Senior Workday Talent Engineer

Sharing a draft of Personal Agent Protocol. Since announcing this new protocol on Tuesday with Meta and Genesys, Instinct, NiCE, Rocket, Shopify, Stripe, and Walmart, the response has been overwhelming. So today Sierra is publishing a draft of Personal Agent Protocol, known as Poppy, and announcing an additional 35 design partners: Adyen, Atomic, Bank of America, BBVA, Chime, Cigna, Cloudflare, Comcast, DIRECTV, ElevenLabs, FOX, Gap Inc., GEICO, Hertz, Insurify, Klaviyo, Liberty Mutual, Mastercard, Nordstrom, Notion, Okta, OneSignal, OpenAI, PayPal, Plaid, SiriusXM, Synchrony, Target, United Airlines, Venmo, Visa, Wells Fargo, Zapier, Zendesk, and 1Password. These companies will participate in the design process for the draft Personal Agent Protocol, contributing valuable feedback from their unique business perspectives. Today, when someone asks their personal agent to make a purchase or resolve an issue, it often has to sign in as the customer and navigate pages built for people. Businesses have no standard way to help guide the agent, which limits what the customer, their personal agent and the brand can do directly together. With the Personal Agent Protocol, consumers have choice and control, and companies know when they're dealing with an agent and who it represents. How Personal Agent Protocol works. Poppy is built on the principle that customers decide what access to give their personal agents, and companies set parameters for what those agents can do. This enables companies to work with personal agents in the way that is best for their customers: through their existing websites and APIs, or through an agent of their own. Poppy defines five building blocks for how personal agents and companies work together. * Discovery. Companies publish one file at a standard address on their website (/.well-known/poppy.json). This tells personal agents how to interact with the company, how customers can sign in, and what the agent can do. * Sessions. The personal agent starts a session on its customer's behalf. It can begin as a guest, which may be enough to check whether a product is in stock or ask about a returns policy. The personal agent identifies itself, so the company always knows when an agent is acting for a customer. * Sign-in. When a task needs the customer's account, the person signs in on the company's page through OAuth. If permitted by the company, the agent can sign in on the customer's behalf with a session token that grants only the access the customer approved. * One session across every channel. The same token works for the company's APIs, its website and conversations with its agent. A question asked before sign-in and an order change made afterward are part of the same visit. The customer doesn't have to start over, and the company sees the whole journey instead of disconnected fragments. * Getting the job done. The company decides which channels to offer, based on what works best for its customers: * Its website: the agent browses the company's regular pages, and the company applies the customer's permissions on each one. * Its APIs: the agent connects through interfaces built on standards such as OpenAPI and MCP. * Its own agent: for tasks that need conversation, such as a warranty claim or an exchange. Replies can stream as they're written, and companies can hold a request open until there's news to share. Built on standards companies already use. A company can start with what it already has and add more over time. Companies can connect once through Poppy, rather than building a separate connection for each personal agent. The protocol is built on OAuth, JSON Web Tokens (JWTs), HTTPS, OpenAPI and MCP. Because these are open and widely used, teams can implement it with libraries and tools they already have. The core is also designed to be extended, so industries can build their own layers on top. Protocols such as Universal Commerce Protocol (UCP) focus on shopping, from finding products to checking out and managing orders. Personal Agent Protocol is complementary, covering how a personal agent identifies itself, gets the customer's permission, and works with a company across any kind of task - from buying a sweater to applying for a mortgage. What it looks like in practice. Personal Agent Protocol works whether a company offers its website, its APIs or its own agent. * Through a website. A customer asks their personal agent to return a jacket. The agent finds the retailer using the protocol, identifies itself, and the customer signs in once. The agent then uses the retailer's regular returns page. The retailer knows it's an agent acting for a signed-in customer, and lets it start a return but not change the payment details on file. * Through APIs. A customer's flight is canceled, and they ask their personal agent to rebook them. The agent connects to the airline's booking tools through MCP using the customer's approved access. It finds the next available flight and confirms the seat with the customer before booking. * Through a company agent. At Sierra Summit on Tuesday, Alex McGillis, VP of Product at Rocket, showed the protocol live featuring Meta's personal agent, Muse. Alex asked Muse to get pre-approved for a mortgage. Muse went to Rocket's website, found Rocket's agent through Poppy, and asked Alex for permission to connect. Alex then signed in to share the credit and income details a mortgage needs. The two agents worked through the purchase price, down payment and interest rate and within moments, Alex had a pre-approval letter ready. While he was in control at every step of the way, the agents did all the work. What comes next. This draft is a starting point. Over the next month Sierra will host design workshops and publish a reference implementation to help developers get started. As personal agents grow in popularity and take on more work, its goal is simple: customers choose who acts for them, companies know who they are working with, and both can do so securely and within the boundaries they set. Sierra'd love as many companies as possible to read the draft and help shape this new protocol.

