Complete AI Training
Sign inGet my AI kit

Your job's AI kit

Get your AI kit

Tell us who you are and what you do. We show you your kit right away and email you the link: skills, prompts, AI agents, MCP servers and courses for your job.

500+ jobs ready, and we make a kit for any other job. No payment needed to look.

Share

AI agent for speech therapists

AAC Device Trial Tracker Agent

Reach a device recommendation backed by enough usage data.

AAC Device Trial Tracker Agent: what goes in, what the agent does and what you get

What it does

Choosing an augmentative communication device needs data from real use, but trials end with opinions. This agent plans the trial period, schedules sessions with each device and sets what to measure, such as messages sent, symptoms of fatigue, access errors and partner feedback. It collects usage logs and session notes, compares options on the same measures, and drafts a recommendation with the evidence. If data are thin, for example too few sessions on one device, it adds a trial session before it drafts. The therapist approves the plan, extra sessions and the final recommendation. Edge case: one device had a week of technical problems, so the agent marks that week as invalid instead of counting it.

How it works

Follow the arrows from top to bottom. The orange dashed arrow is the loop: when a check fails, the agent goes back and tries again.

Start and resultWhat it doesA check on its own workWaits for your OKGoes back and retries
ApprovedYes, continueApprovedNo 1 STARTS WHEN Device trial begins 2 DOES Set measures and a session plan for each device 3 YOU APPROVE Therapist approves the plan 4 USES A TOOL Schedule sessions and collect usage data 5 USES A TOOL Read logs and notes after each session 6 CHECKS THE RESULT Does each device have enough valid sessions? If not: add a trial session and mark invalid days. Backto step 4. 7 DOES Compare the devices on the same measures 8 DOES Draft the recommendation with evidence 9 YOU APPROVE Therapist approves the recommendation 10 RESULT Trial report
Read the steps as a list
  1. Device trial begins
  2. Set measures and a session plan for each device
  3. Therapist approves the planThe agent waits here for your OK.
  4. Schedule sessions and collect usage data
  5. Read logs and notes after each session
  6. Does each device have enough valid sessions?If not: add a trial session and mark invalid days. Back to step 4.
  7. Compare the devices on the same measures
  8. Draft the recommendation with evidence
  9. Therapist approves the recommendationThe agent waits here for your OK.
  10. Trial report

How it decides

It recommends a device only when each option has the minimum sessions and comparable measures.

  • Require at least 5 valid sessions per device
  • Mark technical failure days as invalid
  • Compare on the same goals and tasks
  • Weigh caregiver feedback with the usage data

Make it yours

Every agent is a starting point. You choose these settings for your own situation.

  • Minimum sessions (default 5)
  • Measures tracked
  • Trial length
  • Who gives feedback

What keeps you in control

It always asks you first

  • Therapist approves the plan, extra sessions and the recommendation

Hard limits

  • Never recommend without enough data
  • Never purchase a device

It stops when

  • Done: recommendation approved
  • Stop: client withdraws from the trial

Set it up

We guide you through the set-up, step by step

Members get the full set-up guide for this agent. No technical skills needed: you copy, paste and upload.

10 minto set it up in your AI
5 AIsChatGPT, Claude, Copilot, Gemini, Grok
  • One set of instructions to paste into your AI, with the clicks for ChatGPT, Claude, Microsoft 365 Copilot, Gemini and Grok
  • The agent then walks you through connecting your own data, one source at a time
  • A downloadable copy with the flow chart, the rules and the full guide
Get access to this agent

An example run

What happensTwo tablets were trialed with a 7-year-old. Device A had 6 sessions and Device B had 3 because of a charging fault. The check failed, so the agent marked two B sessions invalid and scheduled 3 more. The final data showed A at 14 messages per session and B at 9, with the caregiver preferring A. The therapist approved A.

More agents for speech therapists