

Lorikeet is an AI concierge that talks to your customers and resolves support tickets. Runtime is an agent harness that support, payment ops, finance, risk, and compliance teams use to build agents for internal investigations and operations, running in your own cloud with approvals before money moves.

How much does Lorikeet cost?

Lorikeet publishes pricing: a Start plan at $2,100 per month and a Scale plan at $5,100 per month, billed annually, plus per-ticket charges for triage, resolution, and QA. A custom Signature plan covers higher volumes, and there is a 30-day free trial.

Can I use Lorikeet and Runtime together?

Yes. Lorikeet can handle the customer conversation while Runtime agents run the investigation behind it, such as tracing a stuck payout across the ledger and processor, and hand the finding back to support with a full record.

Does Lorikeet run in my own cloud?

Lorikeet says it is hosted on Google Cloud Platform with US primary hosting and data residency available in Australia and the EU. Runtime runs agent computers in your own AWS, GCP, or Azure account, or fully self-hosted.