usertold 0.0.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +95 -0
- package/package.json +17 -0
- package/usertold +11900 -0
package/README.md
ADDED
|
@@ -0,0 +1,95 @@
|
|
|
1
|
+
# UserTold.ai CLI
|
|
2
|
+
|
|
3
|
+
Bring human feedback into your agent's decision loop.
|
|
4
|
+
|
|
5
|
+
UserTold.ai is the research layer for autonomous product systems:
|
|
6
|
+
1. design studies
|
|
7
|
+
2. run real-time interviews while users are on your website
|
|
8
|
+
3. extract signals
|
|
9
|
+
4. create evidence-backed tasks
|
|
10
|
+
5. measure impact after release
|
|
11
|
+
|
|
12
|
+
The CLI is the automation-first interface for CI pipelines, agent workflows, and scripted operations.
|
|
13
|
+
|
|
14
|
+
## What interviews look like
|
|
15
|
+
|
|
16
|
+
UserTold.ai conducts real-time interviews while participants actively use your website. The AI operates in three adaptive modes:
|
|
17
|
+
|
|
18
|
+
- **Observe** — Watches silently while the participant navigates, clicks, and thinks aloud. No prompting, no interruption. Captures page changes, interaction events, and spoken thoughts via microphone.
|
|
19
|
+
- **Speak** — Delivers one-way verbal guidance: task instructions, clarifications, a gentle nudge. Stops immediately if the participant starts speaking (barge-in).
|
|
20
|
+
- **Talk** — Full two-way voice conversation via OpenAI Realtime (speech-to-speech). The AI asks follow-up questions, probes emotional moments, and explores unexpected insights in real time.
|
|
21
|
+
|
|
22
|
+
Each study segment defines a base mode and a mode ceiling. The AI escalates automatically when it detects the participant is stuck — using heuristic checks (silence, confusion keywords, navigation loops) that fire in under a second without an API call. After the intervention it returns to the base mode automatically.
|
|
23
|
+
|
|
24
|
+
After each session, the platform extracts structured signals — struggling moments, desired outcomes, workarounds, behavioral context — each with a verbatim quote, confidence score, and a link back to the session recording and transcript timestamp. Signals cluster into tasks. Tasks push to GitHub Issues with evidence attached.
|
|
25
|
+
|
|
26
|
+
## Install
|
|
27
|
+
|
|
28
|
+
```bash
|
|
29
|
+
npm i -g usertold
|
|
30
|
+
usertold --help
|
|
31
|
+
```
|
|
32
|
+
|
|
33
|
+
## Why this CLI
|
|
34
|
+
|
|
35
|
+
- Scriptable and CI-friendly (`--json`, `--yes`)
|
|
36
|
+
- Full workflow coverage: projects, studies, sessions, signals, tasks, screeners
|
|
37
|
+
- Built for agent orchestration and non-interactive runs
|
|
38
|
+
- Works alongside MCP and Web UI
|
|
39
|
+
|
|
40
|
+
## Quick start
|
|
41
|
+
|
|
42
|
+
```bash
|
|
43
|
+
# 1) Authenticate
|
|
44
|
+
usertold auth login
|
|
45
|
+
|
|
46
|
+
# 2) Create project
|
|
47
|
+
usertold project create acme --name "My Product"
|
|
48
|
+
|
|
49
|
+
# 3) Design a study (agent-friendly: read the guide first)
|
|
50
|
+
usertold study guide
|
|
51
|
+
usertold study create acme/my-product --title "Checkout friction study" --type usability --activate
|
|
52
|
+
|
|
53
|
+
# 4) Review completed sessions
|
|
54
|
+
usertold session list acme/my-product --json
|
|
55
|
+
|
|
56
|
+
# 5) Review extracted signals
|
|
57
|
+
usertold signal list acme/my-product --json
|
|
58
|
+
|
|
59
|
+
# 6) Create and push task
|
|
60
|
+
usertold task create-from-signals acme/my-product --title "Fix checkout step confusion" --signals sig_1,sig_2
|
|
61
|
+
usertold task push acme/my-product tsk_123
|
|
62
|
+
```
|
|
63
|
+
|
|
64
|
+
## Agent mode
|
|
65
|
+
|
|
66
|
+
```bash
|
|
67
|
+
usertold init --org acme --name "My Product" --json --yes
|
|
68
|
+
usertold project signal-health acme/my-product --json
|
|
69
|
+
usertold signal bulk-link acme/my-product tsk_123 --signals sig_1,sig_2,sig_3 --json
|
|
70
|
+
```
|
|
71
|
+
|
|
72
|
+
## Core command groups
|
|
73
|
+
|
|
74
|
+
- `auth`
|
|
75
|
+
- `project`
|
|
76
|
+
- `study`
|
|
77
|
+
- `session`
|
|
78
|
+
- `signal`
|
|
79
|
+
- `task`
|
|
80
|
+
- `screener`
|
|
81
|
+
- `overview`
|
|
82
|
+
- `config`
|
|
83
|
+
- `setup`
|
|
84
|
+
- `billing`
|
|
85
|
+
|
|
86
|
+
Run `usertold <group> --help` for details.
|
|
87
|
+
|
|
88
|
+
## Requirements
|
|
89
|
+
|
|
90
|
+
- Node.js 18+
|
|
91
|
+
|
|
92
|
+
## Links
|
|
93
|
+
|
|
94
|
+
- Docs: https://usertold.ai/docs/getting-started
|
|
95
|
+
- CLI reference: https://usertold.ai/docs/cli-reference
|
package/package.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
1
|
+
{
|
|
2
|
+
"name": "usertold",
|
|
3
|
+
"version": "0.0.0",
|
|
4
|
+
"description": "UserTold.ai CLI",
|
|
5
|
+
"license": "UNLICENSED",
|
|
6
|
+
"type": "module",
|
|
7
|
+
"bin": {
|
|
8
|
+
"usertold": "usertold"
|
|
9
|
+
},
|
|
10
|
+
"files": [
|
|
11
|
+
"usertold",
|
|
12
|
+
"README.md"
|
|
13
|
+
],
|
|
14
|
+
"engines": {
|
|
15
|
+
"node": ">=18"
|
|
16
|
+
}
|
|
17
|
+
}
|