ProductsMulti-sourceSelected

Perplexity agents chain Mireye API to screen 327 land parcels

Why we picked it

The notable detail is the agent paying for and discovering a third-party API mid-task, which points to a future where tool selection and micro-transactions happen inside the agent loop. Developers building agent frameworks should study how the workflow budgeted API spend and stacked geospatial, 3D, and video tools. Enterprise teams in real estate or site selection can benchmark their own pipelines against this autonomous approach.

A user asked Perplexity to find land near Sacramento suitable for a 12-cabin build, and the system completed the task end-to-end without human intervention. Perplexity discovered the Mireye API on its own, spent US$2.20 across 31 requests to the Land Search and Enrich API, and cut 327 candidate parcels down to 3 finalists by filtering out plots with over 15% slope, flood zones, wetlands, or protected-land status.

Body

For the finalists, the agent retrieved USGS 3DEP 1m elevation data and NAIP aerial imagery, modeled each site in three.js, picked a winning parcel, and produced a 4K 60fps video recapping the whole process. The demo, shared by Perplexity CEO Arav Srinivas, showcases agentic tool orchestration: API discovery, budgeted spending, geospatial filtering, 3D rendering, and video generation chained in one workflow.

The example illustrates where agentic AI products are heading — autonomous multi-tool workflows where the model plans, pays for API calls, and delivers finished artifacts. For enterprises building land, real estate, or site-selection tools, it signals that agents can now compose third-party data services on demand rather than relying on fixed integrations.

Original · Aravind Srinivas

The level of orchestration here is just incredible Jeff Grimes @jeffgrimes9 A user asked Perplexity to find a suitable parcel of land for a 12-cabin build near Sacramento. Perplexity found the @mireyehq API, spent $2.20 on 31 requests to Mireye's Land Search and Enrich API, and narrowed 327 parcels to 3 finalists by eliminating parcels with >15% slope, flood zones, wetland zones, or protected land. Then Perplexity retrieved USGS 3DEP 1m elevation and NAIP aerial imagery, modeled each site in three.js, recommended a winning parcel, and created this 4K 60fps video to recap its process.

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Products" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Perplexity, Mireye, agents, MCP and tools.

Source attribution: curated from Aravind Srinivas (@AravSrinivas). Cross-source corroboration: 4 independent sources have covered this development (including AI Will, Artificial Analysis, Simon Willison), confirming industry-wide signal strength.

  • AI Will11-19 01:34Source
  • Artificial Analysis11-20 00:59Source
  • Simon Willison11-17 22:40Source