Guozhen AIGlobal AI field notes and model intelligence

Realtime AI News

Purlin lets real estate agents draft an offer by calling an AI agent

At the EDGE 2026 Pitch Battle, real estate AI platform Purlin showed Voice-to-Offer, which turns a phone conversation into a drafted offer on local contract forms. The company says more than 40,000 real estate professionals use the platform, which bundles search, offers, compliance and closing into one system.

Published

At the EDGE 2026 Pitch Battle, real estate AI platform Purlin demonstrated a feature called Voice-to-Offer: instead of opening a laptop and filling in forms, an agent calls an AI agent, dictates the price, terms and timing, and receives a drafted offer on the local contract forms.

The demo was given by one of the co-founders of Final Offer, according to The Tech Buzz's November 3 report, and the scenario was concrete — a client wants to make an offer right after a showing while the agent has afternoon meetings and a school pickup.

Purlin describes itself as an AI platform covering every step of a deal, from first search to closing, for agents, teams, brokerages, loan officers, title and escrow. Its site lists more than 40,000 real estate professionals on the platform, and the event organizers called it the most scaled of this year's finalists.

Part of that scale came through a merger: in February, Purlin combined with Final Offer, a consumer offer-negotiation marketplace, to unify real estate, mortgage and title in one AI platform, with Purlin founder Giorgi Chigogidze leading the combined company as CEO.

The problem it targets is tool sprawl. Agents tend to own good software that does not talk to the other software, and Purlin's AI connects those systems while adding its own offer, negotiation and contract-compliance tools.

On compliance, Purlin's AI reads contracts, extracts the data and flags Fair Housing risks; the report sums this up as compliance in minutes rather than a manual line-by-line review.

Access is designed around how agents already work: they can call, text or email Purlin, or open a single dashboard that opens with a good morning and lists the day's priorities, commissions, goals, the next paycheck, transaction details, training and AI coaches.

Handing high-frequency, format-heavy, compliance-sensitive paperwork such as offer drafting to a voice agent is a concrete way for agentic AI to move from demos into daily business. The evidence here, though, comes from a pitch-competition stage, so real-world completion rates, coverage of contract forms across states and who is liable when the draft is wrong all remain open questions.

Why it matters

For a paperwork-heavy, compliance-sensitive business like real estate, letting a voice agent produce a signable offer moves AI from search assistance into document production. Whether such products scale depends on covering contract differences across states and settling who owns the error.

PurlinAI agentReal estate
Back to realtime news

Nearby Updates

All

11/04, 04:01

Musk calls Grok Bot costs unsustainable as OpenAI admits Dots is compute heavy

Fortune reports that Elon Musk described Grok Bot's costs as unsustainably high, while OpenAI acknowledged that Dots is compute heavy. The paired admissions put inference economics, long an internal matter, into public view for scaled consumer AI products.

11/04, 03:34

Fal doubles valuation to $16B with $1.3B round led by Bessemer

Fal, a San Francisco startup that hosts and runs AI video, image and audio models, has raised $1.3 billion led by Bessemer Venture Partners at a $16 billion valuation, double what it was worth in April. The round shows investors treating inference as a durable layer of the AI stack even as compute costs keep gross margins thin.

11/04, 04:25

Apple flags AI agent risks in annual report as legal and security exposure grows

Apple's latest annual report flags growing legal and security exposure from AI agents that act on a user's behalf, marking the risk as material to investors. The filing moves the company's disclosure language from what models say to what autonomous agents actually do.

11/04, 03:06

OpenAI Employees Warned About Operational Security Lapses for Years, Report Says

Employees at OpenAI repeatedly raised alarms inside the company about operational security gaps over a period of years, according to a media report citing people familiar with the matter. The warnings concern day-to-day protections around internal systems, access and information rather than model capability itself.