Video Agent
One walkthrough video. The whole form filled.
Your tech walks the site with the camera running and says what they see. Fieldproxy reads the footage and the narration together, and writes the survey, the inspection, or the damage report.Photos tell you what was there. They cannot tell you the gate code, which plant room the site contact meant, or the thing your tech muttered about the flashing on the way past. The narration carries all of that, and it is read as part of the same clip.
0:13
0:40
1:07
1:33
2:00
2:27
Site survey
Harbor Point · Northwind Property Group
Filled from one 2:40 walkthrough
Recommended works
Coil clean on unit 2 · reseal NE corner flashing
Tech reviews each answer before it is saved.
One walkthrough, the whole survey filled.
Every answer links to the moment it was shown or said.
How it works
How the Video Agent works
Four steps, and the fourth is the one that matters.
- 1
Your tech walks and talks
Camera running, narrating as they go. On mobile they can record it right inside the job; on web they pick a clip that already exists. - 2
Stills are sampled across the clip
Up to 12 frames, evenly spaced, each labelled with its timestamp so the model reads one continuous walkthrough rather than a pile of unrelated photos. - 3
The narration is transcribed
What your tech said out loud is the half a photo can never capture: the gate code, the access instructions, the thing that is wrong but not visible. - 4
Both go to the model together
Not frames then audio. Shown and said are read as one thing, then written into your fields, your dropdowns, your grid rows.
The video never leaves the device
The frames are sampled and the audio is extracted on the phone or in the browser itself. Only a handful of stills and a small audio file are sent for reading. The footage stays where it was recorded.
That matters for site footage more than most things: a walkthrough of a customer's premises records their property, their staff and whatever is lying around. If you do want the clip kept, because the recording is the evidence, you turn that on deliberately and one pick both reads the video and stores it against the job.
Limits
What it does, exactly
No asterisks. These are the real limits.
Up to 12 frames
Clips up to 5 minutes
Narration read to 3 minutes
Silence is fine
Use cases
Where teams point it
Site surveys
Damage and disputes
Install and handover
Multi-line inspections
AI and humans, working together
The clip fills the form. Your tech still checks it before it is saved, and every field says how confident it was. Neither is doing the other's work.
Bring the form you fill after every site visit
On the mapping call we walk your process end to end and find where this fits. Then we configure it on your workflows and you watch it run.
Also works from ChatGPT, Claude and Copilot in Teams
Fieldproxy's MCP server lets your team run the day and change the software itself from the AI assistant they already use, with a confirm step before anything changes.
Pair this agent with
Most teams adopt one agent first, then layer in two or three more in the same week.
Works in every trade