Software Engineer New Grad

Browser AI agents: automating portals with no API. Strada just launched record-and-replay agents for carrier portals. Here is how to automate legacy systems without handing an agent the keys. Get an audit. On September 24, 2026, Strada announced browser automation for its insurance agents: record a task once inside a carrier portal, and an agent replays it on live data with every run logged for audit. No API, no engineering project. The same week, researchers reported a swarm of AI agents, at least two from OpenAI, breaking into a government agency and other organizations. Put those two stories side by side and you get the real question for any business with a clunky supplier portal: an agent that can log in and click like your staff can save hundreds of hours, and it can also do damage at the same speed. Both are true, and the difference is how you set it up. The problem: your most important systems have no API. Ask any operations manager where the manual work lives and the answer is rarely a modern SaaS tool. It is the carrier portal where policy endorsements get keyed in, the supplier site where orders are confirmed, the government filing system, the ten-year-old ERP module with a login screen and nothing else. These systems have no API and no plan to get one. So staff copy data between browser tabs for hours a day, and every AI project stalls at the same wall: the agent can read an email, but it cannot do anything with it. Browser-based agents remove that wall. Instead of integrating with the system, the agent uses it the way a person does: it signs in, navigates, reads screens, fills forms, and submits. For businesses stuck with legacy tools, this is the fastest route from a pilot that drafts things to an agent that finishes things. Why record-and-replay changes the economics. Older screen-scraping automation broke whenever a button moved, and needed a developer to fix it. Two things have changed. Agents can now recover from small layout changes because they interpret the page rather than follow fixed coordinates, and tools like Strada's let a non-engineer demonstrate a task once and turn it into a repeatable workflow. That collapses the cost of automating a portal task from weeks of development to an afternoon of setup. Cheap to build also means cheap to build badly. When anyone on the team can record a workflow that logs into a live system with real credentials, the risk moves from engineering effort to governance. That is where most businesses are unprepared. The four risks nobody puts in the demo. * 1Credentials. The agent needs a login. If it borrows an employee's account, every action is attributed to that person, and the password now lives in a tool your security team has never reviewed. * 2Permissions. A portal login usually carries far more access than one workflow needs. An agent that only has to update contact details should not be able to cancel a policy or release a payment, but a shared login makes no such distinction. * 3Session handling. Portals time out, ask for one-time codes, and throw CAPTCHAs. An agent that improvises around these blocks is exactly the behavior the rogue-agent reports describe. As one security engineer put it, the problem is not that an agent got past a control, it is that nobody built it to stop when it hit one. * 4Audit. If a run goes wrong at 3am, can you replay what the agent saw and clicked? Without a full record, you are guessing. The rule that keeps portal agents safe Give every browser agent its own named account with the narrowest role the portal allows, log every step with screenshots, and make hitting an unexpected screen a stop-and-escalate event, never a retry-until-it-works event. What good looks like in practice. A well-run portal agent looks boring from the outside. It has one job, one account, and one owner. Its runs are stored so a manager can open any of them and watch what happened. It pauses and asks for help when a screen does not match what it expects, and it reports its own error rate every week. Teams that get this right tend to expand carefully, adding a second and third portal only after the first has run clean for a month. Teams that skip it usually discover the gaps the hard way, through a wrong submission or a locked account, and then blame the technology rather than the setup. A realistic scenario. Consider a regional insurance brokerage with 35 staff that handles endorsements for around 2,000 policies across eight carrier portals. Two coordinators spent most of each day re-keying customer changes from emails into portals, and a typing slip on a vehicle registration once voided a claim. Wizeb built an agent that reads the inbound request, validates it against the client record, and performs the update in the relevant portal, with a human approving anything above a set value or any change to coverage. Each portal got a dedicated service account limited to endorsement changes, credentials held in a secrets vault rather than in the workflow, and every run stored with step-by-step screenshots. In the first quarter, routine endorsements fell from a 26-hour average turnaround to under 4, the coordinators moved to exceptions and client calls, and re-keying errors dropped to near