Back to vendors
F

Floworks

Also known as: Floworks AI, Alisha AI SDR, ThorV2, One Floworks Technologies

Visit site
GTM / revenue agentindependentVerified 2026-06-30

AI sales employee suite led by Alisha, an autonomous AI SDR on the proprietary ThorV2 model that researches prospects, personalizes email and LinkedIn outreach, and books meetings.

Floworks is a Y Combinator backed sales automation company building a suite of AI employees for B2B revenue teams. Its flagship is Alisha, an autonomous AI sales development representative designed to perform the full outbound SDR job: defining the ideal customer profile, finding prospect lists, researching each prospect across roughly 180 web sources and a contact database of hundreds of millions, writing hyper personalized emails, following up, handling replies and objections, and booking meetings across time zones before updating the CRM. Around Alisha sit other role based agents, including Jesse for research and lead sourcing, Sage for RevOps analytics and forecasting, and helpers for LinkedIn outreach and CRM hygiene.

The technical differentiator is ThorV2, Floworks' proprietary function calling model, which the company describes in an Arxiv paper and benchmarks above GPT-4 and Claude 3 on function calling accuracy, reliability, and latency. ThorV2 underpins Alisha's grounded behavior: users upload product and sales material as PDFs, websites, CSVs, or documents, and when a prospect asks a question the agent answers from that material rather than inventing one, alerting the user when it cannot find an answer. Prospecting uses a chat style interface where an operator can request a precise persona in plain language, for example a VP of Sales at UK healthcare SaaS companies that recently signed an NHS deal, and the research agent assembles the list.

Outreach is omnichannel across email and LinkedIn, so if a prospect does not reply to email, Alisha follows up on LinkedIn. Rather than writing every email from scratch, it starts from a library of proven cold email recipes and personalizes each copy per lead, inserting inline images and links, and it books meetings with warm slot suggestions rather than a bare scheduling link. Setup is meant to be fast, with the company claiming a working AI sales team in about a day once data is connected, and unlimited email warmup is included on all plans. Reported customer results include open rates above forty percent and meeting booking lifts, though independent review volume is still thin.

Floworks offers three tiers, plus a free entry point for the Jesse research agent that needs no credit card. The headline Ultra plan runs $498 a month, which is inexpensive for an autonomous AI SDR, positioned against typical AI SDRs near $2,500 a month and human reps at far more, while lower tiers cover email only and email plus LinkedIn for small teams. CRM sync requires an annual commitment on the paid plans. The main caveat noted by reviewers is deliverability transparency: the platform includes warmup but does not surface inbox placement or detailed mailbox health, which matters for a tool sending at volume, so verifying contact data before launch is important.

Vendor details

Canonical URL

https://www.floworks.ai

Category

GTM / revenue agent

Subcategory

AI SDR (suite of sales AI employees)

Funding status

Independent, Y Combinator backed (One Floworks Technologies, Inc.). Builds a suite of AI sales employees led by Alisha, an autonomous AI SDR, powered by its proprietary ThorV2 function calling model, which the company benchmarks above GPT-4 and Claude 3 on function calling accuracy.

Company status

independent

Use cases & customers

Primary use cases

AI SDR outboundprospect researchpersonalized email and LinkedIn outreachobjection handlingmeeting scheduling

Target customers

startups and SMB sales teamsB2B SaaSmid-market

Deployment options

SaaS

Integrations

Built on the ThorV2 function calling model and integrates with email (Gmail, Outlook), calendars (Calendly, Google Calendar), HubSpot CRM, and LinkedIn, with a contact database of hundreds of millions of records for prospecting.

In practice

You are a founder with no SDR team. You upload your sales docs and connect your inbox, and Alisha researches prospects, writes personalized emails, answers their questions from your materials, and books meetings 24/7.

You need a precise lead list fast. You ask in plain language for VPs of Sales at UK healthcare SaaS that recently signed an NHS deal, and the research agent assembles it.

A prospect ignores your emails. Alisha automatically follows up on LinkedIn, and when they reply with an objection, it handles the response and proposes warm meeting slots rather than a cold scheduling link.

