Your Decagon agent can now search the live web
Posted on August 28, 2026

Article
An agent's knowledge base is only as current as the last time someone updated it. But customers ask about things that change by the hour: outages, pricing, shipping delays, news that just broke.
Without a way to check the live web, an agent either guesses or has to hand the conversation off, even when the answer is publicly available a search away. Today, every Decagon customer can turn on live web search in their agent settings using Perplexity's Search API.
Why customer-facing agents need current information
Your agent has always been grounded in a company's own knowledge. Help center content, CRM records, and internal documentation resolve the overwhelming majority of customer questions with high accuracy.
Some questions reach past that boundary. A traveler wants to know whether an entry requirement changed this week. A cardholder asks whether a payment network is having a known outage. These questions require time-sensitive answers, and until now they lived outside what an agent could reach.
Live web search extends that grounding from a company's own knowledge to the open web, with the same source attribution and accuracy standards enterprise teams expect.
What live web search unlocks
Once an agent can search the web mid-conversation, a whole category of questions stops being an escalation. Some examples:
- A policyholder asks whether their state has changed its minimum coverage requirement. The agent checks current regulatory sources and answers with a citation.
- A shopper references a product they saw mentioned in an article. The agent cross-references it against live web information and the current catalog.
- A customer reports trouble with a third-party carrier or payment provider. The agent checks for a known outage before troubleshooting further.
- A traveler asks whether weather or a local disruption will affect a scheduled booking. The agent checks live conditions and advises on options.
Every answer is grounded in a real-time search with cited sources.
Why we chose Perplexity’s Search API
We evaluated several options for live web grounding against four criteria.
- Answer quality. Relevant, source-linked results that hold up under scrutiny.
- Efficiency. Compact, high-signal responses that leave room for the agent to reason and hold conversation context.
- Latency and scale. Fast responses across millions of conversations a day.
- Enterprise readiness. Infrastructure already trusted for high-stakes use cases.
Perplexity's Search API led on all four. It provides access to the same index of hundreds of billions of web pages behind Perplexity's answer engine, with real-time indexing that processes tens of thousands of updates per second. New content becomes searchable almost immediately, so agents work from the latest information.
Get started
Live web search is available to all Decagon customers as a Tool Template. Customers can also reach out to their Decagon account manager to claim $1,000 in search credits, enough for 200,000 queries.
If you're interested in seeing how Decagon agents can ground conversations in live web data, book a demo.
Start improving your workflow with Decagon
With Decagon, CX teams don’t have to guess whether a change will improve CSAT or deflection. They can move quickly, measure what matters, and act on what works.
Join us
There are very few places where you can prototype with frontier LLMs, ship to production in days, and watch users engage with the systems you built—all while owning the entire stack, from intent parsing and tool usage to API integration and observability. This role at Decagon is one of those places.
From my own experience working across both agent development and broader engineering initiatives at Decagon, I’ve seen firsthand how uniquely impactful this work can be. Whether I’m building intelligent workflows for customers or designing infrastructure that supports our agent platform, it’s rare to find an environment where the work transitions from concept to production within days, actively powering user experiences and transforming how businesses operate.
If you’re looking for a role where you can:
- Build at the frontier of LLMs, automation, and user interaction
- Deploy AI agents that solve high-value business use cases across industries including retail, travel and hospitality, fintech, edtech, and more
- Work directly with customers on high-impact use cases
- Ship fast, iterate constantly, and own your work from idea to production
- Join a fast-moving, collaborative team solving real-world challenges with AI
We’d love to hear from you!
The AI concierge for every customer.