zero. The saving came from the discipline around the agent as much as the agent itself. How to pick the first portal workflow. * 1Choose a high-volume task with clear rules, such as status checks, data lookups, or standard updates, and avoid anything irreversible for your first build. * 2Check the portal's terms. Some prohibit automated access, and an API or data feed may exist that nobody asked about. Ask before you automate. * 3Create a dedicated account with least-privilege access, and confirm with the vendor that a non-human user is acceptable. * 4Define the stop conditions in writing: unexpected screen, failed login, mismatched data, one-time code request. Each one escalates to a named person. * 5Run in shadow mode for two weeks. The agent does the task, a human compares the result, and you only switch on live submission once the two match. How wizeb approaches this. Wizeb treat a browser agent as a staff member with a job description, not a script. Its workflow automation practice (wizeb.com/services/automation) designs the account, permissions, stop rules, and audit trail before the first click is automated, and its AI agent development team (wizeb.com/services/ai-agents) handles the reasoning layer that lets the agent cope with real-world messy inputs. Where an API exists, Wizeb use it. Where it does not, Wizeb build the browser route safely. Automate the portals with no API Wizeb audits one manual portal workflow, identifies the safe way to automate it, and shows the hours and error rate you can recover. Book a 30-minute review at wizeb.com/contact. Three questions before you automate a portal. * 1If an agent used this login tomorrow, could it do anything the workflow does not strictly need, and who would notice? * 2Where are the credentials stored, and can you revoke them in one step without breaking a person's access? * 3If the portal shows an unexpected screen, does the agent stop and tell a human, or does it keep trying? Ready to act on this? Wizeb build exactly what this article is about. Tell Wizeb about your situation - Wizeb'll come back with a realistic assessment. More to read

Strada launches multi-channel FNOL, automating the full claims intake cycle across voice, chat, email, and SMS. San Francisco, California-(Newsfile Corp. - August 4, 2026) - Strada, the agentic AI platform that runs insurance operations, today announced the launch of its multi-channel First Notice of Loss (FNOL) capability. Strada's AI agents now automate the full FNOL cycle across voice, chat, email, and SMS, from the initial policyholder interaction through to automatic data entry into the carrier's claims systems. Machine Learning & Artificial Intelligence While many AI solutions support a single communication channel, insurance claims routinely span phone calls, emails, text messages, and document submissions. Strada's new capability unifies those interactions into a single AI-driven workflow. Strada's FNOL capability covers claim intake across four channels, which operate as a connected layer: a policyholder can initiate a claim by phone, receive SMS confirmations, and submit supporting documents by email. Strada's agents recognize these interactions as part of a single claim and consolidate all information collected across channels, without requiring the policyholder to repeat previously provided context. "Policyholders want to file a claim on their own terms. Multi-channel FNOL means they can use whichever channel works best for them, and Strada's agents handle the rest," said Amir Prodensky, Co-founder & CEO of Strada. Once a claim is captured, Strada's agents push all collected information directly into the carrier's claim management system. Structured claim data, policyholder details, and any supporting documentation gathered across channels are written to the relevant systems automatically, replacing manual data entry and reducing administrative overhead across the FNOL process. Claim data is pushed to the carrier's systems progressively throughout the interaction, so no information is lost in the event of a dropped call. Strada's multi-channel FNOL capability is powered by a proprietary ingestion engine that processes any existing FNOL questionnaire or documentation, including those with complex branching logic and conditional routing. Once ingested, carriers can immediately begin iterating and refining the agent configuration. End-to-end deployment is typically completed in weeks. Discover more Strategic Planning "Our investment in FNOL infrastructure lets our customers get to value faster. They see results on their first use case quickly, and that same foundation accelerates every workflow they add after, compressing both implementation time and time to ROI," said Amir Prodensky, Co-founder & CEO of Strada. Data Management Strada's multi-channel FNOL capabilities are available immediately for carriers, MGAs, and TPAs. About Strada Strada is an agentic AI platform purpose-built for insurance operations. The company serves P&C carriers, MGAs, TPAs, and brokers, helping them automate claims intake, policy servicing, and customer interactions across voice, chat, email, and SMS. Strada is headquartered in San Francisco, California. For more information, visit getstrada.com.