Steering toward a hearing: Second Department reverses summary denial of auto body repair shop dissolution. Recently, my partner Peter Sluka wrote about two Kings County Supreme Court decisions testing the procedural boundaries of shareholder-oppression claims under BCL § 1104-a. One of the lessons from those cases is that procedure can shape the outcome of a case as much as the merits. Today's case highlights that point: Matter of Rizzotto v Romano, 2026 NY Slip Op 05401 (2d Dept 2026). The Second Department provided a lifeline to today's petitioner, reversing summary dismissal of his BCL 1104-a dissolution petition, holding that the supreme court should not have denied dissolution without an evidentiary hearing, and remanding for further proceedings. Manhasset Collision, Ltd. Manhasset Collision, Ltd. ("MCL") is an auto body repair shop on Long Island with approximately 16 employees. Ben Romano (the respondent and majority shareholder) incorporated MCL in 2018 and was its sole owner until recent events. In February 2020, petitioner Anthony Rizzotto acquired a 25% interest from Ben for $200,000 and loaned another $25,000 to the company. Anthony joined MCL after 27 years at Geico. The parties executed a Stockholders Agreement dated February 26, 2020. Key terms of the Stockholders Agreement included: * Management Role: Anthony was designated "manager of the Corporation and will run the day to day affairs." He could not be terminated "other than for cause as defined herein." The Agreement did not define "cause." * Compensation: Anthony's base salary was $2,000/week for an initial six-month period, increasing to $2,200/week ($114,400/year) thereafter. He was also entitled to health insurance reimbursement up to $725/month. * Non-Compete: Restricted area defined as Manhasset; broader restrictions applied in cases of death, disability, or agreed sale. The Stockholders Agreement also contained certain profit-sharing provisions, withdrawal and buyout provisions, as well as provisions concerning the allocation of proceeds should the company be sold. The dispute. The business relationship did not last long. In August 2023, Ben sent Anthony an undated letter purporting to terminate his employment for cause, citing the unauthorized signing of a check in Ben's name, inadequate oversight of shop employees, and unilateral changes to work hours. Anthony rejected the termination, arguing that "cause" was undefined in the Stockholders Agreement, and therefore, Anthony could not be terminated "for cause" or otherwise. On August 16, 2023, MCL withdrew the termination letter and asked Anthony to return to work. About a week later, Anthony returned to work but he contends that the environment was immediately hostile, claiming that Ben assigned him tasks inconsistent with his managerial role (cleaning the attic, organizing auto parts); restricted Anthony's interactions with customers; yelled "I am the owner. I am the boss. I tell you what to do"; and told him he was "fired." Ben's account, unsurprisingly, differs. He contends that upon Anthony's return to work, Anthony became argumentative and refused to accomplish pressing tasks in the shop. Ben claimed he "instructed Anthony that if he refused to do his job as head manager, that he would not get paid, and should leave," but denied ever "firing" Anthony. From that point, August 22, 2023, MCL stopped paying Anthony's salary and health insurance benefits. Anthony did not return to MCL and began working for a competing autobody shop approximately five miles away. Ben, meanwhile, commenced a separate action in Suffolk County seeking a declaratory judgment that Anthony was not a shareholder of MCL - relying in part on the fact that MCL had never issued Anthony a K-1 and that Anthony had insisted on W-2 employee treatment. Anthony's dissolution petition falls short in Nassau County Commercial Division. In January 2024, Anthony commenced a special proceeding by Order to Show Cause seeking dissolution under BCL § 1104-a, an accounting, and interim restraints. Anthony alleged shareholder oppression, including that Ben terminated his employment, ceased paying his compensation and benefits, and misappropriated approximately $500,000 of company funds for noncorporate purposes. In a Decision and Order entered May 24, 2024, Nassau County Commercial Division Justice Jerome Murphy denied the dissolution petition without conducting an evidentiary hearing. The court began with the principle that, in determining whether