Capability coverage

3.5 / 14 capabilities · 25%

Integrations & Tool CallingBuilt on the ThorV2 function calling model and integrates with email (Gmail, Outlook), calendars (Calendly, Google Calendar), HubSpot CRM, and LinkedIn, solid tool calling, though the integration surface is scoped to the outbound workflow rather than a broad connector library. Partial
Workflow OrchestrationOrchestrates the full autonomous SDR workflow end to end and coordinates a suite of role based agents (SDR, research, RevOps, success), real orchestration, though it runs its own sales motion rather than offering general workflow building. Partial
Knowledge Grounding & RAGGrounded knowledge is a headline capability: users upload product and sales material and the agent answers prospect questions strictly from it, alerting rather than hallucinating when unsure (via ThorV2), and it also conducts deep prospect research across roughly 180 sources, a genuine retrieval and grounding capability. Full
Human Oversight & GuardrailsEmphasizes fully autonomous operation with no documented per message human approval gate; the anti hallucination alert when no grounded answer is found is a narrow safeguard rather than a human oversight system. Unable to verify
Security, Identity & GovernanceNo infosec certifications, SSO, or governance controls are documented; reviewers note enterprise buyers would need to request compliance artifacts. Unable to verify
Observability & AuditabilityOffers campaign and pipeline dashboards but no agent execution tracing; reviewers specifically flag weak deliverability transparency, with no inbox placement or mailbox health visibility. Unable to verify
Memory & State PersistencePersists an uploaded knowledge base and campaign state, but this is a data store rather than a distinct agent memory or state persistence layer. Unable to verify
Deployment & Data ResidencyDelivered only as a cloud native SaaS platform with no self host, on premises, or in VPC deployment option documented. Unable to verify
Prebuilt Agents, Templates & PacksShips a suite of prebuilt role based agents (SDR, research, RevOps, success) plus a library of cold email recipes and playbooks, reusable building blocks, though configured per customer rather than an open marketplace. Partial
Triggers & Channel CoverageOmnichannel across email and LinkedIn with reply triggered follow up (no email reply triggers a LinkedIn touch) and intent data driven prospecting, solid triggering and channel coverage, though limited to two outreach channels. Partial
Model Flexibility & RoutingRuns on the fixed proprietary ThorV2 model with no user facing model choice, bring your own key, or routing gateway. Unable to verify
APIs, SDKs & MCP ExtensibilityNo public API, SDK, or MCP server is documented; ThorV2 is described in a research paper but not exposed as a developer platform. Unable to verify
Testing, Debugging & OptimizationNo user facing agent testing, debugging, or evaluation product is documented; the Sage agent provides campaign analytics rather than an evaluation framework. Unable to verify
Browser & Computer UseIncludes a dedicated LinkedIn automation agent (Linda) that runs automated LinkedIn outreach alongside email, a form of channel automation, though general browser or computer use is not documented. Partial

Recent platform changes

No recent material changes tracked yet.

Pricing

Jesse research agent free · 3 tiers (email-only, email+LinkedIn, Ultra) · Ultra $498/mo · lower tiers from ~$200/mo (unconfirmed) · CRM sync needs annual commitment

Tiered monthly subscription by plan and channel coverage (email-only, email+LinkedIn, Ultra); Pro tier has a per-meeting component; free research agent tier

Public — partialMedium variable costFree tier

Included quota

Three tiers: an email-only plan and an email+LinkedIn plan for small teams (1-9 reps), and the headline Ultra plan at $498/mo. The Jesse research agent has a free, no-credit-card tier. Unlimited email warmup on all plans. CRM sync requires an annual commitment on the paid (Pro/Ultra) plans. Lower tiers are reportedly around $200/mo (competitor-cited, unconfirmed). A per-meeting rate (~$100-300/meeting, unpublished) has been referenced for a pay-per-meeting model. 10% annual discount for YC referrals.

What is public

The Ultra plan price ($498/mo) and the three-tier structure are public; exact lower-tier prices and any per-meeting rate are not officially published.

Billing mechanics

Tiered monthly subscription by channel coverage, with a free research-agent tier and an annual commitment required for CRM sync on paid plans; a per-meeting component is referenced for one tier.

Cost watchouts

CRM sync requires an annual commitment on paid plans. A per-meeting rate may apply on one tier. Weak deliverability reporting means you may need a separate verification/monitoring tool to protect domain reputation. Lower-tier prices are unconfirmed.

Variable cost rationale

The Ultra plan is a flat monthly subscription, so cost is predictable, but a per-meeting (pay-per-meeting) component on at least one tier means cost can scale with booked meetings, and CRM sync requires an annual commitment. Unlimited warmup is bundled, but data verification (to avoid wasted volume) is a separate operational cost.

Additional watchouts

Deliverability transparency is weak: warmup is included but inbox placement (Primary vs Spam) and mailbox health are not surfaced, and warmup cannot be managed separately from sending, which is risky at volume. CRM sync requires an annual commitment. Review base is thin (13 G2 reviews, mostly one region).

Overage / add-ons

Plans scale by channel coverage and seat/volume; a per-meeting (pay-per-meeting) component applies on at least one tier.

Sales call required

No — self-serve available

Free / trial

Jesse research agent free to start (no credit card). 10% additional discount on annual plans for Y Combinator referrals.

Lowest paid plan

Ultra at $498/month (lower email-only and email+LinkedIn tiers exist for small teams, reportedly from around $200/mo but not officially confirmed)

Commercial notes

Among the cheapest real autonomous AI SDRs (Ultra $498/mo). Differentiated by the proprietary ThorV2 function-calling model and grounded, no-hallucination answers. YC referral discount available.

Key ambiguities

Only the Ultra price ($498/mo) is firmly confirmed; lower-tier prices (~$200) and the per-meeting rate are competitor-cited or unpublished.

Cancellation / refund

Ultra can run month-to-month; CRM sync requires an annual commitment. Other terms not detailed.

Support SLA / resale

24/7 support reported; demo/intro-call onboarding; claims a working setup in about a day.

Missing data

Exact lower-tier prices, the per-meeting rate, and detailed plan quotas are not officially published.

Verified 2026-06-30

Contact us

Found a vendor we missed? Have feedback on the index? We'd love to hear from you.

Agentic AI Index

A directory and comparison resource for AI agent platforms, autonomous workflow tools, and enterprise agentic automation products.

© 2026 Agentic AI Index

3801 N Capital of Texas Hwy, Ste E240 · Austin, TX 78746

Researched from public vendor sources. See Methodology.