conduct is oppressive, the majority's actions should not be deemed oppressive "simply because the petitioner's subjective hopes and desires in joining the venture are not fulfilled" and that "[d]isappointment alone should not necessarily be equated with oppression" (citing Matter of Kemp & Beatley, Inc., 64 NY2d 63, 73 [1984]). The court found that Anthony's allegations of oppression and looting, as recited in the Petition, were "largely unsubstantiated." The court further noted that, in opposition, Ben submitted "unrebutted" and "unassailable" evidence - including financial records and an affidavit addressing the challenged payments - as well as evidence that MCL had paid Anthony total compensation of $623,054.57 during his tenure, and that Anthony "refused to return to work" and was working for a competitor. The court concluded that "given the unsubstantiated allegations in the petition, coupled with the Respondent's utterly undisputed evidence, the Court finds the Petitioner has failed to establish either the existence of 'oppressive conduct' or 'looting' thus rendering dissolution inappropriate." Anthony moved for leave to reargue, which motion was denied. Anthony appealed (read the briefs here and here) The Second Department provides Anthony a lifeline. The Second Department disagreed with the trial court's decision, holding that the court "should not have denied that branch of the petition which was for judicial dissolution of MCL pursuant to Business Corporation Law § 1104-a without conducting a hearing." Without engaging in a detailed factual analysis, the appellate court concluded that "[t]he allegations in the verified petition and its supporting papers were prima facie sufficient to establish a basis for judicial dissolution," holding that "[i]n light of the conflicting claims by the parties regarding the relevant facts, the court should have conducted a hearing before determining whether judicial dissolution was warranted." The Appellate Court thus reversed and remanded back to the trial court for further proceedings. Evidentiary hearing or no evidentiary hearing? Is an evidentiary hearing always required before determination of a dissolution petition? The answer is no. Although BCL 1109 requires that the court "shall hear the allegations and proofs of the parties and determine the facts," New York courts have long interpreted that provision to allow a court to make such determination without conducting an evidentiary hearing, where appropriate. CPLR 409(b) directs the Court to "make a summary determination upon the pleadings, papers and admissions to the extent that no triable issues of fact are raised," in determining Article 4 special proceedings governing BCL 1104-a dissolution proceedings. But there also exist numerous appellate authorities remanding a summary grant or denial of dissolution back to the trial court for an evidentiary hearing, just as the Second Department did here, including, for example: Matter of Nicastro v VJN Real Est. Corp., 175 AD 3d 1296 (2d Dept 2019); Matter of WTB Properties, Inc., 291 AD 2d 566 (2d Dept 2002); Matter of Fancy Windows & Doors Mfg. Corp, 244 AD 2d 484 (2d Dept 1997); Matter of Giordano v Stark, 229 AD 2d 493 (2d Dept 1996). The volume of cases going back on remand suggests to me that the question of whether an evidentiary hearing is necessary can be less than clear, even among the judiciary. A word on procedure. On appeal, Anthony emphasized that the trial court struck his request to submit reply papers and then characterized Respondent's evidence as "undisputed." Anthony dedicated a significant portion of his appellate brief to the evidence he would have presented had he been permitted a reply. In New York, reply papers are not permitted on an order to show cause absent express court permission, which is rarely granted. Anthony could (or should) have anticipated that he would not be permitted to submit a reply. His choice not to press the issue until his appeal (which Respondent correctly points out is the first time the issue was raised), was a gamble to say the least. Ultimately, the Second Department's decision rescued Anthony's case - or at least allowed him to live to fight another day. But it calls to mind Peter Mahler's evergreen best-practice exhortation from 2012, which remains good advice today: "If you're a petitioner in a dissolution proceeding you need to load up your petition (or supplemental affidavits) with as many facts as are available in support of your claims."